Commit ·
b5e2df3
0
Parent(s):
Super-squash branch 'main' using huggingface_hub
Browse files- .gitattributes +36 -0
- README.md +259 -0
- chat_template.jinja +102 -0
- config.json +121 -0
- generation_config.json +7 -0
- model-00001-of-00015.safetensors +3 -0
- model-00002-of-00015.safetensors +3 -0
- model-00003-of-00015.safetensors +3 -0
- model-00004-of-00015.safetensors +3 -0
- model-00005-of-00015.safetensors +3 -0
- model-00006-of-00015.safetensors +3 -0
- model-00007-of-00015.safetensors +3 -0
- model-00008-of-00015.safetensors +3 -0
- model-00009-of-00015.safetensors +3 -0
- model-00010-of-00015.safetensors +3 -0
- model-00011-of-00015.safetensors +3 -0
- model-00012-of-00015.safetensors +3 -0
- model-00013-of-00015.safetensors +3 -0
- model-00014-of-00015.safetensors +3 -0
- model-00015-of-00015.safetensors +3 -0
- model.safetensors.index.json +1034 -0
- tokenizer.json +3 -0
- tokenizer_config.json +15 -0
.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- hybrid
|
| 7 |
+
- ssm
|
| 8 |
+
- state-space-model
|
| 9 |
+
- linear-attention
|
| 10 |
+
- gated-kalmanet
|
| 11 |
+
- priming
|
| 12 |
+
- long-context
|
| 13 |
+
- reasoning
|
| 14 |
+
base_model: Qwen/Qwen3-32B
|
| 15 |
+
paper:
|
| 16 |
+
- https://arxiv.org/abs/2511.21016
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
# GKA-primed-HQwen3-32B-Reasoner
|
| 21 |
+
|
| 22 |
+
GKA-primed-HQwen3-32B-Reasoner is a Hybrid language model consisting of 50% Attention layers and 50% [Gated KalmaNet (GKA)](https://arxiv.org/abs/2511.21016) layers, primed from [Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) using the [Hybrid Model Factory](https://github.com/awslabs/hybrid-model-factory) Priming pipeline. The model is trained for long-context reasoning and supports context lengths of 128K tokens.
|
| 23 |
+
|
| 24 |
+
GKA (pronounced as gee-ka) is a State-Space Model layer inspired by the Kalman Filter that solves an online ridge regression problem at test time, with constant
|
| 25 |
+
memory and linear compute cost in the sequence length.
|
| 26 |
+
|
| 27 |
+
By combining Attention with GKA, our Hybrid model achieves up to **2× faster inference** at long contexts while **closely matching the base Transformer's quality**.
|
| 28 |
+
|
| 29 |
+
## Links
|
| 30 |
+
|
| 31 |
+
- 📄 [Gated KalmaNet paper (CVPR 2026)](https://arxiv.org/abs/2511.21016)
|
| 32 |
+
- 💻 [GitHub: Hybrid Model Factory](https://github.com/awslabs/hybrid-model-factory)
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
## Why Hybrid?
|
| 36 |
+
|
| 37 |
+
Each Primed Hybrid model is initialized from a base Transformer by converting a portion of its Attention layers into State-Space Model (SSM) layers that maintain a fixed-size recurrent state instead of a growing KV cache. At a 50% Hybrid ratio, roughly half the KV cache (which grows linearly with sequence length) is replaced with fixed-size SSM state. The practical benefits:
|
| 38 |
+
|
| 39 |
+
- **Higher throughput at long contexts** — less memory on KV cache means more memory for batching
|
| 40 |
+
- **More concurrent sequences** — ~2× as many concurrent sequences before hitting memory limits
|
| 41 |
+
- **Growing advantage with context length** — at long contexts, Attention dominates the forward pass while SSM layers remain negligible in cost. Since the Hybrid model makes roughly half as many Attention calls as the base Transformer, the throughput advantage grows with context length
|
| 42 |
+
|
| 43 |
+
Increasing hybridization ratio, replacing more Attention layers with SSM layers, further reduces memory and increases throughput, typically at the expense of performance.
|
| 44 |
+
|
| 45 |
+
## Model Overview
|
| 46 |
+
|
| 47 |
+
- **Type**: Causal Language Model (Hybrid Attention + SSM)
|
| 48 |
+
- **Base Model**: Qwen3-32B
|
| 49 |
+
- **Hybrid Layer Type**: Gated KalmaNet (GKA)
|
| 50 |
+
- **Hybrid Ratio**: 50% (32 Attention + 32 GKA layers)
|
| 51 |
+
- **Parameters**: ~32B
|
| 52 |
+
- **Context Length**: 128K natively
|
| 53 |
+
- **Precision**: bfloat16
|
| 54 |
+
- **License**: Apache 2.0
|
| 55 |
+
|
| 56 |
+
## Benchmark Results
|
| 57 |
+
|
| 58 |
+
We consider the following Transformer as a baseline:
|
| 59 |
+
|
| 60 |
+
1. **Qwen3-32B (thinking, from HF)**: The original Qwen model evaluated in thinking mode, which is the intended mode for reasoning tasks. This serves as the base Transformer from which we start the Priming procedure.
|
| 61 |
+
|
| 62 |
+
### Reasoning Benchmarks
|
| 63 |
+
|
| 64 |
+
Evaluations on math reasoning (AIME24/25), science (GPQA), coding (LiveCodeBenchv5, Scicode), tool-calling (BFCLv3/v4), and instruction-following (IFBench). Evaluations are done using the [Nemo Evaluator SDK](https://docs.nvidia.com/nemo/evaluator/latest/). We have provided the evaluation configuration [examples/evaluation/nemo_reasoning_evals.yaml](https://github.com/awslabs/hybrid-model-factory/blob/main/examples/evaluation/nemo_reasoning_evals.yaml) for reproducibility. Evaluations are done at 64K generation length.
|
| 65 |
+
|
| 66 |
+
| Model | AIME24 | AIME25 | GPQA | LiveCodeBench-v5 | BFCLv4 (minus web-search) | BFCLv3 | IFBench | SciCode | Average |
|
| 67 |
+
|-------|------|-----------|--------|-----------|----------|------|----|-----|-----|
|
| 68 |
+
| Qwen3-32B (thinking, from HF) | 86.33 | 70.00 | 65.40 | 64.44 | 69.30 | 69.57 | 32.61 | 15.94 | 59.20 |
|
| 69 |
+
| GKA-primed-HQwen3-32B-Reasoner | 87.67 | 81.67 | 67.30 | 70.24 | 70.14 | 66.34 | 48.22 | 12.34 | 62.99 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
*For BFCLv4, we remove the web-search subtask and weight each task by the number of entries (test examples) for that task:* \\(\text{Overall Accuracy} = \sum_i \left(\text{accuracy}_i \times \text{num\_entries}_i\right) / \sum_i \text{num\_entries}_i\\)
|
| 73 |
+
|
| 74 |
+
**How close is the Hybrid model to the Transformer baseline on complex reasoning tasks?**
|
| 75 |
+
Our Primed GKA Hybrid **outperforms the Qwen3-32B (thinking, from HF) baseline** by ~3.8 points on average, despite using [<0.5% of the base Transformer's pre-training token budget](#training-data). This is enabled by our multi-stage reasoning training pipeline coupled with higher throughput of Hybrid architectures.
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
## About Gated KalmaNet (GKA)
|
| 79 |
+
|
| 80 |
+
Gated KalmaNet is a recently proposed SSM layer that is more expressive than both Mamba2 and Gated DeltaNet. GKA achieves this by employing the Kalman Filter to compute the optimal state at each time-step based on the entire past. In contrast, SSMs like Mamba2 and GDN rely on instantaneous objectives (that rely *solely* on the current input and loss estimate of the past) to compute their state.
|
| 81 |
+
|
| 82 |
+
Unlike other SSM-based hybrid layers, GKA gives you a runtime knob for trading compute against speed — with no retraining nor architecture changes. The `num_iter` parameter controls how many iterations the GKA solver runs during inference. No other hybrid layer type offers this: GDN and Mamba2 have fixed compute per layer, so their speed is fixed a priori. GKA lets you slide along the compute–latency curve per deployment, making it uniquely suited for scenarios where different endpoints or traffic tiers have different latency budgets.
|
| 83 |
+
|
| 84 |
+
For details on controlling GKA's compute–speed tradeoff at serving time via `num_iter`, see [GKA Compute Control](https://github.com/awslabs/hybrid-model-factory/blob/main/docs/Inference.md#gka-compute-control-num_iter), and for more details on the modelling choices see the [GKA paper](https://arxiv.org/abs/2511.21016).
|
| 85 |
+
|
| 86 |
+
This release includes optimized Triton kernels for GKA's Chebyshev solver, enabling the throughput numbers reported in [Inference Efficiency](#inference-efficiency). The training kernels are in [`training/.../gated_kalmanet/ops/chebyshev/`](https://github.com/awslabs/hybrid-model-factory/tree/main/training/src/hmf/model/hybrid_zoo/layers/gated_kalmanet/ops/chebyshev) and the inference kernels in [`vllm-inference/.../gka/ops/`](https://github.com/awslabs/hybrid-model-factory/tree/main/vllm-inference/src/primed_vllm/gka/ops).
|
| 87 |
+
|
| 88 |
+
### Architecture Details
|
| 89 |
+
|
| 90 |
+
| Component | Details |
|
| 91 |
+
|-----------|------------------------------------------------------------------------------|
|
| 92 |
+
| Number of Layers | 64 (32 Attention + 32 GKA) |
|
| 93 |
+
| Hidden Dimension | 5120 |
|
| 94 |
+
| Attention Heads | 64 (Q) / 8 (KV) |
|
| 95 |
+
| Head Dimension | 128 |
|
| 96 |
+
| Intermediate Dimension (FFN) | 25600 |
|
| 97 |
+
| Vocabulary Size | 151,936 |
|
| 98 |
+
| Position Encoding | RoPE (θ = 5,000,000) |
|
| 99 |
+
| Layer Layout | GKA layer indices were selected with our [*selective hybridization*](https://github.com/awslabs/hybrid-model-factory/blob/main/docs/LayerSelection.md) procedure |
|
| 100 |
+
|
| 101 |
+
### Trade-off inference FLOPs for accuracy.
|
| 102 |
+
As discussed above, GKA offers the unique ability to adjust the inference FLOPs by tuning the `num_iter` parameter. Here we summarize reasoning performance across different `num_iter` settings.
|
| 103 |
+
|
| 104 |
+
| Model | Avg. Reasoning Performance |
|
| 105 |
+
|---------------------------------------------------------|----------------------------|
|
| 106 |
+
| GKA-primed-HQwen3-32B-Reasoner (`num_iter=30`, default) | 62.99 |
|
| 107 |
+
| GKA-primed-HQwen3-32B-Reasoner (`num_iter=10`) | 62.63 |
|
| 108 |
+
| GKA-primed-HQwen3-32B-Reasoner (`num_iter=5`) | 61.77 |
|
| 109 |
+
| GKA-primed-HQwen3-32B-Reasoner (`num_iter=1`) | 60.04 |
|
| 110 |
+
| Qwen3-32B (thinking, from HF) | 59.20 |
|
| 111 |
+
|
| 112 |
+
For most practical scenarios, we recommend setting `num_iter=10` for the best trade-off. See next section for inference gains upon reducing number of iterations.
|
| 113 |
+
|
| 114 |
+
> [!NOTE]
|
| 115 |
+
> Interestingly, setting `num_iter=0` effectively converts the GKA model to a Gated Linear Attention (GLA) model. Thus, one can think of increasing num iters as improving upon the initial solution of the GLA model.
|
| 116 |
+
|
| 117 |
+
### Inference Efficiency
|
| 118 |
+
|
| 119 |
+
Sustained decode throughput (tokens/s) on 8× H200 GPUs (TP=8), measured during pure decode with a saturated KV cache. Benchmarked with random data (no prefix-caching benefits). See the full [Inference guide](https://github.com/awslabs/hybrid-model-factory/blob/main/docs/Inference.md#performance-benchmarks) for methodology and additional models.
|
| 120 |
+
|
| 121 |
+
| Model | 16K | 32K | 64K | 128K |
|
| 122 |
+
|-----------------------------------------------------------|---------------|---------------|---------------|---------------|
|
| 123 |
+
| GKA-primed-HQwen3-32B-Reasoner (`num_iter=30`, default) | 6,810 (1.29×) | 4,152 (1.45×) | 2,385 (1.82×) | 1,168 (1.99×) |
|
| 124 |
+
| GKA-primed-HQwen3-32B-Reasoner (`num_iter=10`) | 7,778 (1.47×) | 4,534 (1.58×) | 2,537 (1.94×) | 1,200 (2.05×) |
|
| 125 |
+
| GKA-primed-HQwen3-32B-Reasoner (`num_iter=5`) | 8,039 (1.52×) | 4,621 (1.61×) | 2,569 (1.96×) | 1,206 (2.06×) |
|
| 126 |
+
| GKA-primed-HQwen3-32B-Reasoner (`num_iter=1`) | 8,177 (1.54×) | 4,678 (1.63×) | 2,593 (1.98×) | 1,210 (2.06×) |
|
| 127 |
+
| GDN-primed-HQwen3-32B | 8,133 (1.53×) | 4,876 (1.70×) | 2,688 (2.06×) | 1,238 (2.11×) |
|
| 128 |
+
| Qwen3-32B (thinking, from HF) | 5,299 | 2,865 | 1,308 | 586 |
|
| 129 |
+
|
| 130 |
+
Mean TTFT at the Transformer's saturated batch size (Hybrid model has memory to spare):
|
| 131 |
+
|
| 132 |
+
| Model | 16K | 32K | 64K | 128K |
|
| 133 |
+
|-----------------------------------------------------------|-------------------|-------------------|-------------------|-------------------|
|
| 134 |
+
| GKA-primed-HQwen3-32B-Reasoner (`num_iter=30`, default) | 52,053 ms (1.32×) | 58,613 ms (1.21×) | 68,241 ms (1.05×) | 84,935 ms (0.90×) |
|
| 135 |
+
| GKA-primed-HQwen3-32B-Reasoner (`num_iter=10`) | 48,560 ms (1.23×) | 55,039 ms (1.13×) | 64,766 ms (0.99×) | 81,410 ms (0.86×) |
|
| 136 |
+
| GKA-primed-HQwen3-32B-Reasoner (`num_iter=5`) | 47,958 ms (1.22×) | 54,320 ms (1.12×) | 63,826 ms (0.98×) | 80,369 ms (0.85×) |
|
| 137 |
+
| GKA-primed-HQwen3-32B-Reasoner (`num_iter=1`) | 46,726 ms (1.19×) | 53,061 ms (1.09×) | 62,645 ms (0.96×) | 79,321 ms (0.84×) |
|
| 138 |
+
| GDN-primed-HQwen3-32B | 42,492 ms (1.08×) | 48,417 ms (1.00×) | 57,525 ms (0.88×) | 73,145 ms (0.77×) |
|
| 139 |
+
| Qwen3-32B (thinking, from HF) | 39,421 ms | 48,527 ms | 65,104 ms | 94,479 ms |
|
| 140 |
+
|
| 141 |
+
The decode throughput advantage grows with context length — from 1.29× at 16K to 1.99× at 128K (2.06× with `num_iter=1`) — thanks to GKA layers maintaining a fixed-size recurrent state instead of a growing KV cache. TTFT crosses over at long contexts: GKA prefills 10–16% faster than the Transformer at 128K depending on `num_iter`. Reducing `num_iter` progressively improves both decode and TTFT, with the effect more pronounced at 32B than 8B. See [Trade-off inference FLOPs for accuracy](#trade-off-inference-flops-for-accuracy) for details.
|
| 142 |
+
|
| 143 |
+
|
| 144 |
+
## Usage
|
| 145 |
+
|
| 146 |
+
### With vLLM (recommended)
|
| 147 |
+
|
| 148 |
+
Install the [Hybrid Model Factory vLLM plugin](https://github.com/awslabs/hybrid-model-factory/blob/main/docs/Inference.md#docker-recommended) in your local environment, then serve:
|
| 149 |
+
|
| 150 |
+
```bash
|
| 151 |
+
vllm serve amazon/GKA-primed-HQwen3-32B-Reasoner \
|
| 152 |
+
--enable-prefix-caching \
|
| 153 |
+
--mamba-cache-mode align \
|
| 154 |
+
--mamba-cache-dtype float32 \
|
| 155 |
+
--mamba-ssm-cache-dtype float32 \
|
| 156 |
+
--enable-auto-tool-choice \
|
| 157 |
+
--tool-call-parser hermes \
|
| 158 |
+
--reasoning-parser qwen3
|
| 159 |
+
```
|
| 160 |
+
|
| 161 |
+
Query the server:
|
| 162 |
+
|
| 163 |
+
```bash
|
| 164 |
+
curl http://localhost:8000/v1/chat/completions \
|
| 165 |
+
-H "Content-Type: application/json" \
|
| 166 |
+
-d '{
|
| 167 |
+
"model": "amazon/GKA-primed-HQwen3-32B-Reasoner",
|
| 168 |
+
"messages": [
|
| 169 |
+
{"role": "user", "content": "What is Linear Attention in the context of LLMs?"}
|
| 170 |
+
],
|
| 171 |
+
"temperature": 1.0,
|
| 172 |
+
"top_p": 1.0
|
| 173 |
+
}'
|
| 174 |
+
```
|
| 175 |
+
|
| 176 |
+
> [!TIP]
|
| 177 |
+
> The `--mamba-cache-dtype float32` and `--mamba-ssm-cache-dtype float32` flags are important for accurate long-context generation. See the [Inference guide](https://github.com/awslabs/hybrid-model-factory/blob/main/docs/Inference.md#recommended-flags-for-hybrid-models) for details on all recommended flags.
|
| 178 |
+
|
| 179 |
+
> [!TIP]
|
| 180 |
+
> Similarly to [NVIDIA-Nemotron-3-Nano-30B-A3B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16), for generic reasoning tasks (e.g. Math, Science) we recommend setting `temperature=1.0` and `top_p=1.0`. For tool-calling we recommend `temperature=0.6`, `top_p=0.95`.
|
| 181 |
+
|
| 182 |
+
#### Thinking Versus Non-thinking Setting
|
| 183 |
+
|
| 184 |
+
Our reasoning model supports thinking on/off modes. Whenever thinking mode is on, the model will reason for multiple tokens in a segment delimited by `<think>` and `</think>` (which is extracted by the reasoning parser) before producing a response. This is necessary for difficult queries and increases response quality at the expense of higher latency. Thinking mode is enabled by default, however thinking mode can be turned off via the chat template.
|
| 185 |
+
|
| 186 |
+
If you want to query the model with thinking mode *off*, query the model as follows:
|
| 187 |
+
|
| 188 |
+
```bash
|
| 189 |
+
curl http://localhost:8000/v1/chat/completions \
|
| 190 |
+
-H "Content-Type: application/json" \
|
| 191 |
+
-d '{
|
| 192 |
+
"model": "amazon/GKA-primed-HQwen3-32B-Reasoner",
|
| 193 |
+
"messages": [
|
| 194 |
+
{"role": "user", "content": "What is Linear Attention in the context of LLMs?"}
|
| 195 |
+
],
|
| 196 |
+
"chat_template_kwargs": {"enable_thinking": false}
|
| 197 |
+
}'
|
| 198 |
+
```
|
| 199 |
+
|
| 200 |
+
### With HuggingFace Transformers
|
| 201 |
+
|
| 202 |
+
> [!WARNING]
|
| 203 |
+
> Due to the long generations produced by reasoning models, the lower latency provided by vLLM is preferred over Huggingface for evaluations and in production settings. We recommend Huggingface generation primarily for quick debugging or testing.
|
| 204 |
+
|
| 205 |
+
```python
|
| 206 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 207 |
+
import hmf.model.hybrid_zoo.models.model_register # Register Hybrid models
|
| 208 |
+
|
| 209 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 210 |
+
"amazon/GKA-primed-HQwen3-32B-Reasoner", trust_remote_code=True
|
| 211 |
+
).to("cuda")
|
| 212 |
+
tokenizer = AutoTokenizer.from_pretrained("amazon/GKA-primed-HQwen3-32B-Reasoner")
|
| 213 |
+
|
| 214 |
+
messages = [{"role": "user", "content": "What is linear attention in the context of LLMs?"}]
|
| 215 |
+
prompt = tokenizer.apply_chat_template(
|
| 216 |
+
messages, tokenize=False, add_generation_prompt=True, enable_thinking=True
|
| 217 |
+
)
|
| 218 |
+
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
|
| 219 |
+
outputs = model.generate(**inputs, max_new_tokens=65536, temperature=1.0, top_p=1.0)
|
| 220 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
| 221 |
+
```
|
| 222 |
+
|
| 223 |
+
In order to turn thinking mode off, simply specify `enable_thinking=False` when applying the chat template:
|
| 224 |
+
```python
|
| 225 |
+
messages = [{"role": "user", "content": "What is linear attention in the context of LLMs?"}]
|
| 226 |
+
prompt = tokenizer.apply_chat_template(
|
| 227 |
+
messages, tokenize=False, add_generation_prompt=True, enable_thinking=False
|
| 228 |
+
)
|
| 229 |
+
```
|
| 230 |
+
|
| 231 |
+
## Training data
|
| 232 |
+
These models were produced through the multi-stage Priming pipeline from [Hybrid Model Factory](https://github.com/awslabs/hybrid-model-factory). Training data spans web documents, mathematics, long-context documents, and instruction-following and reasoning examples — each targeting a different capability axis. This diversity is critical: it allows the Priming procedure to convert a base Transformer into a more memory- and compute-efficient Hybrid architecture at nearly the same level of performance, using < 0.5% of the base Transformer model's pre-training token budget.
|
| 233 |
+
|
| 234 |
+
|
| 235 |
+
## Responsible AI Considerations
|
| 236 |
+
At Amazon, we are committed to developing AI responsibly and take a people-centric approach that prioritizes education, science, and our customers, to integrate responsible AI across the end-to-end AI lifecycle. We believe the use of AI must respect the rule of law and human rights, and we encourage the safe and responsible development of AI. When downloaded or used in accordance with [AWS Responsible AI Policy](https://aws.amazon.com/ai/responsible-ai/policy/), developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
|
| 237 |
+
Please report model quality, risk, security vulnerabilities or Amazon AI Concerns [here](https://pages.awscloud.com/global-ln-gc-400-ai-service-cards-contact-us-registration.html).
|
| 238 |
+
|
| 239 |
+
## Citation
|
| 240 |
+
|
| 241 |
+
```bibtex
|
| 242 |
+
@software{hybrid_model_factory,
|
| 243 |
+
title = {Hybrid Model Factory},
|
| 244 |
+
year = {2026},
|
| 245 |
+
url = {https://github.com/awslabs/hybrid-model-factory}
|
| 246 |
+
}
|
| 247 |
+
|
| 248 |
+
@inproceedings{gka2026,
|
| 249 |
+
title = {Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression},
|
| 250 |
+
year = {2026},
|
| 251 |
+
booktitle = {CVPR},
|
| 252 |
+
url = {https://arxiv.org/abs/2511.21016}
|
| 253 |
+
}
|
| 254 |
+
|
| 255 |
+
```
|
| 256 |
+
|
| 257 |
+
## License
|
| 258 |
+
|
| 259 |
+
This model is licensed under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 7 |
+
{{- 'detailed thinking off\n\n' }}
|
| 8 |
+
{%- else %}
|
| 9 |
+
{{- 'detailed thinking on\n\n' }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 12 |
+
{%- for tool in tools %}
|
| 13 |
+
{{- "\n" }}
|
| 14 |
+
{{- tool | tojson }}
|
| 15 |
+
{%- endfor %}
|
| 16 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>" }}
|
| 17 |
+
{{- '<|im_end|>\n' }}
|
| 18 |
+
{%- else %}
|
| 19 |
+
{{- '<|im_start|>system\n' }}
|
| 20 |
+
{%- if messages[0].role == 'system' %}
|
| 21 |
+
{{- messages[0].content + '\n' }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 24 |
+
{{- 'detailed thinking off' }}
|
| 25 |
+
{%- else %}
|
| 26 |
+
{{- 'detailed thinking on' }}
|
| 27 |
+
{%- endif %}
|
| 28 |
+
{{- '<|im_end|>\n' }}
|
| 29 |
+
{%- endif %}
|
| 30 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 31 |
+
{%- for message in messages[::-1] %}
|
| 32 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 33 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 34 |
+
{%- set ns.multi_step_tool = false %}
|
| 35 |
+
{%- set ns.last_query_index = index %}
|
| 36 |
+
{%- endif %}
|
| 37 |
+
{%- endfor %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.content is string %}
|
| 40 |
+
{%- set content = message.content %}
|
| 41 |
+
{%- else %}
|
| 42 |
+
{%- set content = '' %}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 46 |
+
{%- elif message.role == "assistant" %}
|
| 47 |
+
{%- set reasoning_content = '' %}
|
| 48 |
+
{%- if message.reasoning_content is string %}
|
| 49 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 50 |
+
{%- else %}
|
| 51 |
+
{%- if '</think>' in content %}
|
| 52 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 53 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 54 |
+
{%- endif %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 57 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 58 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 59 |
+
{%- else %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- else %}
|
| 63 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 64 |
+
{%- endif %}
|
| 65 |
+
{%- if message.tool_calls %}
|
| 66 |
+
{%- for tool_call in message.tool_calls %}
|
| 67 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 68 |
+
{{- '\n' }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if tool_call.function %}
|
| 71 |
+
{%- set tool_call = tool_call.function %}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 74 |
+
{{- tool_call.name }}
|
| 75 |
+
{{- '", "arguments": ' }}
|
| 76 |
+
{%- if tool_call.arguments is string %}
|
| 77 |
+
{{- tool_call.arguments }}
|
| 78 |
+
{%- else %}
|
| 79 |
+
{{- tool_call.arguments | tojson }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{{- '}\n</tool_call>' }}
|
| 82 |
+
{%- endfor %}
|
| 83 |
+
{%- endif %}
|
| 84 |
+
{{- '<|im_end|>\n' }}
|
| 85 |
+
{%- elif message.role == "tool" %}
|
| 86 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 87 |
+
{{- '<|im_start|>user' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '\n<tool_response>\n' }}
|
| 90 |
+
{{- content }}
|
| 91 |
+
{{- '\n</tool_response>' }}
|
| 92 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 93 |
+
{{- '<|im_end|>\n' }}
|
| 94 |
+
{%- endif %}
|
| 95 |
+
{%- endif %}
|
| 96 |
+
{%- endfor %}
|
| 97 |
+
{%- if add_generation_prompt %}
|
| 98 |
+
{{- '<|im_start|>assistant\n' }}
|
| 99 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 100 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 101 |
+
{%- endif %}
|
| 102 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridQwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"gka_config": {
|
| 11 |
+
"bp_lambda": true,
|
| 12 |
+
"chunk_size": 64,
|
| 13 |
+
"conv_size": 4,
|
| 14 |
+
"gla_rescale": true,
|
| 15 |
+
"head_dim": 128,
|
| 16 |
+
"hidden_size": 5120,
|
| 17 |
+
"norm_eps": 1e-06,
|
| 18 |
+
"num_iter": 30,
|
| 19 |
+
"num_k_heads": 8,
|
| 20 |
+
"num_q_heads": 64,
|
| 21 |
+
"num_v_heads": 8,
|
| 22 |
+
"ridge_strength": 0.02,
|
| 23 |
+
"solver_type": "chebyshev",
|
| 24 |
+
"use_alpha_connection": true,
|
| 25 |
+
"use_beta_gate": true,
|
| 26 |
+
"use_forgetting_gate": true,
|
| 27 |
+
"use_forgetting_gate_kk": true,
|
| 28 |
+
"use_gate": true,
|
| 29 |
+
"use_v_conv": true
|
| 30 |
+
},
|
| 31 |
+
"head_dim": 128,
|
| 32 |
+
"hidden_act": "silu",
|
| 33 |
+
"hidden_size": 5120,
|
| 34 |
+
"hybrid_override_pattern": "*-*-GKA-GKA-*-*-*-GKA-GKA-GKA-GKA-GKA-GKA-GKA-GKA-GKA-GKA-*-*-*-GKA-*-GKA-GKA-GKA-*-GKA-GKA-GKA-GKA-*-*-GKA-GKA-*-GKA-GKA-*-*-GKA-GKA-GKA-*-GKA-GKA-*-*-*-*-*-*-*-*-*-*-*-*-GKA-*-*-GKA-*-*-GKA",
|
| 35 |
+
"initializer_range": 0.02,
|
| 36 |
+
"intermediate_size": 25600,
|
| 37 |
+
"layer_types": [
|
| 38 |
+
"*",
|
| 39 |
+
"*",
|
| 40 |
+
"GKA",
|
| 41 |
+
"GKA",
|
| 42 |
+
"*",
|
| 43 |
+
"*",
|
| 44 |
+
"*",
|
| 45 |
+
"GKA",
|
| 46 |
+
"GKA",
|
| 47 |
+
"GKA",
|
| 48 |
+
"GKA",
|
| 49 |
+
"GKA",
|
| 50 |
+
"GKA",
|
| 51 |
+
"GKA",
|
| 52 |
+
"GKA",
|
| 53 |
+
"GKA",
|
| 54 |
+
"GKA",
|
| 55 |
+
"*",
|
| 56 |
+
"*",
|
| 57 |
+
"*",
|
| 58 |
+
"GKA",
|
| 59 |
+
"*",
|
| 60 |
+
"GKA",
|
| 61 |
+
"GKA",
|
| 62 |
+
"GKA",
|
| 63 |
+
"*",
|
| 64 |
+
"GKA",
|
| 65 |
+
"GKA",
|
| 66 |
+
"GKA",
|
| 67 |
+
"GKA",
|
| 68 |
+
"*",
|
| 69 |
+
"*",
|
| 70 |
+
"GKA",
|
| 71 |
+
"GKA",
|
| 72 |
+
"*",
|
| 73 |
+
"GKA",
|
| 74 |
+
"GKA",
|
| 75 |
+
"*",
|
| 76 |
+
"*",
|
| 77 |
+
"GKA",
|
| 78 |
+
"GKA",
|
| 79 |
+
"GKA",
|
| 80 |
+
"*",
|
| 81 |
+
"GKA",
|
| 82 |
+
"GKA",
|
| 83 |
+
"*",
|
| 84 |
+
"*",
|
| 85 |
+
"*",
|
| 86 |
+
"*",
|
| 87 |
+
"*",
|
| 88 |
+
"*",
|
| 89 |
+
"*",
|
| 90 |
+
"*",
|
| 91 |
+
"*",
|
| 92 |
+
"*",
|
| 93 |
+
"*",
|
| 94 |
+
"*",
|
| 95 |
+
"GKA",
|
| 96 |
+
"*",
|
| 97 |
+
"*",
|
| 98 |
+
"GKA",
|
| 99 |
+
"*",
|
| 100 |
+
"*",
|
| 101 |
+
"GKA"
|
| 102 |
+
],
|
| 103 |
+
"max_position_embeddings": 131072,
|
| 104 |
+
"max_window_layers": 64,
|
| 105 |
+
"model_type": "hybrid_qwen3",
|
| 106 |
+
"num_attention_heads": 64,
|
| 107 |
+
"num_hidden_layers": 64,
|
| 108 |
+
"num_key_value_heads": 8,
|
| 109 |
+
"pad_token_id": null,
|
| 110 |
+
"rms_norm_eps": 1e-06,
|
| 111 |
+
"rope_parameters": {
|
| 112 |
+
"rope_theta": 5000000,
|
| 113 |
+
"rope_type": "default"
|
| 114 |
+
},
|
| 115 |
+
"sliding_window": null,
|
| 116 |
+
"tie_word_embeddings": false,
|
| 117 |
+
"transformers_version": "5.3.0",
|
| 118 |
+
"use_cache": false,
|
| 119 |
+
"use_sliding_window": false,
|
| 120 |
+
"vocab_size": 151936
|
| 121 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": 151645,
|
| 5 |
+
"transformers_version": "4.51.3",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
model-00001-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:478cec5089c8f65c97ebdfcbba77f82bda3c26a3892ee0a49995010b4542db14
|
| 3 |
+
size 4829518760
|
model-00002-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b475b8aea354cc8ac54ee23ca0fe44f7dfcbe6c81b97ad1364ea1bd3d92ffa9a
|
| 3 |
+
size 4785716232
|
model-00003-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c35391cbea643bec0be9c48c7c95b2a2f777f574e8ecdbf0f58ff82cd88accd
|
| 3 |
+
size 4768821432
|
model-00004-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cb6ff1a978dfae5947c5f0b3f4587eb40335e08547470b13c3da1d484f9bd2f
|
| 3 |
+
size 4970102496
|
model-00005-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:684b9dffd9d8cc64df58a62b374ab3a0a61dd11b547ad504592d16a60f4ac376
|
| 3 |
+
size 4773200928
|
model-00006-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ad9e54dce88233680e44c7ff8fc99f12a21326e4f239fe150f041bd1d99aa97
|
| 3 |
+
size 4945030664
|
model-00007-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71d5076ceee0f0c0e30fdb093bcfba3a0b0c05cfbc49dff433c73d323dc097c4
|
| 3 |
+
size 4884166672
|
model-00008-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40452ed9c358aa4f265a21076b6e6b1a0f8104d12b24d8d60004bd76d0a51a2e
|
| 3 |
+
size 4945071672
|
model-00009-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc3d567871f9920acd67c20823b4a3a13d1500e889165f45b4d2aed9432ea5c7
|
| 3 |
+
size 4871651688
|
model-00010-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99b013d4b035929154f1cacd3ad36cb7d7b5a43289dfccb99abe66568d1930e7
|
| 3 |
+
size 4871610264
|
model-00011-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40d49a3c53df9a3972f57f329c40eff612b840b928417f35780b72e6f11025fc
|
| 3 |
+
size 4875989720
|
model-00012-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5e12c0ff19cc950cc76a7416a9927916285f4ac4b304361a4ed5b84c58b3d5a
|
| 3 |
+
size 4875989720
|
model-00013-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6eb490d766b6b254b5478020df5096dd96874fb0f63fad5a4d1fc0576cfba00f
|
| 3 |
+
size 4773200928
|
model-00014-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9db6929d470db5d6abccde0d233cc02794de60585faa7983278bb11ae072905b
|
| 3 |
+
size 3548363864
|
model-00015-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32a177f7e42cdf5d80fa75d653b87965c786f8f0458164d4c754b62e8171d670
|
| 3 |
+
size 1555824736
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1034 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 68274145280
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00015-of-00015.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00015.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00015.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00015.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
| 19 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00015.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00015.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
| 30 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 31 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
| 32 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
| 33 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
| 34 |
+
"model.layers.10.gka.A_log": "model-00003-of-00015.safetensors",
|
| 35 |
+
"model.layers.10.gka.a_proj.weight": "model-00003-of-00015.safetensors",
|
| 36 |
+
"model.layers.10.gka.alpha_proj.bias": "model-00003-of-00015.safetensors",
|
| 37 |
+
"model.layers.10.gka.alpha_proj.weight": "model-00003-of-00015.safetensors",
|
| 38 |
+
"model.layers.10.gka.b_proj.bias": "model-00003-of-00015.safetensors",
|
| 39 |
+
"model.layers.10.gka.b_proj.weight": "model-00003-of-00015.safetensors",
|
| 40 |
+
"model.layers.10.gka.dt_bias": "model-00003-of-00015.safetensors",
|
| 41 |
+
"model.layers.10.gka.g_proj.weight": "model-00003-of-00015.safetensors",
|
| 42 |
+
"model.layers.10.gka.k_conv1d.weight": "model-00003-of-00015.safetensors",
|
| 43 |
+
"model.layers.10.gka.k_proj.weight": "model-00003-of-00015.safetensors",
|
| 44 |
+
"model.layers.10.gka.o_norm.weight": "model-00003-of-00015.safetensors",
|
| 45 |
+
"model.layers.10.gka.o_proj.weight": "model-00003-of-00015.safetensors",
|
| 46 |
+
"model.layers.10.gka.q_conv1d.weight": "model-00003-of-00015.safetensors",
|
| 47 |
+
"model.layers.10.gka.q_proj.weight": "model-00003-of-00015.safetensors",
|
| 48 |
+
"model.layers.10.gka.v_conv1d.weight": "model-00003-of-00015.safetensors",
|
| 49 |
+
"model.layers.10.gka.v_proj.weight": "model-00003-of-00015.safetensors",
|
| 50 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 51 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 52 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
| 53 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
| 54 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
| 55 |
+
"model.layers.11.gka.A_log": "model-00003-of-00015.safetensors",
|
| 56 |
+
"model.layers.11.gka.a_proj.weight": "model-00003-of-00015.safetensors",
|
| 57 |
+
"model.layers.11.gka.alpha_proj.bias": "model-00003-of-00015.safetensors",
|
| 58 |
+
"model.layers.11.gka.alpha_proj.weight": "model-00003-of-00015.safetensors",
|
| 59 |
+
"model.layers.11.gka.b_proj.bias": "model-00003-of-00015.safetensors",
|
| 60 |
+
"model.layers.11.gka.b_proj.weight": "model-00003-of-00015.safetensors",
|
| 61 |
+
"model.layers.11.gka.dt_bias": "model-00003-of-00015.safetensors",
|
| 62 |
+
"model.layers.11.gka.g_proj.weight": "model-00003-of-00015.safetensors",
|
| 63 |
+
"model.layers.11.gka.k_conv1d.weight": "model-00003-of-00015.safetensors",
|
| 64 |
+
"model.layers.11.gka.k_proj.weight": "model-00003-of-00015.safetensors",
|
| 65 |
+
"model.layers.11.gka.o_norm.weight": "model-00003-of-00015.safetensors",
|
| 66 |
+
"model.layers.11.gka.o_proj.weight": "model-00003-of-00015.safetensors",
|
| 67 |
+
"model.layers.11.gka.q_conv1d.weight": "model-00003-of-00015.safetensors",
|
| 68 |
+
"model.layers.11.gka.q_proj.weight": "model-00003-of-00015.safetensors",
|
| 69 |
+
"model.layers.11.gka.v_conv1d.weight": "model-00003-of-00015.safetensors",
|
| 70 |
+
"model.layers.11.gka.v_proj.weight": "model-00003-of-00015.safetensors",
|
| 71 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 72 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 73 |
+
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
| 74 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
| 75 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
| 76 |
+
"model.layers.12.gka.A_log": "model-00004-of-00015.safetensors",
|
| 77 |
+
"model.layers.12.gka.a_proj.weight": "model-00004-of-00015.safetensors",
|
| 78 |
+
"model.layers.12.gka.alpha_proj.bias": "model-00004-of-00015.safetensors",
|
| 79 |
+
"model.layers.12.gka.alpha_proj.weight": "model-00004-of-00015.safetensors",
|
| 80 |
+
"model.layers.12.gka.b_proj.bias": "model-00004-of-00015.safetensors",
|
| 81 |
+
"model.layers.12.gka.b_proj.weight": "model-00004-of-00015.safetensors",
|
| 82 |
+
"model.layers.12.gka.dt_bias": "model-00004-of-00015.safetensors",
|
| 83 |
+
"model.layers.12.gka.g_proj.weight": "model-00004-of-00015.safetensors",
|
| 84 |
+
"model.layers.12.gka.k_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 85 |
+
"model.layers.12.gka.k_proj.weight": "model-00004-of-00015.safetensors",
|
| 86 |
+
"model.layers.12.gka.o_norm.weight": "model-00004-of-00015.safetensors",
|
| 87 |
+
"model.layers.12.gka.o_proj.weight": "model-00004-of-00015.safetensors",
|
| 88 |
+
"model.layers.12.gka.q_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 89 |
+
"model.layers.12.gka.q_proj.weight": "model-00004-of-00015.safetensors",
|
| 90 |
+
"model.layers.12.gka.v_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 91 |
+
"model.layers.12.gka.v_proj.weight": "model-00004-of-00015.safetensors",
|
| 92 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 93 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 94 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
| 95 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
| 96 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
| 97 |
+
"model.layers.13.gka.A_log": "model-00004-of-00015.safetensors",
|
| 98 |
+
"model.layers.13.gka.a_proj.weight": "model-00004-of-00015.safetensors",
|
| 99 |
+
"model.layers.13.gka.alpha_proj.bias": "model-00004-of-00015.safetensors",
|
| 100 |
+
"model.layers.13.gka.alpha_proj.weight": "model-00004-of-00015.safetensors",
|
| 101 |
+
"model.layers.13.gka.b_proj.bias": "model-00004-of-00015.safetensors",
|
| 102 |
+
"model.layers.13.gka.b_proj.weight": "model-00004-of-00015.safetensors",
|
| 103 |
+
"model.layers.13.gka.dt_bias": "model-00004-of-00015.safetensors",
|
| 104 |
+
"model.layers.13.gka.g_proj.weight": "model-00004-of-00015.safetensors",
|
| 105 |
+
"model.layers.13.gka.k_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 106 |
+
"model.layers.13.gka.k_proj.weight": "model-00004-of-00015.safetensors",
|
| 107 |
+
"model.layers.13.gka.o_norm.weight": "model-00004-of-00015.safetensors",
|
| 108 |
+
"model.layers.13.gka.o_proj.weight": "model-00004-of-00015.safetensors",
|
| 109 |
+
"model.layers.13.gka.q_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 110 |
+
"model.layers.13.gka.q_proj.weight": "model-00004-of-00015.safetensors",
|
| 111 |
+
"model.layers.13.gka.v_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 112 |
+
"model.layers.13.gka.v_proj.weight": "model-00004-of-00015.safetensors",
|
| 113 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 114 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 115 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
| 116 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
| 117 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
| 118 |
+
"model.layers.14.gka.A_log": "model-00004-of-00015.safetensors",
|
| 119 |
+
"model.layers.14.gka.a_proj.weight": "model-00004-of-00015.safetensors",
|
| 120 |
+
"model.layers.14.gka.alpha_proj.bias": "model-00004-of-00015.safetensors",
|
| 121 |
+
"model.layers.14.gka.alpha_proj.weight": "model-00004-of-00015.safetensors",
|
| 122 |
+
"model.layers.14.gka.b_proj.bias": "model-00004-of-00015.safetensors",
|
| 123 |
+
"model.layers.14.gka.b_proj.weight": "model-00004-of-00015.safetensors",
|
| 124 |
+
"model.layers.14.gka.dt_bias": "model-00004-of-00015.safetensors",
|
| 125 |
+
"model.layers.14.gka.g_proj.weight": "model-00004-of-00015.safetensors",
|
| 126 |
+
"model.layers.14.gka.k_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 127 |
+
"model.layers.14.gka.k_proj.weight": "model-00004-of-00015.safetensors",
|
| 128 |
+
"model.layers.14.gka.o_norm.weight": "model-00004-of-00015.safetensors",
|
| 129 |
+
"model.layers.14.gka.o_proj.weight": "model-00004-of-00015.safetensors",
|
| 130 |
+
"model.layers.14.gka.q_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 131 |
+
"model.layers.14.gka.q_proj.weight": "model-00004-of-00015.safetensors",
|
| 132 |
+
"model.layers.14.gka.v_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 133 |
+
"model.layers.14.gka.v_proj.weight": "model-00004-of-00015.safetensors",
|
| 134 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 135 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 136 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
| 137 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
| 138 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
| 139 |
+
"model.layers.15.gka.A_log": "model-00004-of-00015.safetensors",
|
| 140 |
+
"model.layers.15.gka.a_proj.weight": "model-00004-of-00015.safetensors",
|
| 141 |
+
"model.layers.15.gka.alpha_proj.bias": "model-00004-of-00015.safetensors",
|
| 142 |
+
"model.layers.15.gka.alpha_proj.weight": "model-00004-of-00015.safetensors",
|
| 143 |
+
"model.layers.15.gka.b_proj.bias": "model-00004-of-00015.safetensors",
|
| 144 |
+
"model.layers.15.gka.b_proj.weight": "model-00004-of-00015.safetensors",
|
| 145 |
+
"model.layers.15.gka.dt_bias": "model-00004-of-00015.safetensors",
|
| 146 |
+
"model.layers.15.gka.g_proj.weight": "model-00004-of-00015.safetensors",
|
| 147 |
+
"model.layers.15.gka.k_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 148 |
+
"model.layers.15.gka.k_proj.weight": "model-00004-of-00015.safetensors",
|
| 149 |
+
"model.layers.15.gka.o_norm.weight": "model-00004-of-00015.safetensors",
|
| 150 |
+
"model.layers.15.gka.o_proj.weight": "model-00004-of-00015.safetensors",
|
| 151 |
+
"model.layers.15.gka.q_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 152 |
+
"model.layers.15.gka.q_proj.weight": "model-00004-of-00015.safetensors",
|
| 153 |
+
"model.layers.15.gka.v_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 154 |
+
"model.layers.15.gka.v_proj.weight": "model-00004-of-00015.safetensors",
|
| 155 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 156 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 157 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
| 158 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
| 159 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
| 160 |
+
"model.layers.16.gka.A_log": "model-00004-of-00015.safetensors",
|
| 161 |
+
"model.layers.16.gka.a_proj.weight": "model-00004-of-00015.safetensors",
|
| 162 |
+
"model.layers.16.gka.alpha_proj.bias": "model-00004-of-00015.safetensors",
|
| 163 |
+
"model.layers.16.gka.alpha_proj.weight": "model-00004-of-00015.safetensors",
|
| 164 |
+
"model.layers.16.gka.b_proj.bias": "model-00004-of-00015.safetensors",
|
| 165 |
+
"model.layers.16.gka.b_proj.weight": "model-00004-of-00015.safetensors",
|
| 166 |
+
"model.layers.16.gka.dt_bias": "model-00004-of-00015.safetensors",
|
| 167 |
+
"model.layers.16.gka.g_proj.weight": "model-00004-of-00015.safetensors",
|
| 168 |
+
"model.layers.16.gka.k_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 169 |
+
"model.layers.16.gka.k_proj.weight": "model-00004-of-00015.safetensors",
|
| 170 |
+
"model.layers.16.gka.o_norm.weight": "model-00004-of-00015.safetensors",
|
| 171 |
+
"model.layers.16.gka.o_proj.weight": "model-00004-of-00015.safetensors",
|
| 172 |
+
"model.layers.16.gka.q_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 173 |
+
"model.layers.16.gka.q_proj.weight": "model-00004-of-00015.safetensors",
|
| 174 |
+
"model.layers.16.gka.v_conv1d.weight": "model-00004-of-00015.safetensors",
|
| 175 |
+
"model.layers.16.gka.v_proj.weight": "model-00004-of-00015.safetensors",
|
| 176 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 177 |
+
"model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 178 |
+
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
| 179 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
| 180 |
+
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
| 181 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 182 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00004-of-00015.safetensors",
|
| 183 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
| 184 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
| 185 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00004-of-00015.safetensors",
|
| 186 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
| 187 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
| 188 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 189 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
| 190 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
| 191 |
+
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
| 192 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 193 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00005-of-00015.safetensors",
|
| 194 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
| 195 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
| 196 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00005-of-00015.safetensors",
|
| 197 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
| 198 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
| 199 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 200 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
| 201 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
| 202 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
| 203 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 204 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00005-of-00015.safetensors",
|
| 205 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
| 206 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
| 207 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00005-of-00015.safetensors",
|
| 208 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
| 209 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
| 210 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 211 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
| 212 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
| 213 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
| 214 |
+
"model.layers.2.gka.A_log": "model-00001-of-00015.safetensors",
|
| 215 |
+
"model.layers.2.gka.a_proj.weight": "model-00001-of-00015.safetensors",
|
| 216 |
+
"model.layers.2.gka.alpha_proj.bias": "model-00001-of-00015.safetensors",
|
| 217 |
+
"model.layers.2.gka.alpha_proj.weight": "model-00001-of-00015.safetensors",
|
| 218 |
+
"model.layers.2.gka.b_proj.bias": "model-00001-of-00015.safetensors",
|
| 219 |
+
"model.layers.2.gka.b_proj.weight": "model-00001-of-00015.safetensors",
|
| 220 |
+
"model.layers.2.gka.dt_bias": "model-00001-of-00015.safetensors",
|
| 221 |
+
"model.layers.2.gka.g_proj.weight": "model-00001-of-00015.safetensors",
|
| 222 |
+
"model.layers.2.gka.k_conv1d.weight": "model-00001-of-00015.safetensors",
|
| 223 |
+
"model.layers.2.gka.k_proj.weight": "model-00001-of-00015.safetensors",
|
| 224 |
+
"model.layers.2.gka.o_norm.weight": "model-00001-of-00015.safetensors",
|
| 225 |
+
"model.layers.2.gka.o_proj.weight": "model-00001-of-00015.safetensors",
|
| 226 |
+
"model.layers.2.gka.q_conv1d.weight": "model-00001-of-00015.safetensors",
|
| 227 |
+
"model.layers.2.gka.q_proj.weight": "model-00001-of-00015.safetensors",
|
| 228 |
+
"model.layers.2.gka.v_conv1d.weight": "model-00001-of-00015.safetensors",
|
| 229 |
+
"model.layers.2.gka.v_proj.weight": "model-00001-of-00015.safetensors",
|
| 230 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 231 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 232 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
| 233 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
| 234 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
| 235 |
+
"model.layers.20.gka.A_log": "model-00005-of-00015.safetensors",
|
| 236 |
+
"model.layers.20.gka.a_proj.weight": "model-00005-of-00015.safetensors",
|
| 237 |
+
"model.layers.20.gka.alpha_proj.bias": "model-00005-of-00015.safetensors",
|
| 238 |
+
"model.layers.20.gka.alpha_proj.weight": "model-00005-of-00015.safetensors",
|
| 239 |
+
"model.layers.20.gka.b_proj.bias": "model-00005-of-00015.safetensors",
|
| 240 |
+
"model.layers.20.gka.b_proj.weight": "model-00005-of-00015.safetensors",
|
| 241 |
+
"model.layers.20.gka.dt_bias": "model-00005-of-00015.safetensors",
|
| 242 |
+
"model.layers.20.gka.g_proj.weight": "model-00005-of-00015.safetensors",
|
| 243 |
+
"model.layers.20.gka.k_conv1d.weight": "model-00005-of-00015.safetensors",
|
| 244 |
+
"model.layers.20.gka.k_proj.weight": "model-00005-of-00015.safetensors",
|
| 245 |
+
"model.layers.20.gka.o_norm.weight": "model-00005-of-00015.safetensors",
|
| 246 |
+
"model.layers.20.gka.o_proj.weight": "model-00005-of-00015.safetensors",
|
| 247 |
+
"model.layers.20.gka.q_conv1d.weight": "model-00005-of-00015.safetensors",
|
| 248 |
+
"model.layers.20.gka.q_proj.weight": "model-00005-of-00015.safetensors",
|
| 249 |
+
"model.layers.20.gka.v_conv1d.weight": "model-00005-of-00015.safetensors",
|
| 250 |
+
"model.layers.20.gka.v_proj.weight": "model-00005-of-00015.safetensors",
|
| 251 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 252 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 253 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
| 254 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
| 255 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
| 256 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 257 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00005-of-00015.safetensors",
|
| 258 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
| 259 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
| 260 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00005-of-00015.safetensors",
|
| 261 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
| 262 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
| 263 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 264 |
+
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
| 265 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
| 266 |
+
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
| 267 |
+
"model.layers.22.gka.A_log": "model-00006-of-00015.safetensors",
|
| 268 |
+
"model.layers.22.gka.a_proj.weight": "model-00006-of-00015.safetensors",
|
| 269 |
+
"model.layers.22.gka.alpha_proj.bias": "model-00006-of-00015.safetensors",
|
| 270 |
+
"model.layers.22.gka.alpha_proj.weight": "model-00006-of-00015.safetensors",
|
| 271 |
+
"model.layers.22.gka.b_proj.bias": "model-00006-of-00015.safetensors",
|
| 272 |
+
"model.layers.22.gka.b_proj.weight": "model-00006-of-00015.safetensors",
|
| 273 |
+
"model.layers.22.gka.dt_bias": "model-00006-of-00015.safetensors",
|
| 274 |
+
"model.layers.22.gka.g_proj.weight": "model-00006-of-00015.safetensors",
|
| 275 |
+
"model.layers.22.gka.k_conv1d.weight": "model-00006-of-00015.safetensors",
|
| 276 |
+
"model.layers.22.gka.k_proj.weight": "model-00006-of-00015.safetensors",
|
| 277 |
+
"model.layers.22.gka.o_norm.weight": "model-00006-of-00015.safetensors",
|
| 278 |
+
"model.layers.22.gka.o_proj.weight": "model-00006-of-00015.safetensors",
|
| 279 |
+
"model.layers.22.gka.q_conv1d.weight": "model-00006-of-00015.safetensors",
|
| 280 |
+
"model.layers.22.gka.q_proj.weight": "model-00006-of-00015.safetensors",
|
| 281 |
+
"model.layers.22.gka.v_conv1d.weight": "model-00006-of-00015.safetensors",
|
| 282 |
+
"model.layers.22.gka.v_proj.weight": "model-00006-of-00015.safetensors",
|
| 283 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 284 |
+
"model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 285 |
+
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
| 286 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
| 287 |
+
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
| 288 |
+
"model.layers.23.gka.A_log": "model-00006-of-00015.safetensors",
|
| 289 |
+
"model.layers.23.gka.a_proj.weight": "model-00006-of-00015.safetensors",
|
| 290 |
+
"model.layers.23.gka.alpha_proj.bias": "model-00006-of-00015.safetensors",
|
| 291 |
+
"model.layers.23.gka.alpha_proj.weight": "model-00006-of-00015.safetensors",
|
| 292 |
+
"model.layers.23.gka.b_proj.bias": "model-00006-of-00015.safetensors",
|
| 293 |
+
"model.layers.23.gka.b_proj.weight": "model-00006-of-00015.safetensors",
|
| 294 |
+
"model.layers.23.gka.dt_bias": "model-00006-of-00015.safetensors",
|
| 295 |
+
"model.layers.23.gka.g_proj.weight": "model-00006-of-00015.safetensors",
|
| 296 |
+
"model.layers.23.gka.k_conv1d.weight": "model-00006-of-00015.safetensors",
|
| 297 |
+
"model.layers.23.gka.k_proj.weight": "model-00006-of-00015.safetensors",
|
| 298 |
+
"model.layers.23.gka.o_norm.weight": "model-00006-of-00015.safetensors",
|
| 299 |
+
"model.layers.23.gka.o_proj.weight": "model-00006-of-00015.safetensors",
|
| 300 |
+
"model.layers.23.gka.q_conv1d.weight": "model-00006-of-00015.safetensors",
|
| 301 |
+
"model.layers.23.gka.q_proj.weight": "model-00006-of-00015.safetensors",
|
| 302 |
+
"model.layers.23.gka.v_conv1d.weight": "model-00006-of-00015.safetensors",
|
| 303 |
+
"model.layers.23.gka.v_proj.weight": "model-00006-of-00015.safetensors",
|
| 304 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 305 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 306 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
| 307 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
| 308 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
| 309 |
+
"model.layers.24.gka.A_log": "model-00006-of-00015.safetensors",
|
| 310 |
+
"model.layers.24.gka.a_proj.weight": "model-00006-of-00015.safetensors",
|
| 311 |
+
"model.layers.24.gka.alpha_proj.bias": "model-00006-of-00015.safetensors",
|
| 312 |
+
"model.layers.24.gka.alpha_proj.weight": "model-00006-of-00015.safetensors",
|
| 313 |
+
"model.layers.24.gka.b_proj.bias": "model-00006-of-00015.safetensors",
|
| 314 |
+
"model.layers.24.gka.b_proj.weight": "model-00006-of-00015.safetensors",
|
| 315 |
+
"model.layers.24.gka.dt_bias": "model-00006-of-00015.safetensors",
|
| 316 |
+
"model.layers.24.gka.g_proj.weight": "model-00006-of-00015.safetensors",
|
| 317 |
+
"model.layers.24.gka.k_conv1d.weight": "model-00006-of-00015.safetensors",
|
| 318 |
+
"model.layers.24.gka.k_proj.weight": "model-00006-of-00015.safetensors",
|
| 319 |
+
"model.layers.24.gka.o_norm.weight": "model-00006-of-00015.safetensors",
|
| 320 |
+
"model.layers.24.gka.o_proj.weight": "model-00006-of-00015.safetensors",
|
| 321 |
+
"model.layers.24.gka.q_conv1d.weight": "model-00006-of-00015.safetensors",
|
| 322 |
+
"model.layers.24.gka.q_proj.weight": "model-00006-of-00015.safetensors",
|
| 323 |
+
"model.layers.24.gka.v_conv1d.weight": "model-00006-of-00015.safetensors",
|
| 324 |
+
"model.layers.24.gka.v_proj.weight": "model-00006-of-00015.safetensors",
|
| 325 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 326 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 327 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
| 328 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
| 329 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
| 330 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 331 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00006-of-00015.safetensors",
|
| 332 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
| 333 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
| 334 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00006-of-00015.safetensors",
|
| 335 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
| 336 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
| 337 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 338 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
| 339 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
| 340 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
| 341 |
+
"model.layers.26.gka.A_log": "model-00006-of-00015.safetensors",
|
| 342 |
+
"model.layers.26.gka.a_proj.weight": "model-00007-of-00015.safetensors",
|
| 343 |
+
"model.layers.26.gka.alpha_proj.bias": "model-00007-of-00015.safetensors",
|
| 344 |
+
"model.layers.26.gka.alpha_proj.weight": "model-00007-of-00015.safetensors",
|
| 345 |
+
"model.layers.26.gka.b_proj.bias": "model-00007-of-00015.safetensors",
|
| 346 |
+
"model.layers.26.gka.b_proj.weight": "model-00007-of-00015.safetensors",
|
| 347 |
+
"model.layers.26.gka.dt_bias": "model-00006-of-00015.safetensors",
|
| 348 |
+
"model.layers.26.gka.g_proj.weight": "model-00007-of-00015.safetensors",
|
| 349 |
+
"model.layers.26.gka.k_conv1d.weight": "model-00007-of-00015.safetensors",
|
| 350 |
+
"model.layers.26.gka.k_proj.weight": "model-00007-of-00015.safetensors",
|
| 351 |
+
"model.layers.26.gka.o_norm.weight": "model-00007-of-00015.safetensors",
|
| 352 |
+
"model.layers.26.gka.o_proj.weight": "model-00007-of-00015.safetensors",
|
| 353 |
+
"model.layers.26.gka.q_conv1d.weight": "model-00007-of-00015.safetensors",
|
| 354 |
+
"model.layers.26.gka.q_proj.weight": "model-00007-of-00015.safetensors",
|
| 355 |
+
"model.layers.26.gka.v_conv1d.weight": "model-00007-of-00015.safetensors",
|
| 356 |
+
"model.layers.26.gka.v_proj.weight": "model-00007-of-00015.safetensors",
|
| 357 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 358 |
+
"model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 359 |
+
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
| 360 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
| 361 |
+
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
| 362 |
+
"model.layers.27.gka.A_log": "model-00007-of-00015.safetensors",
|
| 363 |
+
"model.layers.27.gka.a_proj.weight": "model-00007-of-00015.safetensors",
|
| 364 |
+
"model.layers.27.gka.alpha_proj.bias": "model-00007-of-00015.safetensors",
|
| 365 |
+
"model.layers.27.gka.alpha_proj.weight": "model-00007-of-00015.safetensors",
|
| 366 |
+
"model.layers.27.gka.b_proj.bias": "model-00007-of-00015.safetensors",
|
| 367 |
+
"model.layers.27.gka.b_proj.weight": "model-00007-of-00015.safetensors",
|
| 368 |
+
"model.layers.27.gka.dt_bias": "model-00007-of-00015.safetensors",
|
| 369 |
+
"model.layers.27.gka.g_proj.weight": "model-00007-of-00015.safetensors",
|
| 370 |
+
"model.layers.27.gka.k_conv1d.weight": "model-00007-of-00015.safetensors",
|
| 371 |
+
"model.layers.27.gka.k_proj.weight": "model-00007-of-00015.safetensors",
|
| 372 |
+
"model.layers.27.gka.o_norm.weight": "model-00007-of-00015.safetensors",
|
| 373 |
+
"model.layers.27.gka.o_proj.weight": "model-00007-of-00015.safetensors",
|
| 374 |
+
"model.layers.27.gka.q_conv1d.weight": "model-00007-of-00015.safetensors",
|
| 375 |
+
"model.layers.27.gka.q_proj.weight": "model-00007-of-00015.safetensors",
|
| 376 |
+
"model.layers.27.gka.v_conv1d.weight": "model-00007-of-00015.safetensors",
|
| 377 |
+
"model.layers.27.gka.v_proj.weight": "model-00007-of-00015.safetensors",
|
| 378 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 379 |
+
"model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 380 |
+
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
| 381 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
| 382 |
+
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
| 383 |
+
"model.layers.28.gka.A_log": "model-00007-of-00015.safetensors",
|
| 384 |
+
"model.layers.28.gka.a_proj.weight": "model-00007-of-00015.safetensors",
|
| 385 |
+
"model.layers.28.gka.alpha_proj.bias": "model-00007-of-00015.safetensors",
|
| 386 |
+
"model.layers.28.gka.alpha_proj.weight": "model-00007-of-00015.safetensors",
|
| 387 |
+
"model.layers.28.gka.b_proj.bias": "model-00007-of-00015.safetensors",
|
| 388 |
+
"model.layers.28.gka.b_proj.weight": "model-00007-of-00015.safetensors",
|
| 389 |
+
"model.layers.28.gka.dt_bias": "model-00007-of-00015.safetensors",
|
| 390 |
+
"model.layers.28.gka.g_proj.weight": "model-00007-of-00015.safetensors",
|
| 391 |
+
"model.layers.28.gka.k_conv1d.weight": "model-00007-of-00015.safetensors",
|
| 392 |
+
"model.layers.28.gka.k_proj.weight": "model-00007-of-00015.safetensors",
|
| 393 |
+
"model.layers.28.gka.o_norm.weight": "model-00007-of-00015.safetensors",
|
| 394 |
+
"model.layers.28.gka.o_proj.weight": "model-00007-of-00015.safetensors",
|
| 395 |
+
"model.layers.28.gka.q_conv1d.weight": "model-00007-of-00015.safetensors",
|
| 396 |
+
"model.layers.28.gka.q_proj.weight": "model-00007-of-00015.safetensors",
|
| 397 |
+
"model.layers.28.gka.v_conv1d.weight": "model-00007-of-00015.safetensors",
|
| 398 |
+
"model.layers.28.gka.v_proj.weight": "model-00007-of-00015.safetensors",
|
| 399 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 400 |
+
"model.layers.29.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 401 |
+
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
| 402 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
| 403 |
+
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
| 404 |
+
"model.layers.29.gka.A_log": "model-00007-of-00015.safetensors",
|
| 405 |
+
"model.layers.29.gka.a_proj.weight": "model-00007-of-00015.safetensors",
|
| 406 |
+
"model.layers.29.gka.alpha_proj.bias": "model-00007-of-00015.safetensors",
|
| 407 |
+
"model.layers.29.gka.alpha_proj.weight": "model-00007-of-00015.safetensors",
|
| 408 |
+
"model.layers.29.gka.b_proj.bias": "model-00007-of-00015.safetensors",
|
| 409 |
+
"model.layers.29.gka.b_proj.weight": "model-00007-of-00015.safetensors",
|
| 410 |
+
"model.layers.29.gka.dt_bias": "model-00007-of-00015.safetensors",
|
| 411 |
+
"model.layers.29.gka.g_proj.weight": "model-00007-of-00015.safetensors",
|
| 412 |
+
"model.layers.29.gka.k_conv1d.weight": "model-00007-of-00015.safetensors",
|
| 413 |
+
"model.layers.29.gka.k_proj.weight": "model-00007-of-00015.safetensors",
|
| 414 |
+
"model.layers.29.gka.o_norm.weight": "model-00007-of-00015.safetensors",
|
| 415 |
+
"model.layers.29.gka.o_proj.weight": "model-00007-of-00015.safetensors",
|
| 416 |
+
"model.layers.29.gka.q_conv1d.weight": "model-00007-of-00015.safetensors",
|
| 417 |
+
"model.layers.29.gka.q_proj.weight": "model-00007-of-00015.safetensors",
|
| 418 |
+
"model.layers.29.gka.v_conv1d.weight": "model-00007-of-00015.safetensors",
|
| 419 |
+
"model.layers.29.gka.v_proj.weight": "model-00007-of-00015.safetensors",
|
| 420 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 421 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 422 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
| 423 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
| 424 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
| 425 |
+
"model.layers.3.gka.A_log": "model-00002-of-00015.safetensors",
|
| 426 |
+
"model.layers.3.gka.a_proj.weight": "model-00002-of-00015.safetensors",
|
| 427 |
+
"model.layers.3.gka.alpha_proj.bias": "model-00002-of-00015.safetensors",
|
| 428 |
+
"model.layers.3.gka.alpha_proj.weight": "model-00002-of-00015.safetensors",
|
| 429 |
+
"model.layers.3.gka.b_proj.bias": "model-00002-of-00015.safetensors",
|
| 430 |
+
"model.layers.3.gka.b_proj.weight": "model-00002-of-00015.safetensors",
|
| 431 |
+
"model.layers.3.gka.dt_bias": "model-00002-of-00015.safetensors",
|
| 432 |
+
"model.layers.3.gka.g_proj.weight": "model-00002-of-00015.safetensors",
|
| 433 |
+
"model.layers.3.gka.k_conv1d.weight": "model-00002-of-00015.safetensors",
|
| 434 |
+
"model.layers.3.gka.k_proj.weight": "model-00002-of-00015.safetensors",
|
| 435 |
+
"model.layers.3.gka.o_norm.weight": "model-00002-of-00015.safetensors",
|
| 436 |
+
"model.layers.3.gka.o_proj.weight": "model-00002-of-00015.safetensors",
|
| 437 |
+
"model.layers.3.gka.q_conv1d.weight": "model-00002-of-00015.safetensors",
|
| 438 |
+
"model.layers.3.gka.q_proj.weight": "model-00002-of-00015.safetensors",
|
| 439 |
+
"model.layers.3.gka.v_conv1d.weight": "model-00002-of-00015.safetensors",
|
| 440 |
+
"model.layers.3.gka.v_proj.weight": "model-00002-of-00015.safetensors",
|
| 441 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 442 |
+
"model.layers.30.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 443 |
+
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
| 444 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
| 445 |
+
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
| 446 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 447 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00007-of-00015.safetensors",
|
| 448 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
| 449 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
| 450 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00007-of-00015.safetensors",
|
| 451 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
| 452 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
| 453 |
+
"model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 454 |
+
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
| 455 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
| 456 |
+
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
| 457 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 458 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00007-of-00015.safetensors",
|
| 459 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
| 460 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
| 461 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00007-of-00015.safetensors",
|
| 462 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
| 463 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
| 464 |
+
"model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 465 |
+
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
| 466 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
| 467 |
+
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
| 468 |
+
"model.layers.32.gka.A_log": "model-00008-of-00015.safetensors",
|
| 469 |
+
"model.layers.32.gka.a_proj.weight": "model-00008-of-00015.safetensors",
|
| 470 |
+
"model.layers.32.gka.alpha_proj.bias": "model-00008-of-00015.safetensors",
|
| 471 |
+
"model.layers.32.gka.alpha_proj.weight": "model-00008-of-00015.safetensors",
|
| 472 |
+
"model.layers.32.gka.b_proj.bias": "model-00008-of-00015.safetensors",
|
| 473 |
+
"model.layers.32.gka.b_proj.weight": "model-00008-of-00015.safetensors",
|
| 474 |
+
"model.layers.32.gka.dt_bias": "model-00008-of-00015.safetensors",
|
| 475 |
+
"model.layers.32.gka.g_proj.weight": "model-00008-of-00015.safetensors",
|
| 476 |
+
"model.layers.32.gka.k_conv1d.weight": "model-00008-of-00015.safetensors",
|
| 477 |
+
"model.layers.32.gka.k_proj.weight": "model-00008-of-00015.safetensors",
|
| 478 |
+
"model.layers.32.gka.o_norm.weight": "model-00008-of-00015.safetensors",
|
| 479 |
+
"model.layers.32.gka.o_proj.weight": "model-00008-of-00015.safetensors",
|
| 480 |
+
"model.layers.32.gka.q_conv1d.weight": "model-00008-of-00015.safetensors",
|
| 481 |
+
"model.layers.32.gka.q_proj.weight": "model-00008-of-00015.safetensors",
|
| 482 |
+
"model.layers.32.gka.v_conv1d.weight": "model-00008-of-00015.safetensors",
|
| 483 |
+
"model.layers.32.gka.v_proj.weight": "model-00008-of-00015.safetensors",
|
| 484 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 485 |
+
"model.layers.33.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 486 |
+
"model.layers.33.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
| 487 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
| 488 |
+
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
| 489 |
+
"model.layers.33.gka.A_log": "model-00008-of-00015.safetensors",
|
| 490 |
+
"model.layers.33.gka.a_proj.weight": "model-00008-of-00015.safetensors",
|
| 491 |
+
"model.layers.33.gka.alpha_proj.bias": "model-00008-of-00015.safetensors",
|
| 492 |
+
"model.layers.33.gka.alpha_proj.weight": "model-00008-of-00015.safetensors",
|
| 493 |
+
"model.layers.33.gka.b_proj.bias": "model-00008-of-00015.safetensors",
|
| 494 |
+
"model.layers.33.gka.b_proj.weight": "model-00008-of-00015.safetensors",
|
| 495 |
+
"model.layers.33.gka.dt_bias": "model-00008-of-00015.safetensors",
|
| 496 |
+
"model.layers.33.gka.g_proj.weight": "model-00008-of-00015.safetensors",
|
| 497 |
+
"model.layers.33.gka.k_conv1d.weight": "model-00008-of-00015.safetensors",
|
| 498 |
+
"model.layers.33.gka.k_proj.weight": "model-00008-of-00015.safetensors",
|
| 499 |
+
"model.layers.33.gka.o_norm.weight": "model-00008-of-00015.safetensors",
|
| 500 |
+
"model.layers.33.gka.o_proj.weight": "model-00008-of-00015.safetensors",
|
| 501 |
+
"model.layers.33.gka.q_conv1d.weight": "model-00008-of-00015.safetensors",
|
| 502 |
+
"model.layers.33.gka.q_proj.weight": "model-00008-of-00015.safetensors",
|
| 503 |
+
"model.layers.33.gka.v_conv1d.weight": "model-00008-of-00015.safetensors",
|
| 504 |
+
"model.layers.33.gka.v_proj.weight": "model-00008-of-00015.safetensors",
|
| 505 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 506 |
+
"model.layers.34.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 507 |
+
"model.layers.34.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
| 508 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
| 509 |
+
"model.layers.34.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
| 510 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 511 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00008-of-00015.safetensors",
|
| 512 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
| 513 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
| 514 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00008-of-00015.safetensors",
|
| 515 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
| 516 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
| 517 |
+
"model.layers.35.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 518 |
+
"model.layers.35.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
| 519 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
| 520 |
+
"model.layers.35.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
| 521 |
+
"model.layers.35.gka.A_log": "model-00008-of-00015.safetensors",
|
| 522 |
+
"model.layers.35.gka.a_proj.weight": "model-00008-of-00015.safetensors",
|
| 523 |
+
"model.layers.35.gka.alpha_proj.bias": "model-00008-of-00015.safetensors",
|
| 524 |
+
"model.layers.35.gka.alpha_proj.weight": "model-00008-of-00015.safetensors",
|
| 525 |
+
"model.layers.35.gka.b_proj.bias": "model-00008-of-00015.safetensors",
|
| 526 |
+
"model.layers.35.gka.b_proj.weight": "model-00008-of-00015.safetensors",
|
| 527 |
+
"model.layers.35.gka.dt_bias": "model-00008-of-00015.safetensors",
|
| 528 |
+
"model.layers.35.gka.g_proj.weight": "model-00008-of-00015.safetensors",
|
| 529 |
+
"model.layers.35.gka.k_conv1d.weight": "model-00008-of-00015.safetensors",
|
| 530 |
+
"model.layers.35.gka.k_proj.weight": "model-00008-of-00015.safetensors",
|
| 531 |
+
"model.layers.35.gka.o_norm.weight": "model-00008-of-00015.safetensors",
|
| 532 |
+
"model.layers.35.gka.o_proj.weight": "model-00008-of-00015.safetensors",
|
| 533 |
+
"model.layers.35.gka.q_conv1d.weight": "model-00008-of-00015.safetensors",
|
| 534 |
+
"model.layers.35.gka.q_proj.weight": "model-00008-of-00015.safetensors",
|
| 535 |
+
"model.layers.35.gka.v_conv1d.weight": "model-00008-of-00015.safetensors",
|
| 536 |
+
"model.layers.35.gka.v_proj.weight": "model-00008-of-00015.safetensors",
|
| 537 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 538 |
+
"model.layers.36.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 539 |
+
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
| 540 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
| 541 |
+
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
| 542 |
+
"model.layers.36.gka.A_log": "model-00009-of-00015.safetensors",
|
| 543 |
+
"model.layers.36.gka.a_proj.weight": "model-00009-of-00015.safetensors",
|
| 544 |
+
"model.layers.36.gka.alpha_proj.bias": "model-00009-of-00015.safetensors",
|
| 545 |
+
"model.layers.36.gka.alpha_proj.weight": "model-00009-of-00015.safetensors",
|
| 546 |
+
"model.layers.36.gka.b_proj.bias": "model-00009-of-00015.safetensors",
|
| 547 |
+
"model.layers.36.gka.b_proj.weight": "model-00009-of-00015.safetensors",
|
| 548 |
+
"model.layers.36.gka.dt_bias": "model-00009-of-00015.safetensors",
|
| 549 |
+
"model.layers.36.gka.g_proj.weight": "model-00009-of-00015.safetensors",
|
| 550 |
+
"model.layers.36.gka.k_conv1d.weight": "model-00009-of-00015.safetensors",
|
| 551 |
+
"model.layers.36.gka.k_proj.weight": "model-00009-of-00015.safetensors",
|
| 552 |
+
"model.layers.36.gka.o_norm.weight": "model-00009-of-00015.safetensors",
|
| 553 |
+
"model.layers.36.gka.o_proj.weight": "model-00009-of-00015.safetensors",
|
| 554 |
+
"model.layers.36.gka.q_conv1d.weight": "model-00009-of-00015.safetensors",
|
| 555 |
+
"model.layers.36.gka.q_proj.weight": "model-00009-of-00015.safetensors",
|
| 556 |
+
"model.layers.36.gka.v_conv1d.weight": "model-00009-of-00015.safetensors",
|
| 557 |
+
"model.layers.36.gka.v_proj.weight": "model-00009-of-00015.safetensors",
|
| 558 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 559 |
+
"model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 560 |
+
"model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
| 561 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
| 562 |
+
"model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
| 563 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 564 |
+
"model.layers.37.self_attn.k_norm.weight": "model-00009-of-00015.safetensors",
|
| 565 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
| 566 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
| 567 |
+
"model.layers.37.self_attn.q_norm.weight": "model-00009-of-00015.safetensors",
|
| 568 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
| 569 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
| 570 |
+
"model.layers.38.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 571 |
+
"model.layers.38.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
| 572 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
| 573 |
+
"model.layers.38.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
| 574 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 575 |
+
"model.layers.38.self_attn.k_norm.weight": "model-00009-of-00015.safetensors",
|
| 576 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
| 577 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
| 578 |
+
"model.layers.38.self_attn.q_norm.weight": "model-00009-of-00015.safetensors",
|
| 579 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
| 580 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
| 581 |
+
"model.layers.39.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 582 |
+
"model.layers.39.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
| 583 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
| 584 |
+
"model.layers.39.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
| 585 |
+
"model.layers.39.gka.A_log": "model-00009-of-00015.safetensors",
|
| 586 |
+
"model.layers.39.gka.a_proj.weight": "model-00009-of-00015.safetensors",
|
| 587 |
+
"model.layers.39.gka.alpha_proj.bias": "model-00009-of-00015.safetensors",
|
| 588 |
+
"model.layers.39.gka.alpha_proj.weight": "model-00009-of-00015.safetensors",
|
| 589 |
+
"model.layers.39.gka.b_proj.bias": "model-00009-of-00015.safetensors",
|
| 590 |
+
"model.layers.39.gka.b_proj.weight": "model-00009-of-00015.safetensors",
|
| 591 |
+
"model.layers.39.gka.dt_bias": "model-00009-of-00015.safetensors",
|
| 592 |
+
"model.layers.39.gka.g_proj.weight": "model-00009-of-00015.safetensors",
|
| 593 |
+
"model.layers.39.gka.k_conv1d.weight": "model-00009-of-00015.safetensors",
|
| 594 |
+
"model.layers.39.gka.k_proj.weight": "model-00009-of-00015.safetensors",
|
| 595 |
+
"model.layers.39.gka.o_norm.weight": "model-00009-of-00015.safetensors",
|
| 596 |
+
"model.layers.39.gka.o_proj.weight": "model-00009-of-00015.safetensors",
|
| 597 |
+
"model.layers.39.gka.q_conv1d.weight": "model-00009-of-00015.safetensors",
|
| 598 |
+
"model.layers.39.gka.q_proj.weight": "model-00009-of-00015.safetensors",
|
| 599 |
+
"model.layers.39.gka.v_conv1d.weight": "model-00009-of-00015.safetensors",
|
| 600 |
+
"model.layers.39.gka.v_proj.weight": "model-00009-of-00015.safetensors",
|
| 601 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 602 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 603 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
| 604 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
| 605 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
| 606 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 607 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00015.safetensors",
|
| 608 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
| 609 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
| 610 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00002-of-00015.safetensors",
|
| 611 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
| 612 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
| 613 |
+
"model.layers.40.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 614 |
+
"model.layers.40.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
| 615 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
| 616 |
+
"model.layers.40.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
| 617 |
+
"model.layers.40.gka.A_log": "model-00009-of-00015.safetensors",
|
| 618 |
+
"model.layers.40.gka.a_proj.weight": "model-00009-of-00015.safetensors",
|
| 619 |
+
"model.layers.40.gka.alpha_proj.bias": "model-00009-of-00015.safetensors",
|
| 620 |
+
"model.layers.40.gka.alpha_proj.weight": "model-00009-of-00015.safetensors",
|
| 621 |
+
"model.layers.40.gka.b_proj.bias": "model-00009-of-00015.safetensors",
|
| 622 |
+
"model.layers.40.gka.b_proj.weight": "model-00009-of-00015.safetensors",
|
| 623 |
+
"model.layers.40.gka.dt_bias": "model-00009-of-00015.safetensors",
|
| 624 |
+
"model.layers.40.gka.g_proj.weight": "model-00009-of-00015.safetensors",
|
| 625 |
+
"model.layers.40.gka.k_conv1d.weight": "model-00009-of-00015.safetensors",
|
| 626 |
+
"model.layers.40.gka.k_proj.weight": "model-00009-of-00015.safetensors",
|
| 627 |
+
"model.layers.40.gka.o_norm.weight": "model-00009-of-00015.safetensors",
|
| 628 |
+
"model.layers.40.gka.o_proj.weight": "model-00009-of-00015.safetensors",
|
| 629 |
+
"model.layers.40.gka.q_conv1d.weight": "model-00009-of-00015.safetensors",
|
| 630 |
+
"model.layers.40.gka.q_proj.weight": "model-00009-of-00015.safetensors",
|
| 631 |
+
"model.layers.40.gka.v_conv1d.weight": "model-00009-of-00015.safetensors",
|
| 632 |
+
"model.layers.40.gka.v_proj.weight": "model-00009-of-00015.safetensors",
|
| 633 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 634 |
+
"model.layers.41.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 635 |
+
"model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
| 636 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
| 637 |
+
"model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
| 638 |
+
"model.layers.41.gka.A_log": "model-00010-of-00015.safetensors",
|
| 639 |
+
"model.layers.41.gka.a_proj.weight": "model-00010-of-00015.safetensors",
|
| 640 |
+
"model.layers.41.gka.alpha_proj.bias": "model-00010-of-00015.safetensors",
|
| 641 |
+
"model.layers.41.gka.alpha_proj.weight": "model-00010-of-00015.safetensors",
|
| 642 |
+
"model.layers.41.gka.b_proj.bias": "model-00010-of-00015.safetensors",
|
| 643 |
+
"model.layers.41.gka.b_proj.weight": "model-00010-of-00015.safetensors",
|
| 644 |
+
"model.layers.41.gka.dt_bias": "model-00010-of-00015.safetensors",
|
| 645 |
+
"model.layers.41.gka.g_proj.weight": "model-00010-of-00015.safetensors",
|
| 646 |
+
"model.layers.41.gka.k_conv1d.weight": "model-00010-of-00015.safetensors",
|
| 647 |
+
"model.layers.41.gka.k_proj.weight": "model-00010-of-00015.safetensors",
|
| 648 |
+
"model.layers.41.gka.o_norm.weight": "model-00010-of-00015.safetensors",
|
| 649 |
+
"model.layers.41.gka.o_proj.weight": "model-00010-of-00015.safetensors",
|
| 650 |
+
"model.layers.41.gka.q_conv1d.weight": "model-00010-of-00015.safetensors",
|
| 651 |
+
"model.layers.41.gka.q_proj.weight": "model-00010-of-00015.safetensors",
|
| 652 |
+
"model.layers.41.gka.v_conv1d.weight": "model-00010-of-00015.safetensors",
|
| 653 |
+
"model.layers.41.gka.v_proj.weight": "model-00010-of-00015.safetensors",
|
| 654 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 655 |
+
"model.layers.42.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 656 |
+
"model.layers.42.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
| 657 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
| 658 |
+
"model.layers.42.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
| 659 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 660 |
+
"model.layers.42.self_attn.k_norm.weight": "model-00010-of-00015.safetensors",
|
| 661 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
| 662 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
| 663 |
+
"model.layers.42.self_attn.q_norm.weight": "model-00010-of-00015.safetensors",
|
| 664 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
| 665 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
| 666 |
+
"model.layers.43.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 667 |
+
"model.layers.43.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
| 668 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
| 669 |
+
"model.layers.43.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
| 670 |
+
"model.layers.43.gka.A_log": "model-00010-of-00015.safetensors",
|
| 671 |
+
"model.layers.43.gka.a_proj.weight": "model-00010-of-00015.safetensors",
|
| 672 |
+
"model.layers.43.gka.alpha_proj.bias": "model-00010-of-00015.safetensors",
|
| 673 |
+
"model.layers.43.gka.alpha_proj.weight": "model-00010-of-00015.safetensors",
|
| 674 |
+
"model.layers.43.gka.b_proj.bias": "model-00010-of-00015.safetensors",
|
| 675 |
+
"model.layers.43.gka.b_proj.weight": "model-00010-of-00015.safetensors",
|
| 676 |
+
"model.layers.43.gka.dt_bias": "model-00010-of-00015.safetensors",
|
| 677 |
+
"model.layers.43.gka.g_proj.weight": "model-00010-of-00015.safetensors",
|
| 678 |
+
"model.layers.43.gka.k_conv1d.weight": "model-00010-of-00015.safetensors",
|
| 679 |
+
"model.layers.43.gka.k_proj.weight": "model-00010-of-00015.safetensors",
|
| 680 |
+
"model.layers.43.gka.o_norm.weight": "model-00010-of-00015.safetensors",
|
| 681 |
+
"model.layers.43.gka.o_proj.weight": "model-00010-of-00015.safetensors",
|
| 682 |
+
"model.layers.43.gka.q_conv1d.weight": "model-00010-of-00015.safetensors",
|
| 683 |
+
"model.layers.43.gka.q_proj.weight": "model-00010-of-00015.safetensors",
|
| 684 |
+
"model.layers.43.gka.v_conv1d.weight": "model-00010-of-00015.safetensors",
|
| 685 |
+
"model.layers.43.gka.v_proj.weight": "model-00010-of-00015.safetensors",
|
| 686 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 687 |
+
"model.layers.44.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 688 |
+
"model.layers.44.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
| 689 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
| 690 |
+
"model.layers.44.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
| 691 |
+
"model.layers.44.gka.A_log": "model-00010-of-00015.safetensors",
|
| 692 |
+
"model.layers.44.gka.a_proj.weight": "model-00010-of-00015.safetensors",
|
| 693 |
+
"model.layers.44.gka.alpha_proj.bias": "model-00010-of-00015.safetensors",
|
| 694 |
+
"model.layers.44.gka.alpha_proj.weight": "model-00010-of-00015.safetensors",
|
| 695 |
+
"model.layers.44.gka.b_proj.bias": "model-00010-of-00015.safetensors",
|
| 696 |
+
"model.layers.44.gka.b_proj.weight": "model-00010-of-00015.safetensors",
|
| 697 |
+
"model.layers.44.gka.dt_bias": "model-00010-of-00015.safetensors",
|
| 698 |
+
"model.layers.44.gka.g_proj.weight": "model-00010-of-00015.safetensors",
|
| 699 |
+
"model.layers.44.gka.k_conv1d.weight": "model-00010-of-00015.safetensors",
|
| 700 |
+
"model.layers.44.gka.k_proj.weight": "model-00010-of-00015.safetensors",
|
| 701 |
+
"model.layers.44.gka.o_norm.weight": "model-00010-of-00015.safetensors",
|
| 702 |
+
"model.layers.44.gka.o_proj.weight": "model-00010-of-00015.safetensors",
|
| 703 |
+
"model.layers.44.gka.q_conv1d.weight": "model-00010-of-00015.safetensors",
|
| 704 |
+
"model.layers.44.gka.q_proj.weight": "model-00010-of-00015.safetensors",
|
| 705 |
+
"model.layers.44.gka.v_conv1d.weight": "model-00010-of-00015.safetensors",
|
| 706 |
+
"model.layers.44.gka.v_proj.weight": "model-00010-of-00015.safetensors",
|
| 707 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 708 |
+
"model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 709 |
+
"model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
| 710 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
| 711 |
+
"model.layers.45.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
| 712 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 713 |
+
"model.layers.45.self_attn.k_norm.weight": "model-00010-of-00015.safetensors",
|
| 714 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
| 715 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
| 716 |
+
"model.layers.45.self_attn.q_norm.weight": "model-00010-of-00015.safetensors",
|
| 717 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
| 718 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
| 719 |
+
"model.layers.46.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 720 |
+
"model.layers.46.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
| 721 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
| 722 |
+
"model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
| 723 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 724 |
+
"model.layers.46.self_attn.k_norm.weight": "model-00011-of-00015.safetensors",
|
| 725 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
| 726 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
| 727 |
+
"model.layers.46.self_attn.q_norm.weight": "model-00011-of-00015.safetensors",
|
| 728 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
| 729 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
| 730 |
+
"model.layers.47.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 731 |
+
"model.layers.47.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
| 732 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
| 733 |
+
"model.layers.47.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
| 734 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 735 |
+
"model.layers.47.self_attn.k_norm.weight": "model-00011-of-00015.safetensors",
|
| 736 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
| 737 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
| 738 |
+
"model.layers.47.self_attn.q_norm.weight": "model-00011-of-00015.safetensors",
|
| 739 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
| 740 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
| 741 |
+
"model.layers.48.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 742 |
+
"model.layers.48.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
| 743 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
| 744 |
+
"model.layers.48.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
| 745 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 746 |
+
"model.layers.48.self_attn.k_norm.weight": "model-00011-of-00015.safetensors",
|
| 747 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
| 748 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
| 749 |
+
"model.layers.48.self_attn.q_norm.weight": "model-00011-of-00015.safetensors",
|
| 750 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
| 751 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
| 752 |
+
"model.layers.49.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 753 |
+
"model.layers.49.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
| 754 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
| 755 |
+
"model.layers.49.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
| 756 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 757 |
+
"model.layers.49.self_attn.k_norm.weight": "model-00011-of-00015.safetensors",
|
| 758 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
| 759 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
| 760 |
+
"model.layers.49.self_attn.q_norm.weight": "model-00011-of-00015.safetensors",
|
| 761 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
| 762 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
| 763 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 764 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
| 765 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
| 766 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
| 767 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 768 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00015.safetensors",
|
| 769 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
| 770 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
| 771 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00002-of-00015.safetensors",
|
| 772 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
| 773 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
| 774 |
+
"model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 775 |
+
"model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
| 776 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
| 777 |
+
"model.layers.50.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
| 778 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 779 |
+
"model.layers.50.self_attn.k_norm.weight": "model-00011-of-00015.safetensors",
|
| 780 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
| 781 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
| 782 |
+
"model.layers.50.self_attn.q_norm.weight": "model-00011-of-00015.safetensors",
|
| 783 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
| 784 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
| 785 |
+
"model.layers.51.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 786 |
+
"model.layers.51.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
| 787 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
| 788 |
+
"model.layers.51.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
| 789 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 790 |
+
"model.layers.51.self_attn.k_norm.weight": "model-00012-of-00015.safetensors",
|
| 791 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
| 792 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
| 793 |
+
"model.layers.51.self_attn.q_norm.weight": "model-00012-of-00015.safetensors",
|
| 794 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
| 795 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
| 796 |
+
"model.layers.52.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 797 |
+
"model.layers.52.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
| 798 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
| 799 |
+
"model.layers.52.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
| 800 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 801 |
+
"model.layers.52.self_attn.k_norm.weight": "model-00012-of-00015.safetensors",
|
| 802 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
| 803 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
| 804 |
+
"model.layers.52.self_attn.q_norm.weight": "model-00012-of-00015.safetensors",
|
| 805 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
| 806 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
| 807 |
+
"model.layers.53.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 808 |
+
"model.layers.53.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
| 809 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
| 810 |
+
"model.layers.53.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
| 811 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 812 |
+
"model.layers.53.self_attn.k_norm.weight": "model-00012-of-00015.safetensors",
|
| 813 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
| 814 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
| 815 |
+
"model.layers.53.self_attn.q_norm.weight": "model-00012-of-00015.safetensors",
|
| 816 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
| 817 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
| 818 |
+
"model.layers.54.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 819 |
+
"model.layers.54.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
| 820 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
| 821 |
+
"model.layers.54.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
| 822 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 823 |
+
"model.layers.54.self_attn.k_norm.weight": "model-00012-of-00015.safetensors",
|
| 824 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
| 825 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
| 826 |
+
"model.layers.54.self_attn.q_norm.weight": "model-00012-of-00015.safetensors",
|
| 827 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
| 828 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
| 829 |
+
"model.layers.55.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 830 |
+
"model.layers.55.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
| 831 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
| 832 |
+
"model.layers.55.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
| 833 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 834 |
+
"model.layers.55.self_attn.k_norm.weight": "model-00012-of-00015.safetensors",
|
| 835 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
| 836 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
| 837 |
+
"model.layers.55.self_attn.q_norm.weight": "model-00012-of-00015.safetensors",
|
| 838 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
| 839 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
| 840 |
+
"model.layers.56.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 841 |
+
"model.layers.56.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
| 842 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
| 843 |
+
"model.layers.56.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
| 844 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 845 |
+
"model.layers.56.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
|
| 846 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
| 847 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
| 848 |
+
"model.layers.56.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
|
| 849 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
| 850 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
| 851 |
+
"model.layers.57.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 852 |
+
"model.layers.57.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
| 853 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
| 854 |
+
"model.layers.57.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
| 855 |
+
"model.layers.57.gka.A_log": "model-00013-of-00015.safetensors",
|
| 856 |
+
"model.layers.57.gka.a_proj.weight": "model-00013-of-00015.safetensors",
|
| 857 |
+
"model.layers.57.gka.alpha_proj.bias": "model-00013-of-00015.safetensors",
|
| 858 |
+
"model.layers.57.gka.alpha_proj.weight": "model-00013-of-00015.safetensors",
|
| 859 |
+
"model.layers.57.gka.b_proj.bias": "model-00013-of-00015.safetensors",
|
| 860 |
+
"model.layers.57.gka.b_proj.weight": "model-00013-of-00015.safetensors",
|
| 861 |
+
"model.layers.57.gka.dt_bias": "model-00013-of-00015.safetensors",
|
| 862 |
+
"model.layers.57.gka.g_proj.weight": "model-00013-of-00015.safetensors",
|
| 863 |
+
"model.layers.57.gka.k_conv1d.weight": "model-00013-of-00015.safetensors",
|
| 864 |
+
"model.layers.57.gka.k_proj.weight": "model-00013-of-00015.safetensors",
|
| 865 |
+
"model.layers.57.gka.o_norm.weight": "model-00013-of-00015.safetensors",
|
| 866 |
+
"model.layers.57.gka.o_proj.weight": "model-00013-of-00015.safetensors",
|
| 867 |
+
"model.layers.57.gka.q_conv1d.weight": "model-00013-of-00015.safetensors",
|
| 868 |
+
"model.layers.57.gka.q_proj.weight": "model-00013-of-00015.safetensors",
|
| 869 |
+
"model.layers.57.gka.v_conv1d.weight": "model-00013-of-00015.safetensors",
|
| 870 |
+
"model.layers.57.gka.v_proj.weight": "model-00013-of-00015.safetensors",
|
| 871 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 872 |
+
"model.layers.58.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 873 |
+
"model.layers.58.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
| 874 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
| 875 |
+
"model.layers.58.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
| 876 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 877 |
+
"model.layers.58.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
|
| 878 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
| 879 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
| 880 |
+
"model.layers.58.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
|
| 881 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
| 882 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
| 883 |
+
"model.layers.59.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 884 |
+
"model.layers.59.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
| 885 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
| 886 |
+
"model.layers.59.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
| 887 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 888 |
+
"model.layers.59.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
|
| 889 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
| 890 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
| 891 |
+
"model.layers.59.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
|
| 892 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
| 893 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
| 894 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 895 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
| 896 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
| 897 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
| 898 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 899 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00015.safetensors",
|
| 900 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
| 901 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
| 902 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00015.safetensors",
|
| 903 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
| 904 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
| 905 |
+
"model.layers.60.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 906 |
+
"model.layers.60.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
| 907 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
| 908 |
+
"model.layers.60.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
| 909 |
+
"model.layers.60.gka.A_log": "model-00014-of-00015.safetensors",
|
| 910 |
+
"model.layers.60.gka.a_proj.weight": "model-00014-of-00015.safetensors",
|
| 911 |
+
"model.layers.60.gka.alpha_proj.bias": "model-00014-of-00015.safetensors",
|
| 912 |
+
"model.layers.60.gka.alpha_proj.weight": "model-00014-of-00015.safetensors",
|
| 913 |
+
"model.layers.60.gka.b_proj.bias": "model-00014-of-00015.safetensors",
|
| 914 |
+
"model.layers.60.gka.b_proj.weight": "model-00014-of-00015.safetensors",
|
| 915 |
+
"model.layers.60.gka.dt_bias": "model-00014-of-00015.safetensors",
|
| 916 |
+
"model.layers.60.gka.g_proj.weight": "model-00014-of-00015.safetensors",
|
| 917 |
+
"model.layers.60.gka.k_conv1d.weight": "model-00014-of-00015.safetensors",
|
| 918 |
+
"model.layers.60.gka.k_proj.weight": "model-00014-of-00015.safetensors",
|
| 919 |
+
"model.layers.60.gka.o_norm.weight": "model-00014-of-00015.safetensors",
|
| 920 |
+
"model.layers.60.gka.o_proj.weight": "model-00014-of-00015.safetensors",
|
| 921 |
+
"model.layers.60.gka.q_conv1d.weight": "model-00014-of-00015.safetensors",
|
| 922 |
+
"model.layers.60.gka.q_proj.weight": "model-00014-of-00015.safetensors",
|
| 923 |
+
"model.layers.60.gka.v_conv1d.weight": "model-00014-of-00015.safetensors",
|
| 924 |
+
"model.layers.60.gka.v_proj.weight": "model-00014-of-00015.safetensors",
|
| 925 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 926 |
+
"model.layers.61.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 927 |
+
"model.layers.61.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
| 928 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
| 929 |
+
"model.layers.61.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
| 930 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 931 |
+
"model.layers.61.self_attn.k_norm.weight": "model-00014-of-00015.safetensors",
|
| 932 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
| 933 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
| 934 |
+
"model.layers.61.self_attn.q_norm.weight": "model-00014-of-00015.safetensors",
|
| 935 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
| 936 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
| 937 |
+
"model.layers.62.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 938 |
+
"model.layers.62.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
| 939 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
| 940 |
+
"model.layers.62.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
| 941 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 942 |
+
"model.layers.62.self_attn.k_norm.weight": "model-00014-of-00015.safetensors",
|
| 943 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
| 944 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
| 945 |
+
"model.layers.62.self_attn.q_norm.weight": "model-00014-of-00015.safetensors",
|
| 946 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
| 947 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
| 948 |
+
"model.layers.63.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 949 |
+
"model.layers.63.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
| 950 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
| 951 |
+
"model.layers.63.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
| 952 |
+
"model.layers.63.gka.A_log": "model-00014-of-00015.safetensors",
|
| 953 |
+
"model.layers.63.gka.a_proj.weight": "model-00014-of-00015.safetensors",
|
| 954 |
+
"model.layers.63.gka.alpha_proj.bias": "model-00014-of-00015.safetensors",
|
| 955 |
+
"model.layers.63.gka.alpha_proj.weight": "model-00014-of-00015.safetensors",
|
| 956 |
+
"model.layers.63.gka.b_proj.bias": "model-00014-of-00015.safetensors",
|
| 957 |
+
"model.layers.63.gka.b_proj.weight": "model-00014-of-00015.safetensors",
|
| 958 |
+
"model.layers.63.gka.dt_bias": "model-00014-of-00015.safetensors",
|
| 959 |
+
"model.layers.63.gka.g_proj.weight": "model-00014-of-00015.safetensors",
|
| 960 |
+
"model.layers.63.gka.k_conv1d.weight": "model-00014-of-00015.safetensors",
|
| 961 |
+
"model.layers.63.gka.k_proj.weight": "model-00014-of-00015.safetensors",
|
| 962 |
+
"model.layers.63.gka.o_norm.weight": "model-00014-of-00015.safetensors",
|
| 963 |
+
"model.layers.63.gka.o_proj.weight": "model-00014-of-00015.safetensors",
|
| 964 |
+
"model.layers.63.gka.q_conv1d.weight": "model-00014-of-00015.safetensors",
|
| 965 |
+
"model.layers.63.gka.q_proj.weight": "model-00014-of-00015.safetensors",
|
| 966 |
+
"model.layers.63.gka.v_conv1d.weight": "model-00014-of-00015.safetensors",
|
| 967 |
+
"model.layers.63.gka.v_proj.weight": "model-00014-of-00015.safetensors",
|
| 968 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 969 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 970 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
| 971 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
| 972 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
| 973 |
+
"model.layers.7.gka.A_log": "model-00002-of-00015.safetensors",
|
| 974 |
+
"model.layers.7.gka.a_proj.weight": "model-00002-of-00015.safetensors",
|
| 975 |
+
"model.layers.7.gka.alpha_proj.bias": "model-00002-of-00015.safetensors",
|
| 976 |
+
"model.layers.7.gka.alpha_proj.weight": "model-00002-of-00015.safetensors",
|
| 977 |
+
"model.layers.7.gka.b_proj.bias": "model-00002-of-00015.safetensors",
|
| 978 |
+
"model.layers.7.gka.b_proj.weight": "model-00002-of-00015.safetensors",
|
| 979 |
+
"model.layers.7.gka.dt_bias": "model-00002-of-00015.safetensors",
|
| 980 |
+
"model.layers.7.gka.g_proj.weight": "model-00002-of-00015.safetensors",
|
| 981 |
+
"model.layers.7.gka.k_conv1d.weight": "model-00002-of-00015.safetensors",
|
| 982 |
+
"model.layers.7.gka.k_proj.weight": "model-00002-of-00015.safetensors",
|
| 983 |
+
"model.layers.7.gka.o_norm.weight": "model-00002-of-00015.safetensors",
|
| 984 |
+
"model.layers.7.gka.o_proj.weight": "model-00002-of-00015.safetensors",
|
| 985 |
+
"model.layers.7.gka.q_conv1d.weight": "model-00002-of-00015.safetensors",
|
| 986 |
+
"model.layers.7.gka.q_proj.weight": "model-00002-of-00015.safetensors",
|
| 987 |
+
"model.layers.7.gka.v_conv1d.weight": "model-00002-of-00015.safetensors",
|
| 988 |
+
"model.layers.7.gka.v_proj.weight": "model-00002-of-00015.safetensors",
|
| 989 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 990 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 991 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
| 992 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
| 993 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
| 994 |
+
"model.layers.8.gka.A_log": "model-00003-of-00015.safetensors",
|
| 995 |
+
"model.layers.8.gka.a_proj.weight": "model-00003-of-00015.safetensors",
|
| 996 |
+
"model.layers.8.gka.alpha_proj.bias": "model-00003-of-00015.safetensors",
|
| 997 |
+
"model.layers.8.gka.alpha_proj.weight": "model-00003-of-00015.safetensors",
|
| 998 |
+
"model.layers.8.gka.b_proj.bias": "model-00003-of-00015.safetensors",
|
| 999 |
+
"model.layers.8.gka.b_proj.weight": "model-00003-of-00015.safetensors",
|
| 1000 |
+
"model.layers.8.gka.dt_bias": "model-00003-of-00015.safetensors",
|
| 1001 |
+
"model.layers.8.gka.g_proj.weight": "model-00003-of-00015.safetensors",
|
| 1002 |
+
"model.layers.8.gka.k_conv1d.weight": "model-00003-of-00015.safetensors",
|
| 1003 |
+
"model.layers.8.gka.k_proj.weight": "model-00003-of-00015.safetensors",
|
| 1004 |
+
"model.layers.8.gka.o_norm.weight": "model-00003-of-00015.safetensors",
|
| 1005 |
+
"model.layers.8.gka.o_proj.weight": "model-00003-of-00015.safetensors",
|
| 1006 |
+
"model.layers.8.gka.q_conv1d.weight": "model-00003-of-00015.safetensors",
|
| 1007 |
+
"model.layers.8.gka.q_proj.weight": "model-00003-of-00015.safetensors",
|
| 1008 |
+
"model.layers.8.gka.v_conv1d.weight": "model-00003-of-00015.safetensors",
|
| 1009 |
+
"model.layers.8.gka.v_proj.weight": "model-00003-of-00015.safetensors",
|
| 1010 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 1011 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 1012 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
| 1013 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
| 1014 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
| 1015 |
+
"model.layers.9.gka.A_log": "model-00003-of-00015.safetensors",
|
| 1016 |
+
"model.layers.9.gka.a_proj.weight": "model-00003-of-00015.safetensors",
|
| 1017 |
+
"model.layers.9.gka.alpha_proj.bias": "model-00003-of-00015.safetensors",
|
| 1018 |
+
"model.layers.9.gka.alpha_proj.weight": "model-00003-of-00015.safetensors",
|
| 1019 |
+
"model.layers.9.gka.b_proj.bias": "model-00003-of-00015.safetensors",
|
| 1020 |
+
"model.layers.9.gka.b_proj.weight": "model-00003-of-00015.safetensors",
|
| 1021 |
+
"model.layers.9.gka.dt_bias": "model-00003-of-00015.safetensors",
|
| 1022 |
+
"model.layers.9.gka.g_proj.weight": "model-00003-of-00015.safetensors",
|
| 1023 |
+
"model.layers.9.gka.k_conv1d.weight": "model-00003-of-00015.safetensors",
|
| 1024 |
+
"model.layers.9.gka.k_proj.weight": "model-00003-of-00015.safetensors",
|
| 1025 |
+
"model.layers.9.gka.o_norm.weight": "model-00003-of-00015.safetensors",
|
| 1026 |
+
"model.layers.9.gka.o_proj.weight": "model-00003-of-00015.safetensors",
|
| 1027 |
+
"model.layers.9.gka.q_conv1d.weight": "model-00003-of-00015.safetensors",
|
| 1028 |
+
"model.layers.9.gka.q_proj.weight": "model-00003-of-00015.safetensors",
|
| 1029 |
+
"model.layers.9.gka.v_conv1d.weight": "model-00003-of-00015.safetensors",
|
| 1030 |
+
"model.layers.9.gka.v_proj.weight": "model-00003-of-00015.safetensors",
|
| 1031 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 1032 |
+
"model.norm.weight": "model-00014-of-00015.safetensors"
|
| 1033 |
+
}
|
| 1034 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
+
size 11422650
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"model_max_length": 131072,
|
| 10 |
+
"pad_token": "<|endoftext|>",
|
| 11 |
+
"padding_side": "right",
|
| 12 |
+
"split_special_tokens": false,
|
| 13 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 14 |
+
"unk_token": null
|
| 15 |
+
}
|