Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +235 -0
- chat_template.jinja +154 -0
- config.json +95 -0
- generation_config.json +13 -0
- merge_metadata.json +70 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +701 -0
- tokenizer.json +3 -0
- tokenizer_config.json +32 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* 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
|
|
|
|
|
|
| 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 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- self-distillation
|
| 8 |
+
- ssd
|
| 9 |
+
- qwen
|
| 10 |
+
- qwen3.6
|
| 11 |
+
- moe
|
| 12 |
+
- deltanet
|
| 13 |
+
- linear-attention
|
| 14 |
+
- code-generation
|
| 15 |
+
- coding
|
| 16 |
+
- lora-merged
|
| 17 |
+
- bf16
|
| 18 |
+
base_model: Qwen/Qwen3.6-35B-A3B
|
| 19 |
+
pipeline_tag: text-generation
|
| 20 |
+
model-index:
|
| 21 |
+
- name: Qwen3.6-35B-A3B-SSD
|
| 22 |
+
results:
|
| 23 |
+
- task:
|
| 24 |
+
type: text-generation
|
| 25 |
+
dataset:
|
| 26 |
+
name: Self-generated coding dataset (SSD)
|
| 27 |
+
type: custom
|
| 28 |
+
metrics:
|
| 29 |
+
- name: Train Loss
|
| 30 |
+
type: train_loss
|
| 31 |
+
value: 0.523
|
| 32 |
+
- name: pass@10 (temp=0.7, 13 problems)
|
| 33 |
+
type: pass_at_k
|
| 34 |
+
value: 0.985
|
| 35 |
+
---
|
| 36 |
+
|
| 37 |
+
# Qwen3.6-35B-A3B-SSD
|
| 38 |
+
|
| 39 |
+
A self-distilled version of [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B), fine-tuned using the **Self-play Self-Distillation (SSD)** technique. The LoRA adapter has been merged into the base weights -- this is a standard bf16 model ready for direct use or quantization.
|
| 40 |
+
|
| 41 |
+
## What is SSD?
|
| 42 |
+
|
| 43 |
+
Self-play Self-Distillation generates training data from the model itself at high temperature (1.6), filters for correctness, then fine-tunes the model on its own best outputs. No external judge, no reward model, no human annotation required.
|
| 44 |
+
|
| 45 |
+
The key insight: training on the model's own high-temperature outputs acts as a form of self-distillation that improves pass@k at temperature > 0. At temp=0, the merged model produces output identical to base. The improvement appears in the diversity and correctness of samples at higher temperatures.
|
| 46 |
+
|
| 47 |
+
## Model Details
|
| 48 |
+
|
| 49 |
+
| Property | Value |
|
| 50 |
+
|----------|-------|
|
| 51 |
+
| Architecture | Qwen3.5 MoE with Gated DeltaNet linear attention |
|
| 52 |
+
| Total parameters | 34.66B |
|
| 53 |
+
| Active parameters | ~3B (Mixture of Experts, 256 experts, 8 active per token) |
|
| 54 |
+
| Hidden layers | 40 (30 linear attention + 10 full attention) |
|
| 55 |
+
| Precision | bfloat16 |
|
| 56 |
+
| Model size on disk | ~64 GB |
|
| 57 |
+
| Context length | 262,144 tokens |
|
| 58 |
+
| License | Apache 2.0 |
|
| 59 |
+
|
| 60 |
+
## Training Details
|
| 61 |
+
|
| 62 |
+
### Method
|
| 63 |
+
|
| 64 |
+
1. Generated 2,000 coding solutions from the base model at temp=1.6, top_k=20, top_p=0.8
|
| 65 |
+
2. Filtered for correctness (execution + test pass) -- 1,796 samples survived
|
| 66 |
+
3. Split into 1,616 train / 180 validation
|
| 67 |
+
4. Fine-tuned with LoRA, then merged adapter into base weights
|
| 68 |
+
|
| 69 |
+
### LoRA Configuration
|
| 70 |
+
|
| 71 |
+
| Parameter | Value |
|
| 72 |
+
|-----------|-------|
|
| 73 |
+
| Rank (r) | 16 |
|
| 74 |
+
| Alpha | 16 |
|
| 75 |
+
| Dropout | 0.0 |
|
| 76 |
+
| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj, in_proj_qkv, in_proj_z, out_proj |
|
| 77 |
+
| Trainable parameters | 19.2M / 34.66B (0.055%) |
|
| 78 |
+
|
| 79 |
+
The target modules include both standard transformer attention/MLP layers and Qwen3.6's DeltaNet linear attention layers (in_proj_qkv, in_proj_z, out_proj).
|
| 80 |
+
|
| 81 |
+
### Training Hyperparameters
|
| 82 |
+
|
| 83 |
+
| Parameter | Value |
|
| 84 |
+
|-----------|-------|
|
| 85 |
+
| Optimizer | AdamW 8-bit |
|
| 86 |
+
| Learning rate | 2e-4 (cosine schedule) |
|
| 87 |
+
| Warmup | 6% of steps |
|
| 88 |
+
| Max steps | 150 |
|
| 89 |
+
| Batch size | 4 |
|
| 90 |
+
| Gradient accumulation | 8 (effective batch = 32) |
|
| 91 |
+
| Max sequence length | 2,048 |
|
| 92 |
+
| Weight decay | 0.01 |
|
| 93 |
+
| Precision | bfloat16 (no quantization during training) |
|
| 94 |
+
| Seed | 42 |
|
| 95 |
+
|
| 96 |
+
### Training Results
|
| 97 |
+
|
| 98 |
+
| Metric | Value |
|
| 99 |
+
|--------|-------|
|
| 100 |
+
| Final train loss | 0.523 |
|
| 101 |
+
| Eval loss | 0.482 (at step 150) |
|
| 102 |
+
| Token accuracy | 85.9% |
|
| 103 |
+
| Training time | 78 min |
|
| 104 |
+
| Peak GPU memory | 64.7 GB |
|
| 105 |
+
| Hardware | NVIDIA H200 (Modal cloud) |
|
| 106 |
+
| Estimated cost | ~$6.20 |
|
| 107 |
+
|
| 108 |
+
### Merge
|
| 109 |
+
|
| 110 |
+
Adapter merged into base weights using `PeftModel.merge_and_unload()` from PEFT 0.19.1. The result is a standard HuggingFace model -- no adapter loading required at inference time.
|
| 111 |
+
|
| 112 |
+
## Evaluation
|
| 113 |
+
|
| 114 |
+
Tested as a 6-bit MLX quantization on Mac Studio M4 Max (128GB) against the base model (unsloth 4-bit quantization). 13 coding problems, 10 samples each at temp=0.7:
|
| 115 |
+
|
| 116 |
+
| Problem difficulty | Base (4-bit) | Merged (6-bit) |
|
| 117 |
+
|-------------------|-------------|----------------|
|
| 118 |
+
| Easy (5 problems) | 50/50 (100%) | 50/50 (100%) |
|
| 119 |
+
| Hard (8 problems) | 76/80 (95%) | 78/80 (98%) |
|
| 120 |
+
| **Overall** | **126/130 (97%)** | **128/130 (98%)** |
|
| 121 |
+
|
| 122 |
+
Biggest improvement on the hardest problem (expression evaluator with operator precedence and parentheses): base 7/10 → merged 9/10.
|
| 123 |
+
|
| 124 |
+
| Metric | Value |
|
| 125 |
+
|--------|-------|
|
| 126 |
+
| Inference speed (6-bit MLX) | 78.9 tok/s average |
|
| 127 |
+
| Base model speed (4-bit MLX) | 86.7 tok/s average |
|
| 128 |
+
|
| 129 |
+
Note: At temp=0, the merged model produces output identical to the base model. The SSD improvement manifests at temperature > 0 through improved sample diversity and correctness, particularly on harder problems.
|
| 130 |
+
|
| 131 |
+
## How to Use
|
| 132 |
+
|
| 133 |
+
### With Transformers
|
| 134 |
+
|
| 135 |
+
```python
|
| 136 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 137 |
+
import torch
|
| 138 |
+
|
| 139 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 140 |
+
"shaneMattner/Qwen3.6-35B-A3B-SSD",
|
| 141 |
+
torch_dtype=torch.bfloat16,
|
| 142 |
+
device_map="auto",
|
| 143 |
+
attn_implementation="eager",
|
| 144 |
+
)
|
| 145 |
+
tokenizer = AutoTokenizer.from_pretrained("shaneMattner/Qwen3.6-35B-A3B-SSD")
|
| 146 |
+
|
| 147 |
+
messages = [
|
| 148 |
+
{"role": "user", "content": "Write a Python function to merge two sorted lists into one sorted list."}
|
| 149 |
+
]
|
| 150 |
+
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 151 |
+
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
| 152 |
+
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)
|
| 153 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
| 154 |
+
```
|
| 155 |
+
|
| 156 |
+
### With MLX (Apple Silicon)
|
| 157 |
+
|
| 158 |
+
```bash
|
| 159 |
+
pip install mlx-lm
|
| 160 |
+
```
|
| 161 |
+
|
| 162 |
+
```python
|
| 163 |
+
from mlx_lm import load, generate
|
| 164 |
+
|
| 165 |
+
model, tokenizer = load("shaneMattner/Qwen3.6-35B-A3B-SSD")
|
| 166 |
+
response = generate(
|
| 167 |
+
model,
|
| 168 |
+
tokenizer,
|
| 169 |
+
prompt="Write a Python function to merge two sorted lists.",
|
| 170 |
+
max_tokens=512,
|
| 171 |
+
)
|
| 172 |
+
print(response)
|
| 173 |
+
```
|
| 174 |
+
|
| 175 |
+
Or quantize first for faster inference:
|
| 176 |
+
|
| 177 |
+
```bash
|
| 178 |
+
# Convert to 6-bit MLX format
|
| 179 |
+
python -m mlx_lm.convert \
|
| 180 |
+
--hf-path shaneMattner/Qwen3.6-35B-A3B-SSD \
|
| 181 |
+
--mlx-path Qwen3.6-35B-A3B-SSD-6bit \
|
| 182 |
+
-q --q-bits 6
|
| 183 |
+
```
|
| 184 |
+
|
| 185 |
+
**Note**: If you encounter errors related to `model_type`, you may need to change `"model_type": "qwen3_5_moe_text"` to `"model_type": "qwen3_5_moe"` in `config.json` for mlx-lm compatibility.
|
| 186 |
+
|
| 187 |
+
### With llama.cpp / GGUF
|
| 188 |
+
|
| 189 |
+
Convert to GGUF for use with llama.cpp, Ollama, or other GGUF-compatible tools:
|
| 190 |
+
|
| 191 |
+
```bash
|
| 192 |
+
# Clone llama.cpp and convert
|
| 193 |
+
python convert_hf_to_gguf.py shaneMattner/Qwen3.6-35B-A3B-SSD --outtype bf16
|
| 194 |
+
|
| 195 |
+
# Quantize to desired format
|
| 196 |
+
./llama-quantize Qwen3.6-35B-A3B-SSD-bf16.gguf Qwen3.6-35B-A3B-SSD-Q4_K_M.gguf Q4_K_M
|
| 197 |
+
```
|
| 198 |
+
|
| 199 |
+
## Limitations
|
| 200 |
+
|
| 201 |
+
- **Coding-focused**: Fine-tuned exclusively on Python coding tasks. General instruction following may not improve (or may slightly regress) compared to the base model.
|
| 202 |
+
- **Bounded by base model**: Self-distillation cannot exceed the base model's capability ceiling -- it improves sampling consistency, not peak ability.
|
| 203 |
+
- **Small training set**: 1,616 samples is a proof-of-concept. Larger datasets with more diverse problems would likely yield stronger results.
|
| 204 |
+
- **Eval coverage**: Tested on 5 coding problems only. Broader benchmarks (HumanEval, MBPP, etc.) have not been run.
|
| 205 |
+
- **DeltaNet targeting**: The in_proj_a and in_proj_b DeltaNet gating layers were not included in LoRA targets -- adding them may improve results in future iterations.
|
| 206 |
+
|
| 207 |
+
## Architecture Notes
|
| 208 |
+
|
| 209 |
+
Qwen3.6-35B-A3B uses a hybrid architecture:
|
| 210 |
+
- **Mixture of Experts (MoE)**: 256 experts with 8 active per token, keeping active compute at ~3B parameters despite 34.66B total
|
| 211 |
+
- **Gated DeltaNet linear attention**: 30 of 40 layers use linear attention (every 4th layer uses full attention), enabling efficient long-context processing
|
| 212 |
+
- **262K context window**: Supports up to 262,144 tokens
|
| 213 |
+
|
| 214 |
+
## Citation
|
| 215 |
+
|
| 216 |
+
If you use this model, please cite:
|
| 217 |
+
|
| 218 |
+
```bibtex
|
| 219 |
+
@misc{mattner2026qwen36ssd,
|
| 220 |
+
title={Qwen3.6-35B-A3B-SSD: Self-Distilled Qwen3.6 for Coding},
|
| 221 |
+
author={Shane Mattner},
|
| 222 |
+
year={2026},
|
| 223 |
+
url={https://huggingface.co/shaneMattner/Qwen3.6-35B-A3B-SSD}
|
| 224 |
+
}
|
| 225 |
+
```
|
| 226 |
+
|
| 227 |
+
### Related Work
|
| 228 |
+
|
| 229 |
+
- [Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) -- Base model by Qwen team
|
| 230 |
+
- [LoRA: Low-Rank Adaptation of Large Language Models](https://arxiv.org/abs/2106.09685) -- Hu et al., 2021
|
| 231 |
+
- Self-play Self-Distillation (SSD) technique for improving pass@k at temperature > 0
|
| 232 |
+
|
| 233 |
+
## License
|
| 234 |
+
|
| 235 |
+
Apache 2.0 (same as the base model [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B))
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attn_output_gate": true,
|
| 8 |
+
"bos_token_id": 248044,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 248044,
|
| 11 |
+
"full_attention_interval": 4,
|
| 12 |
+
"head_dim": 256,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 2048,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"layer_types": [
|
| 17 |
+
"linear_attention",
|
| 18 |
+
"linear_attention",
|
| 19 |
+
"linear_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"linear_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"full_attention"
|
| 57 |
+
],
|
| 58 |
+
"linear_conv_kernel_dim": 4,
|
| 59 |
+
"linear_key_head_dim": 128,
|
| 60 |
+
"linear_num_key_heads": 16,
|
| 61 |
+
"linear_num_value_heads": 32,
|
| 62 |
+
"linear_value_head_dim": 128,
|
| 63 |
+
"mamba_ssm_dtype": "float32",
|
| 64 |
+
"max_position_embeddings": 262144,
|
| 65 |
+
"model_type": "qwen3_5_moe",
|
| 66 |
+
"moe_intermediate_size": 512,
|
| 67 |
+
"mtp_num_hidden_layers": 1,
|
| 68 |
+
"mtp_use_dedicated_embeddings": false,
|
| 69 |
+
"num_attention_heads": 16,
|
| 70 |
+
"num_experts": 256,
|
| 71 |
+
"num_experts_per_tok": 8,
|
| 72 |
+
"num_hidden_layers": 40,
|
| 73 |
+
"num_key_value_heads": 2,
|
| 74 |
+
"output_router_logits": false,
|
| 75 |
+
"pad_token_id": null,
|
| 76 |
+
"partial_rotary_factor": 0.25,
|
| 77 |
+
"rms_norm_eps": 1e-06,
|
| 78 |
+
"rope_parameters": {
|
| 79 |
+
"mrope_interleaved": true,
|
| 80 |
+
"mrope_section": [
|
| 81 |
+
11,
|
| 82 |
+
11,
|
| 83 |
+
10
|
| 84 |
+
],
|
| 85 |
+
"partial_rotary_factor": 0.25,
|
| 86 |
+
"rope_theta": 10000000,
|
| 87 |
+
"rope_type": "default"
|
| 88 |
+
},
|
| 89 |
+
"router_aux_loss_coef": 0.001,
|
| 90 |
+
"shared_expert_intermediate_size": 512,
|
| 91 |
+
"tie_word_embeddings": false,
|
| 92 |
+
"transformers_version": "5.8.0",
|
| 93 |
+
"use_cache": true,
|
| 94 |
+
"vocab_size": 248320
|
| 95 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 248044,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
248046,
|
| 6 |
+
248044
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 248044,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "5.8.0"
|
| 13 |
+
}
|
merge_metadata.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"experiment": "ssd-Qwen3.6-35B-A3B-r16-full-20260505-184155",
|
| 3 |
+
"base_model": "Qwen/Qwen3.6-35B-A3B",
|
| 4 |
+
"adapter_path": "/checkpoints/experiments/ssd-Qwen3.6-35B-A3B-r16-full-20260505-184155/final_adapter",
|
| 5 |
+
"merged_at": "2026-05-06T07:14:33",
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"merge_method": "PeftModel.merge_and_unload()",
|
| 8 |
+
"training_metadata": {
|
| 9 |
+
"experiment": "ssd-Qwen3.6-35B-A3B-r16-full-20260505-184155",
|
| 10 |
+
"model": "Qwen/Qwen3.6-35B-A3B",
|
| 11 |
+
"config": {
|
| 12 |
+
"model_name": "Qwen/Qwen3.6-35B-A3B",
|
| 13 |
+
"max_seq_length": 2048,
|
| 14 |
+
"load_in_4bit": false,
|
| 15 |
+
"load_in_8bit": false,
|
| 16 |
+
"lora_r": 16,
|
| 17 |
+
"lora_alpha": 16,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"lora_bias": "none",
|
| 20 |
+
"use_rslora": false,
|
| 21 |
+
"optim": "adamw_8bit",
|
| 22 |
+
"batch_size": 4,
|
| 23 |
+
"gradient_accumulation_steps": 8,
|
| 24 |
+
"packing": false,
|
| 25 |
+
"learning_rate": 0.0002,
|
| 26 |
+
"lr_scheduler_type": "cosine",
|
| 27 |
+
"warmup_steps": 0.06,
|
| 28 |
+
"weight_decay": 0.01,
|
| 29 |
+
"max_steps": 150,
|
| 30 |
+
"save_steps": 50,
|
| 31 |
+
"eval_steps": 25,
|
| 32 |
+
"logging_steps": 5,
|
| 33 |
+
"seed": 42,
|
| 34 |
+
"experiment_name": "ssd-Qwen3.6-35B-A3B-r16-full-20260505-184155",
|
| 35 |
+
"skip_eval": false,
|
| 36 |
+
"smoke_test": false
|
| 37 |
+
},
|
| 38 |
+
"results": {
|
| 39 |
+
"train_loss": 0.5228066476186116,
|
| 40 |
+
"steps": 150,
|
| 41 |
+
"epoch": null
|
| 42 |
+
},
|
| 43 |
+
"timings": {
|
| 44 |
+
"model_load_sec": 31.11,
|
| 45 |
+
"data_load_sec": 22.24,
|
| 46 |
+
"lora_setup_sec": 9.57,
|
| 47 |
+
"training_sec": 4606.66,
|
| 48 |
+
"training_loss": 0.5228,
|
| 49 |
+
"training_steps": 150,
|
| 50 |
+
"save_sec": 1.65,
|
| 51 |
+
"step_timing": {
|
| 52 |
+
"total_steps": 150,
|
| 53 |
+
"avg_step_sec": 29.347,
|
| 54 |
+
"min_step_sec": 14.719,
|
| 55 |
+
"max_step_sec": 33.735,
|
| 56 |
+
"total_step_sec": 4402.09,
|
| 57 |
+
"eval_count": 5,
|
| 58 |
+
"total_eval_sec": 3821.16,
|
| 59 |
+
"save_count": 3,
|
| 60 |
+
"total_save_sec": 10.16,
|
| 61 |
+
"peak_gpu_gb": 64.7
|
| 62 |
+
},
|
| 63 |
+
"total_sec": 4690.74,
|
| 64 |
+
"total_min": 78.18,
|
| 65 |
+
"total_params": 34679779968,
|
| 66 |
+
"trainable_params": 19169280,
|
| 67 |
+
"trainable_pct": 0.0553
|
| 68 |
+
}
|
| 69 |
+
}
|
| 70 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2438ff5493ab1e5f24638dbcdf686b3e67058cd5bd7a3cc6abf075d40651a313
|
| 3 |
+
size 49739502312
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41f898a7e644e674d3992dc40213369f67fffcc9344ea651cf32dd32ca2a9098
|
| 3 |
+
size 19581812712
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,701 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 34660610688,
|
| 4 |
+
"total_size": 69321221376
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.0.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.1.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.1.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.1.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.1.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.10.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.10.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.10.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.10.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.10.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.11.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.11.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.11.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.11.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.11.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.12.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.12.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.12.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.12.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.12.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.13.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.13.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.13.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.13.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.13.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.14.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.14.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.14.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.14.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.14.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.15.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.15.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.15.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.15.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.15.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.16.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.16.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.16.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.16.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.16.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.17.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.17.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.17.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.17.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.17.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.18.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.18.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.18.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.18.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.18.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.19.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.19.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.19.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.19.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.19.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.2.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.2.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.2.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.2.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.2.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.20.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.20.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.20.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.20.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.20.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.21.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.21.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.21.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.21.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.21.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.22.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.22.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.22.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.22.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.22.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.23.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.23.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.23.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.23.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.23.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.24.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.24.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.24.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.24.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.24.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.25.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.25.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.25.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.25.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.25.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.26.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.26.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.26.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.26.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.26.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.27.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.27.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.27.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.27.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.27.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.28.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.28.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.28.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.28.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.28.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.29.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.29.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.29.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 404 |
+
"model.language_model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 405 |
+
"model.language_model.layers.29.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"model.language_model.layers.29.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 407 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 408 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.language_model.layers.3.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.language_model.layers.3.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.language_model.layers.3.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.language_model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.language_model.layers.3.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.language_model.layers.3.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 425 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 426 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 427 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 428 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 429 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 430 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 433 |
+
"model.language_model.layers.30.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.language_model.layers.30.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.language_model.layers.30.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.language_model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.language_model.layers.30.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.language_model.layers.30.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 441 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 442 |
+
"model.language_model.layers.31.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 443 |
+
"model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 444 |
+
"model.language_model.layers.31.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 445 |
+
"model.language_model.layers.31.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 446 |
+
"model.language_model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 447 |
+
"model.language_model.layers.31.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 448 |
+
"model.language_model.layers.31.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 449 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 450 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 451 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 453 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 454 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 455 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 456 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 457 |
+
"model.language_model.layers.32.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 458 |
+
"model.language_model.layers.32.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 459 |
+
"model.language_model.layers.32.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 460 |
+
"model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 461 |
+
"model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 462 |
+
"model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 463 |
+
"model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"model.language_model.layers.32.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 465 |
+
"model.language_model.layers.32.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 466 |
+
"model.language_model.layers.32.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 467 |
+
"model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 468 |
+
"model.language_model.layers.32.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 469 |
+
"model.language_model.layers.32.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 470 |
+
"model.language_model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 471 |
+
"model.language_model.layers.32.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 472 |
+
"model.language_model.layers.32.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 473 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 474 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 475 |
+
"model.language_model.layers.33.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 476 |
+
"model.language_model.layers.33.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 477 |
+
"model.language_model.layers.33.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 478 |
+
"model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 479 |
+
"model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 480 |
+
"model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 481 |
+
"model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 482 |
+
"model.language_model.layers.33.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 483 |
+
"model.language_model.layers.33.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 484 |
+
"model.language_model.layers.33.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 485 |
+
"model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 486 |
+
"model.language_model.layers.33.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 487 |
+
"model.language_model.layers.33.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"model.language_model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 489 |
+
"model.language_model.layers.33.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.language_model.layers.33.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 492 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 493 |
+
"model.language_model.layers.34.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 494 |
+
"model.language_model.layers.34.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 495 |
+
"model.language_model.layers.34.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.language_model.layers.34.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.language_model.layers.34.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.language_model.layers.34.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.language_model.layers.34.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.language_model.layers.34.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.language_model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.language_model.layers.34.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.language_model.layers.34.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.language_model.layers.35.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.language_model.layers.35.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.language_model.layers.35.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.language_model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.language_model.layers.35.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.language_model.layers.35.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.language_model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.language_model.layers.36.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.language_model.layers.36.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.language_model.layers.36.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.language_model.layers.36.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.language_model.layers.36.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.language_model.layers.36.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.language_model.layers.36.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.language_model.layers.36.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.language_model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.language_model.layers.36.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.language_model.layers.36.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.language_model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.language_model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.language_model.layers.37.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.language_model.layers.37.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.language_model.layers.37.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.language_model.layers.37.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.language_model.layers.37.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.language_model.layers.37.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.language_model.layers.37.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.language_model.layers.37.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.language_model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.language_model.layers.37.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.language_model.layers.37.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.language_model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.language_model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.language_model.layers.38.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.language_model.layers.38.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.language_model.layers.38.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.language_model.layers.38.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.language_model.layers.38.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.language_model.layers.38.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.language_model.layers.38.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.language_model.layers.38.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.language_model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.language_model.layers.38.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.language_model.layers.38.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.language_model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.language_model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.language_model.layers.39.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.language_model.layers.39.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.language_model.layers.39.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.language_model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.language_model.layers.39.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.language_model.layers.39.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.language_model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.language_model.layers.39.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.language_model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.language_model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.language_model.layers.39.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.language_model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.language_model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.language_model.layers.4.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.language_model.layers.4.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.language_model.layers.4.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.language_model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.language_model.layers.4.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.language_model.layers.4.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.language_model.layers.5.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.language_model.layers.5.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.language_model.layers.5.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.language_model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.language_model.layers.5.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.language_model.layers.5.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 637 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"model.language_model.layers.6.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 641 |
+
"model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 642 |
+
"model.language_model.layers.6.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"model.language_model.layers.6.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"model.language_model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 645 |
+
"model.language_model.layers.6.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"model.language_model.layers.6.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 647 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"model.language_model.layers.7.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 650 |
+
"model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 651 |
+
"model.language_model.layers.7.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.language_model.layers.7.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.language_model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.language_model.layers.7.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.language_model.layers.7.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 661 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 663 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.language_model.layers.8.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.language_model.layers.8.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.language_model.layers.8.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.language_model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.language_model.layers.8.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.language_model.layers.8.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 689 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"model.language_model.layers.9.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 692 |
+
"model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 693 |
+
"model.language_model.layers.9.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"model.language_model.layers.9.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"model.language_model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"model.language_model.layers.9.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 697 |
+
"model.language_model.layers.9.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 699 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors"
|
| 700 |
+
}
|
| 701 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null,
|
| 29 |
+
"video_token": "<|video_pad|>",
|
| 30 |
+
"vision_bos_token": "<|vision_start|>",
|
| 31 |
+
"vision_eos_token": "<|vision_end|>"
|
| 32 |
+
}
|