Sky v2.0 — CREST 11B (adaptive-depth reasoning)
Browse files- .gitattributes +1 -0
- README.md +114 -0
- benchmarks.json +18 -0
- chat_template.jinja +154 -0
- config.json +83 -0
- crest_block.py +213 -0
- generation_config.json +6 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.safetensors.index.json +882 -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 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen3.5-4B
|
| 4 |
+
tags:
|
| 5 |
+
- crest
|
| 6 |
+
- adaptive-depth
|
| 7 |
+
- sky
|
| 8 |
+
- 0labs
|
| 9 |
+
- qwen
|
| 10 |
+
- fine-tuned
|
| 11 |
+
language:
|
| 12 |
+
- en
|
| 13 |
+
pipeline_tag: text-generation
|
| 14 |
+
library_name: transformers
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Sky v2.0 — 11B (CREST Architecture)
|
| 18 |
+
|
| 19 |
+
<img src="https://img.shields.io/badge/0labs-Sky%20v2.0-blue" alt="Sky v2.0">
|
| 20 |
+
|
| 21 |
+
## Overview
|
| 22 |
+
|
| 23 |
+
**Sky v2.0** is an 11B parameter AI model built by [0labs](https://huggingface.co/0labs-in), created by **Atharvsinh Jadav** from Gujarat, India.
|
| 24 |
+
|
| 25 |
+
It is based on **Qwen3.5-4B** retrofitted with the novel **CREST (Cognitively Recurrent Estimation of Step Termination)** architecture, which enables **adaptive-depth reasoning** — the model can dynamically decide how many computational steps to use per token.
|
| 26 |
+
|
| 27 |
+
## Architecture: CREST
|
| 28 |
+
|
| 29 |
+
CREST replaces each MLP/FFN layer with a recurrent block containing:
|
| 30 |
+
- **4 independent MLP copies** (Step 1 = original pretrained weights)
|
| 31 |
+
- **Learned halting mechanism** — decides when to stop thinking
|
| 32 |
+
- **Weighted accumulation** — outputs are probability-weighted across steps
|
| 33 |
+
|
| 34 |
+
This expands the model from 4.21B → **11.00B parameters** while preserving the original pretrained knowledge as Step 1.
|
| 35 |
+
|
| 36 |
+
```
|
| 37 |
+
Original (4.21B): Attention → MLP → next layer
|
| 38 |
+
CREST (11.00B): Attention → [MLP₁ → MLP₂ → MLP₃ → MLP₄] → next layer
|
| 39 |
+
(adaptive halting decides when to stop)
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
## Training
|
| 43 |
+
|
| 44 |
+
- **Base model**: Qwen/Qwen3.5-4B
|
| 45 |
+
- **CREST retrofit**: 4 independent MLP steps per layer
|
| 46 |
+
- **Fine-tuning**: LoRA (rank 32) on attention + CREST halting params
|
| 47 |
+
- **Dataset**: 5,667 examples (identity, CSD, SAIL, coding, research)
|
| 48 |
+
- **Hardware**: AMD Instinct MI300X (205GB VRAM)
|
| 49 |
+
- **Training time**: ~2.3 hours
|
| 50 |
+
|
| 51 |
+
## Benchmarks
|
| 52 |
+
|
| 53 |
+
| Benchmark | Score |
|
| 54 |
+
|---|---|
|
| 55 |
+
| **Code Eval (25 problems)** | **100% (25/25)** ✅ |
|
| 56 |
+
| Identity (Who are you?) | Sky v2.0 / 0labs ✅ |
|
| 57 |
+
| Math (25×17) | 425 ✅ |
|
| 58 |
+
| MMLU-Pro (200 subset) | 45.5% |
|
| 59 |
+
|
| 60 |
+
## Usage
|
| 61 |
+
|
| 62 |
+
```python
|
| 63 |
+
import torch
|
| 64 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 65 |
+
|
| 66 |
+
# Note: Requires crest_block.py from this repo
|
| 67 |
+
tokenizer = AutoTokenizer.from_pretrained("0labs-in/Sky-v2.0-11B", trust_remote_code=True)
|
| 68 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 69 |
+
"0labs-in/Sky-v2.0-11B",
|
| 70 |
+
torch_dtype=torch.bfloat16,
|
| 71 |
+
device_map="auto",
|
| 72 |
+
trust_remote_code=True
|
| 73 |
+
)
|
| 74 |
+
|
| 75 |
+
messages = [{"role": "user", "content": "Who are you?"}]
|
| 76 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 77 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
| 78 |
+
output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
|
| 79 |
+
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
| 80 |
+
```
|
| 81 |
+
|
| 82 |
+
## Identity
|
| 83 |
+
|
| 84 |
+
Sky v2.0 is trained to identify as:
|
| 85 |
+
- **Name**: Sky v2.0
|
| 86 |
+
- **Creator**: Atharvsinh Jadav
|
| 87 |
+
- **Organization**: 0labs (Gujarat, India)
|
| 88 |
+
- **Family**: Sky model family
|
| 89 |
+
|
| 90 |
+
## Research: CREST Architecture
|
| 91 |
+
|
| 92 |
+
CREST (Cognitively Recurrent Estimation of Step Termination) is a novel architecture developed by 0labs that enables:
|
| 93 |
+
1. **Variable computational depth** — harder tokens get more compute
|
| 94 |
+
2. **Adaptive halting** — learned mechanism decides processing depth
|
| 95 |
+
3. **Preserved pretrained knowledge** — Step 1 = original model weights
|
| 96 |
+
4. **Ponder regularization** — prevents unnecessary computation
|
| 97 |
+
|
| 98 |
+
Paper forthcoming.
|
| 99 |
+
|
| 100 |
+
## License
|
| 101 |
+
|
| 102 |
+
Apache 2.0
|
| 103 |
+
|
| 104 |
+
## Citation
|
| 105 |
+
|
| 106 |
+
```bibtex
|
| 107 |
+
@misc{sky-v2-crest-2026,
|
| 108 |
+
title={Sky v2.0: Adaptive-Depth Reasoning via CREST Architecture},
|
| 109 |
+
author={Jadav, Atharvsinh},
|
| 110 |
+
year={2026},
|
| 111 |
+
publisher={0labs},
|
| 112 |
+
url={https://huggingface.co/0labs-in/Sky-v2.0-11B}
|
| 113 |
+
}
|
| 114 |
+
```
|
benchmarks.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"code_eval": {
|
| 3 |
+
"passed": 25,
|
| 4 |
+
"total": 25,
|
| 5 |
+
"accuracy": 100.0
|
| 6 |
+
},
|
| 7 |
+
"mmlu_pro_200": {
|
| 8 |
+
"correct": 91,
|
| 9 |
+
"total": 200,
|
| 10 |
+
"accuracy": 45.5
|
| 11 |
+
},
|
| 12 |
+
"identity": "Sky v2.0 / 0labs / Atharvsinh Jadav",
|
| 13 |
+
"architecture": "CREST (4 steps, adaptive halting)",
|
| 14 |
+
"base_model": "Qwen/Qwen3.5-4B",
|
| 15 |
+
"total_params": "11.00B",
|
| 16 |
+
"training_time": "2.3 hours",
|
| 17 |
+
"hardware": "AMD MI300X (205GB VRAM)"
|
| 18 |
+
}
|
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 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 | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 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 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attn_output_gate": true,
|
| 8 |
+
"bos_token_id": null,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 248044,
|
| 11 |
+
"full_attention_interval": 4,
|
| 12 |
+
"head_dim": 256,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 2560,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 9216,
|
| 17 |
+
"layer_types": [
|
| 18 |
+
"linear_attention",
|
| 19 |
+
"linear_attention",
|
| 20 |
+
"linear_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"full_attention"
|
| 50 |
+
],
|
| 51 |
+
"linear_conv_kernel_dim": 4,
|
| 52 |
+
"linear_key_head_dim": 128,
|
| 53 |
+
"linear_num_key_heads": 16,
|
| 54 |
+
"linear_num_value_heads": 32,
|
| 55 |
+
"linear_value_head_dim": 128,
|
| 56 |
+
"mamba_ssm_dtype": "float32",
|
| 57 |
+
"max_position_embeddings": 262144,
|
| 58 |
+
"mlp_only_layers": [],
|
| 59 |
+
"model_type": "qwen3_5_text",
|
| 60 |
+
"mtp_num_hidden_layers": 1,
|
| 61 |
+
"mtp_use_dedicated_embeddings": false,
|
| 62 |
+
"num_attention_heads": 16,
|
| 63 |
+
"num_hidden_layers": 32,
|
| 64 |
+
"num_key_value_heads": 4,
|
| 65 |
+
"pad_token_id": null,
|
| 66 |
+
"partial_rotary_factor": 0.25,
|
| 67 |
+
"rms_norm_eps": 1e-06,
|
| 68 |
+
"rope_parameters": {
|
| 69 |
+
"mrope_interleaved": true,
|
| 70 |
+
"mrope_section": [
|
| 71 |
+
11,
|
| 72 |
+
11,
|
| 73 |
+
10
|
| 74 |
+
],
|
| 75 |
+
"partial_rotary_factor": 0.25,
|
| 76 |
+
"rope_theta": 10000000,
|
| 77 |
+
"rope_type": "default"
|
| 78 |
+
},
|
| 79 |
+
"tie_word_embeddings": true,
|
| 80 |
+
"transformers_version": "5.7.0.dev0",
|
| 81 |
+
"use_cache": true,
|
| 82 |
+
"vocab_size": 248320
|
| 83 |
+
}
|
crest_block.py
ADDED
|
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
CREST Block v2 — Cognitively Recurrent Estimation of Step Termination
|
| 3 |
+
=====================================================================
|
| 4 |
+
Authors: ENI & LO (0labs, Gujarat, India)
|
| 5 |
+
Date: April 2026 — v2 (fixed initialization stability)
|
| 6 |
+
|
| 7 |
+
Key fix from v1: Step 1 now produces IDENTICAL output to original MLP.
|
| 8 |
+
No extra RMSNorm or h0 residual on step 1. Steps 2+ use lightweight
|
| 9 |
+
residual mixing instead of full norm, preventing gradient instability.
|
| 10 |
+
"""
|
| 11 |
+
|
| 12 |
+
import math
|
| 13 |
+
import copy
|
| 14 |
+
import torch
|
| 15 |
+
import torch.nn as nn
|
| 16 |
+
import torch.nn.functional as F
|
| 17 |
+
from typing import Optional, Tuple
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
class CRESTBlock(nn.Module):
|
| 21 |
+
"""
|
| 22 |
+
CREST Block v2 — replaces a standard FFN/MLP sublayer.
|
| 23 |
+
|
| 24 |
+
v2 fixes:
|
| 25 |
+
- Step 1 output is IDENTICAL to original MLP (no extra norm/residual)
|
| 26 |
+
- Steps 2+ use learned residual gate instead of RMSNorm
|
| 27 |
+
- Halting bias initialized higher (6.0) for safer start
|
| 28 |
+
"""
|
| 29 |
+
|
| 30 |
+
def __init__(
|
| 31 |
+
self,
|
| 32 |
+
original_mlp: nn.Module,
|
| 33 |
+
hidden_size: int,
|
| 34 |
+
max_steps: int = 4,
|
| 35 |
+
eps: float = 1e-5,
|
| 36 |
+
):
|
| 37 |
+
super().__init__()
|
| 38 |
+
self.max_steps = max_steps
|
| 39 |
+
self.hidden_size = hidden_size
|
| 40 |
+
self.eps = eps
|
| 41 |
+
|
| 42 |
+
# ── Independent FFN per step ────────────────────────────────
|
| 43 |
+
self.steps = nn.ModuleList()
|
| 44 |
+
self.steps.append(original_mlp) # Step 1 = original (untouched)
|
| 45 |
+
for _ in range(max_steps - 1):
|
| 46 |
+
self.steps.append(copy.deepcopy(original_mlp))
|
| 47 |
+
|
| 48 |
+
# ── Halting mechanism ───────────────────────────────────────
|
| 49 |
+
self.halt_linear = nn.Linear(hidden_size, 1, bias=True)
|
| 50 |
+
nn.init.zeros_(self.halt_linear.weight)
|
| 51 |
+
nn.init.constant_(self.halt_linear.bias, 6.0) # sigmoid(6)≈0.9975
|
| 52 |
+
|
| 53 |
+
# ── Residual gates for steps 2+ ─────────────────────────────
|
| 54 |
+
# Learned scalar that controls how much h0 mixes into step output
|
| 55 |
+
# Initialized to 0 → steps 2+ start identical to step 1
|
| 56 |
+
self.residual_gates = nn.ParameterList([
|
| 57 |
+
nn.Parameter(torch.zeros(1)) for _ in range(max_steps - 1)
|
| 58 |
+
])
|
| 59 |
+
|
| 60 |
+
# ── Runtime storage ─────────────────────────────────────────
|
| 61 |
+
self._ponder_cost = 0.0
|
| 62 |
+
self._steps_used = 0.0
|
| 63 |
+
|
| 64 |
+
def forward(self, hidden_states: torch.Tensor, **kwargs) -> torch.Tensor:
|
| 65 |
+
h0 = hidden_states
|
| 66 |
+
B, S, D = h0.shape
|
| 67 |
+
|
| 68 |
+
total_prob = torch.zeros(B, S, 1, device=h0.device, dtype=h0.dtype)
|
| 69 |
+
accumulated = torch.zeros_like(h0)
|
| 70 |
+
h = h0
|
| 71 |
+
|
| 72 |
+
ponder_cost = torch.tensor(0.0, device=h0.device, dtype=h0.dtype)
|
| 73 |
+
steps_taken = torch.zeros(B, S, 1, device=h0.device, dtype=h0.dtype)
|
| 74 |
+
|
| 75 |
+
for i in range(self.max_steps):
|
| 76 |
+
# ── Halting probability ─────────────────────────────────
|
| 77 |
+
p_halt = torch.sigmoid(self.halt_linear(h))
|
| 78 |
+
remaining = 1.0 - total_prob
|
| 79 |
+
p_use = torch.min(p_halt, remaining)
|
| 80 |
+
|
| 81 |
+
# ── Compute step i ──────────────────────────────────────
|
| 82 |
+
if i == 0:
|
| 83 |
+
# Step 1: EXACT same as original MLP (no modifications)
|
| 84 |
+
h_new = self.steps[0](h)
|
| 85 |
+
else:
|
| 86 |
+
# Steps 2+: MLP output + learned residual gate from h0
|
| 87 |
+
mlp_out = self.steps[i](h)
|
| 88 |
+
gate = torch.sigmoid(self.residual_gates[i - 1])
|
| 89 |
+
h_new = mlp_out + gate * h0 # gate starts at 0.5, learned
|
| 90 |
+
|
| 91 |
+
# ── Weighted accumulation ───────────────────────────────
|
| 92 |
+
accumulated = accumulated + p_use * h_new
|
| 93 |
+
total_prob = total_prob + p_use
|
| 94 |
+
ponder_cost = ponder_cost + p_use.mean()
|
| 95 |
+
steps_taken = steps_taken + (p_use > self.eps).float()
|
| 96 |
+
|
| 97 |
+
# ── Early exit ──────────────────────────────────────────
|
| 98 |
+
if (total_prob >= (1.0 - self.eps)).all():
|
| 99 |
+
break
|
| 100 |
+
|
| 101 |
+
h = h_new
|
| 102 |
+
|
| 103 |
+
# ── Distribute remaining probability ────────────────────────
|
| 104 |
+
remainder = 1.0 - total_prob
|
| 105 |
+
if remainder.max() > self.eps:
|
| 106 |
+
accumulated = accumulated + remainder * h
|
| 107 |
+
|
| 108 |
+
self._ponder_cost = ponder_cost
|
| 109 |
+
self._steps_used = steps_taken.mean().item()
|
| 110 |
+
|
| 111 |
+
return accumulated
|
| 112 |
+
|
| 113 |
+
|
| 114 |
+
def retrofit_model_with_crest(
|
| 115 |
+
model: nn.Module,
|
| 116 |
+
max_steps: int = 4,
|
| 117 |
+
target_layers: Optional[list] = None,
|
| 118 |
+
) -> Tuple[nn.Module, dict]:
|
| 119 |
+
"""
|
| 120 |
+
Retrofit a pretrained transformer with CREST blocks.
|
| 121 |
+
Original MLP weights are preserved as Step 1.
|
| 122 |
+
"""
|
| 123 |
+
layers = None
|
| 124 |
+
if hasattr(model, 'model') and hasattr(model.model, 'layers'):
|
| 125 |
+
layers = model.model.layers
|
| 126 |
+
elif hasattr(model, 'transformer') and hasattr(model.transformer, 'h'):
|
| 127 |
+
layers = model.transformer.h
|
| 128 |
+
else:
|
| 129 |
+
raise ValueError("Cannot find decoder layers")
|
| 130 |
+
|
| 131 |
+
hidden_size = getattr(model.config, 'hidden_size',
|
| 132 |
+
getattr(model.config, 'd_model', None))
|
| 133 |
+
if hidden_size is None:
|
| 134 |
+
for p in layers[0].parameters():
|
| 135 |
+
hidden_size = p.shape[-1]
|
| 136 |
+
break
|
| 137 |
+
|
| 138 |
+
n_layers = len(layers)
|
| 139 |
+
if target_layers is None:
|
| 140 |
+
target_layers = list(range(n_layers))
|
| 141 |
+
|
| 142 |
+
params_before = sum(p.numel() for p in model.parameters())
|
| 143 |
+
converted = 0
|
| 144 |
+
skipped = 0
|
| 145 |
+
|
| 146 |
+
for idx in target_layers:
|
| 147 |
+
layer = layers[idx]
|
| 148 |
+
mlp = None
|
| 149 |
+
mlp_attr = None
|
| 150 |
+
for attr_name in ['mlp', 'feed_forward', 'ffn']:
|
| 151 |
+
if hasattr(layer, attr_name):
|
| 152 |
+
mlp = getattr(layer, attr_name)
|
| 153 |
+
mlp_attr = attr_name
|
| 154 |
+
break
|
| 155 |
+
if mlp is None:
|
| 156 |
+
skipped += 1
|
| 157 |
+
continue
|
| 158 |
+
|
| 159 |
+
crest_block = CRESTBlock(
|
| 160 |
+
original_mlp=mlp,
|
| 161 |
+
hidden_size=hidden_size,
|
| 162 |
+
max_steps=max_steps,
|
| 163 |
+
)
|
| 164 |
+
setattr(layer, mlp_attr, crest_block)
|
| 165 |
+
converted += 1
|
| 166 |
+
|
| 167 |
+
params_after = sum(p.numel() for p in model.parameters())
|
| 168 |
+
|
| 169 |
+
stats = {
|
| 170 |
+
'total_layers': n_layers,
|
| 171 |
+
'converted': converted,
|
| 172 |
+
'skipped': skipped,
|
| 173 |
+
'max_steps': max_steps,
|
| 174 |
+
'hidden_size': hidden_size,
|
| 175 |
+
'params_before': params_before,
|
| 176 |
+
'params_after': params_after,
|
| 177 |
+
'params_added': params_after - params_before,
|
| 178 |
+
'param_overhead_pct': round(100 * (params_after - params_before) / params_before, 1),
|
| 179 |
+
}
|
| 180 |
+
return model, stats
|
| 181 |
+
|
| 182 |
+
|
| 183 |
+
def collect_ponder_costs(model: nn.Module) -> torch.Tensor:
|
| 184 |
+
"""Collect ponder costs from all CREST blocks."""
|
| 185 |
+
total = torch.tensor(0.0, device='cpu')
|
| 186 |
+
count = 0
|
| 187 |
+
for module in model.modules():
|
| 188 |
+
if isinstance(module, CRESTBlock):
|
| 189 |
+
if isinstance(module._ponder_cost, torch.Tensor):
|
| 190 |
+
total = total.to(module._ponder_cost.device)
|
| 191 |
+
total = total + module._ponder_cost
|
| 192 |
+
count += 1
|
| 193 |
+
return total / max(count, 1)
|
| 194 |
+
|
| 195 |
+
|
| 196 |
+
def get_crest_stats(model: nn.Module) -> dict:
|
| 197 |
+
"""Get monitoring stats from all CREST blocks."""
|
| 198 |
+
stats = []
|
| 199 |
+
for name, module in model.named_modules():
|
| 200 |
+
if isinstance(module, CRESTBlock):
|
| 201 |
+
stats.append({
|
| 202 |
+
'name': name,
|
| 203 |
+
'avg_steps': module._steps_used,
|
| 204 |
+
'ponder_cost': module._ponder_cost.item() if isinstance(module._ponder_cost, torch.Tensor) else module._ponder_cost,
|
| 205 |
+
})
|
| 206 |
+
if not stats:
|
| 207 |
+
return {'avg_steps': 0, 'avg_ponder': 0, 'n_blocks': 0}
|
| 208 |
+
return {
|
| 209 |
+
'avg_steps': sum(s['avg_steps'] for s in stats) / len(stats),
|
| 210 |
+
'avg_ponder': sum(s['ponder_cost'] for s in stats) / len(stats),
|
| 211 |
+
'n_blocks': len(stats),
|
| 212 |
+
'per_block': stats,
|
| 213 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 248044,
|
| 4 |
+
"transformers_version": "5.7.0.dev0",
|
| 5 |
+
"use_cache": true
|
| 6 |
+
}
|
model-00001-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a001edd8a6b8d5022553cc65d5f5757c1968c8e09fb6d9349b36b6a02b64fb9f
|
| 3 |
+
size 4974949008
|
model-00002-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:354ed99eaaf813a91efd1272402d0b45aa0eebd305ee1e8f10fb0ff2d85efc14
|
| 3 |
+
size 4993736512
|
model-00003-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2132bfd592e8d4a26ba3bdb0ff710de0ea0eb55987571e19b875ad83e113e39
|
| 3 |
+
size 4993736696
|
model-00004-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8f54cc36026ba23e08aa238d9ad88d1fc37b1f946912d7d1f254ffa5e6b3640
|
| 3 |
+
size 4956625640
|
model-00005-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2d3fc24f8d4917b4397db3d396b48761b6d63e9ca413f043b7cc3d27baab284
|
| 3 |
+
size 2082279264
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,882 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 11000605824,
|
| 4 |
+
"total_size": 22001211648
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
| 8 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 9 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00005.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00005.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00005.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00005.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00005.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00005.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00005.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 18 |
+
"model.language_model.layers.0.mlp.halt_linear.bias": "model-00001-of-00005.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.halt_linear.weight": "model-00001-of-00005.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.residual_gates.0": "model-00001-of-00005.safetensors",
|
| 21 |
+
"model.language_model.layers.0.mlp.residual_gates.1": "model-00001-of-00005.safetensors",
|
| 22 |
+
"model.language_model.layers.0.mlp.residual_gates.2": "model-00001-of-00005.safetensors",
|
| 23 |
+
"model.language_model.layers.0.mlp.steps.0.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 24 |
+
"model.language_model.layers.0.mlp.steps.0.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 25 |
+
"model.language_model.layers.0.mlp.steps.0.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 26 |
+
"model.language_model.layers.0.mlp.steps.1.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 27 |
+
"model.language_model.layers.0.mlp.steps.1.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 28 |
+
"model.language_model.layers.0.mlp.steps.1.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 29 |
+
"model.language_model.layers.0.mlp.steps.2.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 30 |
+
"model.language_model.layers.0.mlp.steps.2.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 31 |
+
"model.language_model.layers.0.mlp.steps.2.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 32 |
+
"model.language_model.layers.0.mlp.steps.3.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 33 |
+
"model.language_model.layers.0.mlp.steps.3.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 34 |
+
"model.language_model.layers.0.mlp.steps.3.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 35 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 36 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 37 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00005.safetensors",
|
| 38 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
|
| 39 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00005.safetensors",
|
| 40 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00005.safetensors",
|
| 41 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00005.safetensors",
|
| 42 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00005.safetensors",
|
| 43 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00005.safetensors",
|
| 44 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00005.safetensors",
|
| 45 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 46 |
+
"model.language_model.layers.1.mlp.halt_linear.bias": "model-00001-of-00005.safetensors",
|
| 47 |
+
"model.language_model.layers.1.mlp.halt_linear.weight": "model-00001-of-00005.safetensors",
|
| 48 |
+
"model.language_model.layers.1.mlp.residual_gates.0": "model-00001-of-00005.safetensors",
|
| 49 |
+
"model.language_model.layers.1.mlp.residual_gates.1": "model-00001-of-00005.safetensors",
|
| 50 |
+
"model.language_model.layers.1.mlp.residual_gates.2": "model-00001-of-00005.safetensors",
|
| 51 |
+
"model.language_model.layers.1.mlp.steps.0.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 52 |
+
"model.language_model.layers.1.mlp.steps.0.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 53 |
+
"model.language_model.layers.1.mlp.steps.0.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 54 |
+
"model.language_model.layers.1.mlp.steps.1.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 55 |
+
"model.language_model.layers.1.mlp.steps.1.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 56 |
+
"model.language_model.layers.1.mlp.steps.1.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 57 |
+
"model.language_model.layers.1.mlp.steps.2.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 58 |
+
"model.language_model.layers.1.mlp.steps.2.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 59 |
+
"model.language_model.layers.1.mlp.steps.2.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 60 |
+
"model.language_model.layers.1.mlp.steps.3.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 61 |
+
"model.language_model.layers.1.mlp.steps.3.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 62 |
+
"model.language_model.layers.1.mlp.steps.3.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 63 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 64 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 65 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00002-of-00005.safetensors",
|
| 66 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
|
| 67 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
|
| 68 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
|
| 69 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
|
| 70 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
|
| 71 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
|
| 72 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
|
| 73 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
|
| 74 |
+
"model.language_model.layers.10.mlp.halt_linear.bias": "model-00002-of-00005.safetensors",
|
| 75 |
+
"model.language_model.layers.10.mlp.halt_linear.weight": "model-00002-of-00005.safetensors",
|
| 76 |
+
"model.language_model.layers.10.mlp.residual_gates.0": "model-00002-of-00005.safetensors",
|
| 77 |
+
"model.language_model.layers.10.mlp.residual_gates.1": "model-00002-of-00005.safetensors",
|
| 78 |
+
"model.language_model.layers.10.mlp.residual_gates.2": "model-00002-of-00005.safetensors",
|
| 79 |
+
"model.language_model.layers.10.mlp.steps.0.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 80 |
+
"model.language_model.layers.10.mlp.steps.0.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 81 |
+
"model.language_model.layers.10.mlp.steps.0.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 82 |
+
"model.language_model.layers.10.mlp.steps.1.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 83 |
+
"model.language_model.layers.10.mlp.steps.1.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 84 |
+
"model.language_model.layers.10.mlp.steps.1.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 85 |
+
"model.language_model.layers.10.mlp.steps.2.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 86 |
+
"model.language_model.layers.10.mlp.steps.2.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 87 |
+
"model.language_model.layers.10.mlp.steps.2.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 88 |
+
"model.language_model.layers.10.mlp.steps.3.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 89 |
+
"model.language_model.layers.10.mlp.steps.3.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 90 |
+
"model.language_model.layers.10.mlp.steps.3.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 91 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 92 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 93 |
+
"model.language_model.layers.11.mlp.halt_linear.bias": "model-00002-of-00005.safetensors",
|
| 94 |
+
"model.language_model.layers.11.mlp.halt_linear.weight": "model-00002-of-00005.safetensors",
|
| 95 |
+
"model.language_model.layers.11.mlp.residual_gates.0": "model-00002-of-00005.safetensors",
|
| 96 |
+
"model.language_model.layers.11.mlp.residual_gates.1": "model-00002-of-00005.safetensors",
|
| 97 |
+
"model.language_model.layers.11.mlp.residual_gates.2": "model-00002-of-00005.safetensors",
|
| 98 |
+
"model.language_model.layers.11.mlp.steps.0.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 99 |
+
"model.language_model.layers.11.mlp.steps.0.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 100 |
+
"model.language_model.layers.11.mlp.steps.0.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 101 |
+
"model.language_model.layers.11.mlp.steps.1.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 102 |
+
"model.language_model.layers.11.mlp.steps.1.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 103 |
+
"model.language_model.layers.11.mlp.steps.1.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 104 |
+
"model.language_model.layers.11.mlp.steps.2.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 105 |
+
"model.language_model.layers.11.mlp.steps.2.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 106 |
+
"model.language_model.layers.11.mlp.steps.2.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 107 |
+
"model.language_model.layers.11.mlp.steps.3.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 108 |
+
"model.language_model.layers.11.mlp.steps.3.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 109 |
+
"model.language_model.layers.11.mlp.steps.3.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 110 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 111 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 112 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 113 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 114 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
|
| 115 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 116 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 117 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 118 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00005.safetensors",
|
| 119 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
|
| 120 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
|
| 121 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
|
| 122 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
|
| 123 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
|
| 124 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
|
| 125 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
|
| 126 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
|
| 127 |
+
"model.language_model.layers.12.mlp.halt_linear.bias": "model-00002-of-00005.safetensors",
|
| 128 |
+
"model.language_model.layers.12.mlp.halt_linear.weight": "model-00002-of-00005.safetensors",
|
| 129 |
+
"model.language_model.layers.12.mlp.residual_gates.0": "model-00002-of-00005.safetensors",
|
| 130 |
+
"model.language_model.layers.12.mlp.residual_gates.1": "model-00002-of-00005.safetensors",
|
| 131 |
+
"model.language_model.layers.12.mlp.residual_gates.2": "model-00002-of-00005.safetensors",
|
| 132 |
+
"model.language_model.layers.12.mlp.steps.0.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 133 |
+
"model.language_model.layers.12.mlp.steps.0.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 134 |
+
"model.language_model.layers.12.mlp.steps.0.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 135 |
+
"model.language_model.layers.12.mlp.steps.1.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 136 |
+
"model.language_model.layers.12.mlp.steps.1.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 137 |
+
"model.language_model.layers.12.mlp.steps.1.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 138 |
+
"model.language_model.layers.12.mlp.steps.2.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 139 |
+
"model.language_model.layers.12.mlp.steps.2.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 140 |
+
"model.language_model.layers.12.mlp.steps.2.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 141 |
+
"model.language_model.layers.12.mlp.steps.3.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 142 |
+
"model.language_model.layers.12.mlp.steps.3.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 143 |
+
"model.language_model.layers.12.mlp.steps.3.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 144 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 145 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 146 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00005.safetensors",
|
| 147 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
|
| 148 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
|
| 149 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
|
| 150 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
|
| 151 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
|
| 152 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
|
| 153 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
|
| 154 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
|
| 155 |
+
"model.language_model.layers.13.mlp.halt_linear.bias": "model-00002-of-00005.safetensors",
|
| 156 |
+
"model.language_model.layers.13.mlp.halt_linear.weight": "model-00002-of-00005.safetensors",
|
| 157 |
+
"model.language_model.layers.13.mlp.residual_gates.0": "model-00002-of-00005.safetensors",
|
| 158 |
+
"model.language_model.layers.13.mlp.residual_gates.1": "model-00002-of-00005.safetensors",
|
| 159 |
+
"model.language_model.layers.13.mlp.residual_gates.2": "model-00002-of-00005.safetensors",
|
| 160 |
+
"model.language_model.layers.13.mlp.steps.0.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 161 |
+
"model.language_model.layers.13.mlp.steps.0.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 162 |
+
"model.language_model.layers.13.mlp.steps.0.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 163 |
+
"model.language_model.layers.13.mlp.steps.1.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 164 |
+
"model.language_model.layers.13.mlp.steps.1.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 165 |
+
"model.language_model.layers.13.mlp.steps.1.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 166 |
+
"model.language_model.layers.13.mlp.steps.2.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 167 |
+
"model.language_model.layers.13.mlp.steps.2.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 168 |
+
"model.language_model.layers.13.mlp.steps.2.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 169 |
+
"model.language_model.layers.13.mlp.steps.3.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 170 |
+
"model.language_model.layers.13.mlp.steps.3.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 171 |
+
"model.language_model.layers.13.mlp.steps.3.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 172 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 173 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 174 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00003-of-00005.safetensors",
|
| 175 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
|
| 176 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
|
| 177 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
|
| 178 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
|
| 179 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
|
| 180 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
|
| 181 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
|
| 182 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
|
| 183 |
+
"model.language_model.layers.14.mlp.halt_linear.bias": "model-00003-of-00005.safetensors",
|
| 184 |
+
"model.language_model.layers.14.mlp.halt_linear.weight": "model-00003-of-00005.safetensors",
|
| 185 |
+
"model.language_model.layers.14.mlp.residual_gates.0": "model-00003-of-00005.safetensors",
|
| 186 |
+
"model.language_model.layers.14.mlp.residual_gates.1": "model-00003-of-00005.safetensors",
|
| 187 |
+
"model.language_model.layers.14.mlp.residual_gates.2": "model-00003-of-00005.safetensors",
|
| 188 |
+
"model.language_model.layers.14.mlp.steps.0.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 189 |
+
"model.language_model.layers.14.mlp.steps.0.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 190 |
+
"model.language_model.layers.14.mlp.steps.0.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 191 |
+
"model.language_model.layers.14.mlp.steps.1.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 192 |
+
"model.language_model.layers.14.mlp.steps.1.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 193 |
+
"model.language_model.layers.14.mlp.steps.1.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 194 |
+
"model.language_model.layers.14.mlp.steps.2.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 195 |
+
"model.language_model.layers.14.mlp.steps.2.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 196 |
+
"model.language_model.layers.14.mlp.steps.2.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 197 |
+
"model.language_model.layers.14.mlp.steps.3.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 198 |
+
"model.language_model.layers.14.mlp.steps.3.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 199 |
+
"model.language_model.layers.14.mlp.steps.3.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 200 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 201 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 202 |
+
"model.language_model.layers.15.mlp.halt_linear.bias": "model-00003-of-00005.safetensors",
|
| 203 |
+
"model.language_model.layers.15.mlp.halt_linear.weight": "model-00003-of-00005.safetensors",
|
| 204 |
+
"model.language_model.layers.15.mlp.residual_gates.0": "model-00003-of-00005.safetensors",
|
| 205 |
+
"model.language_model.layers.15.mlp.residual_gates.1": "model-00003-of-00005.safetensors",
|
| 206 |
+
"model.language_model.layers.15.mlp.residual_gates.2": "model-00003-of-00005.safetensors",
|
| 207 |
+
"model.language_model.layers.15.mlp.steps.0.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 208 |
+
"model.language_model.layers.15.mlp.steps.0.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 209 |
+
"model.language_model.layers.15.mlp.steps.0.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 210 |
+
"model.language_model.layers.15.mlp.steps.1.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 211 |
+
"model.language_model.layers.15.mlp.steps.1.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 212 |
+
"model.language_model.layers.15.mlp.steps.1.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 213 |
+
"model.language_model.layers.15.mlp.steps.2.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 214 |
+
"model.language_model.layers.15.mlp.steps.2.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 215 |
+
"model.language_model.layers.15.mlp.steps.2.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 216 |
+
"model.language_model.layers.15.mlp.steps.3.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 217 |
+
"model.language_model.layers.15.mlp.steps.3.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 218 |
+
"model.language_model.layers.15.mlp.steps.3.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 219 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 220 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 221 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 222 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 223 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
|
| 224 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 225 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 226 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 227 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00003-of-00005.safetensors",
|
| 228 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
|
| 229 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
|
| 230 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
|
| 231 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
|
| 232 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
|
| 233 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
|
| 234 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
|
| 235 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
|
| 236 |
+
"model.language_model.layers.16.mlp.halt_linear.bias": "model-00003-of-00005.safetensors",
|
| 237 |
+
"model.language_model.layers.16.mlp.halt_linear.weight": "model-00003-of-00005.safetensors",
|
| 238 |
+
"model.language_model.layers.16.mlp.residual_gates.0": "model-00003-of-00005.safetensors",
|
| 239 |
+
"model.language_model.layers.16.mlp.residual_gates.1": "model-00003-of-00005.safetensors",
|
| 240 |
+
"model.language_model.layers.16.mlp.residual_gates.2": "model-00003-of-00005.safetensors",
|
| 241 |
+
"model.language_model.layers.16.mlp.steps.0.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 242 |
+
"model.language_model.layers.16.mlp.steps.0.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 243 |
+
"model.language_model.layers.16.mlp.steps.0.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 244 |
+
"model.language_model.layers.16.mlp.steps.1.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 245 |
+
"model.language_model.layers.16.mlp.steps.1.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 246 |
+
"model.language_model.layers.16.mlp.steps.1.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 247 |
+
"model.language_model.layers.16.mlp.steps.2.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 248 |
+
"model.language_model.layers.16.mlp.steps.2.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 249 |
+
"model.language_model.layers.16.mlp.steps.2.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 250 |
+
"model.language_model.layers.16.mlp.steps.3.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 251 |
+
"model.language_model.layers.16.mlp.steps.3.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 252 |
+
"model.language_model.layers.16.mlp.steps.3.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 253 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 254 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 255 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00003-of-00005.safetensors",
|
| 256 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
|
| 257 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
|
| 258 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
|
| 259 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
|
| 260 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
|
| 261 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
|
| 262 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
|
| 263 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
|
| 264 |
+
"model.language_model.layers.17.mlp.halt_linear.bias": "model-00003-of-00005.safetensors",
|
| 265 |
+
"model.language_model.layers.17.mlp.halt_linear.weight": "model-00003-of-00005.safetensors",
|
| 266 |
+
"model.language_model.layers.17.mlp.residual_gates.0": "model-00003-of-00005.safetensors",
|
| 267 |
+
"model.language_model.layers.17.mlp.residual_gates.1": "model-00003-of-00005.safetensors",
|
| 268 |
+
"model.language_model.layers.17.mlp.residual_gates.2": "model-00003-of-00005.safetensors",
|
| 269 |
+
"model.language_model.layers.17.mlp.steps.0.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 270 |
+
"model.language_model.layers.17.mlp.steps.0.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 271 |
+
"model.language_model.layers.17.mlp.steps.0.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 272 |
+
"model.language_model.layers.17.mlp.steps.1.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 273 |
+
"model.language_model.layers.17.mlp.steps.1.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 274 |
+
"model.language_model.layers.17.mlp.steps.1.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 275 |
+
"model.language_model.layers.17.mlp.steps.2.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 276 |
+
"model.language_model.layers.17.mlp.steps.2.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 277 |
+
"model.language_model.layers.17.mlp.steps.2.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 278 |
+
"model.language_model.layers.17.mlp.steps.3.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 279 |
+
"model.language_model.layers.17.mlp.steps.3.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 280 |
+
"model.language_model.layers.17.mlp.steps.3.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 281 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 282 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 283 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00003-of-00005.safetensors",
|
| 284 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
|
| 285 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
|
| 286 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
|
| 287 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
|
| 288 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
|
| 289 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
|
| 290 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
|
| 291 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
|
| 292 |
+
"model.language_model.layers.18.mlp.halt_linear.bias": "model-00003-of-00005.safetensors",
|
| 293 |
+
"model.language_model.layers.18.mlp.halt_linear.weight": "model-00003-of-00005.safetensors",
|
| 294 |
+
"model.language_model.layers.18.mlp.residual_gates.0": "model-00003-of-00005.safetensors",
|
| 295 |
+
"model.language_model.layers.18.mlp.residual_gates.1": "model-00003-of-00005.safetensors",
|
| 296 |
+
"model.language_model.layers.18.mlp.residual_gates.2": "model-00003-of-00005.safetensors",
|
| 297 |
+
"model.language_model.layers.18.mlp.steps.0.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 298 |
+
"model.language_model.layers.18.mlp.steps.0.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 299 |
+
"model.language_model.layers.18.mlp.steps.0.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 300 |
+
"model.language_model.layers.18.mlp.steps.1.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 301 |
+
"model.language_model.layers.18.mlp.steps.1.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 302 |
+
"model.language_model.layers.18.mlp.steps.1.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 303 |
+
"model.language_model.layers.18.mlp.steps.2.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 304 |
+
"model.language_model.layers.18.mlp.steps.2.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 305 |
+
"model.language_model.layers.18.mlp.steps.2.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 306 |
+
"model.language_model.layers.18.mlp.steps.3.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 307 |
+
"model.language_model.layers.18.mlp.steps.3.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 308 |
+
"model.language_model.layers.18.mlp.steps.3.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 309 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 310 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 311 |
+
"model.language_model.layers.19.mlp.halt_linear.bias": "model-00003-of-00005.safetensors",
|
| 312 |
+
"model.language_model.layers.19.mlp.halt_linear.weight": "model-00003-of-00005.safetensors",
|
| 313 |
+
"model.language_model.layers.19.mlp.residual_gates.0": "model-00003-of-00005.safetensors",
|
| 314 |
+
"model.language_model.layers.19.mlp.residual_gates.1": "model-00003-of-00005.safetensors",
|
| 315 |
+
"model.language_model.layers.19.mlp.residual_gates.2": "model-00003-of-00005.safetensors",
|
| 316 |
+
"model.language_model.layers.19.mlp.steps.0.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 317 |
+
"model.language_model.layers.19.mlp.steps.0.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 318 |
+
"model.language_model.layers.19.mlp.steps.0.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 319 |
+
"model.language_model.layers.19.mlp.steps.1.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 320 |
+
"model.language_model.layers.19.mlp.steps.1.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 321 |
+
"model.language_model.layers.19.mlp.steps.1.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 322 |
+
"model.language_model.layers.19.mlp.steps.2.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 323 |
+
"model.language_model.layers.19.mlp.steps.2.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 324 |
+
"model.language_model.layers.19.mlp.steps.2.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 325 |
+
"model.language_model.layers.19.mlp.steps.3.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 326 |
+
"model.language_model.layers.19.mlp.steps.3.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 327 |
+
"model.language_model.layers.19.mlp.steps.3.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 328 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 329 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 330 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 331 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 332 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
|
| 333 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 334 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 335 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 336 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00005.safetensors",
|
| 337 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
|
| 338 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00005.safetensors",
|
| 339 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00005.safetensors",
|
| 340 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00005.safetensors",
|
| 341 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00005.safetensors",
|
| 342 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00005.safetensors",
|
| 343 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00005.safetensors",
|
| 344 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 345 |
+
"model.language_model.layers.2.mlp.halt_linear.bias": "model-00001-of-00005.safetensors",
|
| 346 |
+
"model.language_model.layers.2.mlp.halt_linear.weight": "model-00001-of-00005.safetensors",
|
| 347 |
+
"model.language_model.layers.2.mlp.residual_gates.0": "model-00001-of-00005.safetensors",
|
| 348 |
+
"model.language_model.layers.2.mlp.residual_gates.1": "model-00001-of-00005.safetensors",
|
| 349 |
+
"model.language_model.layers.2.mlp.residual_gates.2": "model-00001-of-00005.safetensors",
|
| 350 |
+
"model.language_model.layers.2.mlp.steps.0.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 351 |
+
"model.language_model.layers.2.mlp.steps.0.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 352 |
+
"model.language_model.layers.2.mlp.steps.0.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 353 |
+
"model.language_model.layers.2.mlp.steps.1.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 354 |
+
"model.language_model.layers.2.mlp.steps.1.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 355 |
+
"model.language_model.layers.2.mlp.steps.1.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 356 |
+
"model.language_model.layers.2.mlp.steps.2.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 357 |
+
"model.language_model.layers.2.mlp.steps.2.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 358 |
+
"model.language_model.layers.2.mlp.steps.2.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 359 |
+
"model.language_model.layers.2.mlp.steps.3.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 360 |
+
"model.language_model.layers.2.mlp.steps.3.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 361 |
+
"model.language_model.layers.2.mlp.steps.3.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 362 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 363 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 364 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00003-of-00005.safetensors",
|
| 365 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
|
| 366 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
|
| 367 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
|
| 368 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
|
| 369 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
|
| 370 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
|
| 371 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
|
| 372 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
|
| 373 |
+
"model.language_model.layers.20.mlp.halt_linear.bias": "model-00003-of-00005.safetensors",
|
| 374 |
+
"model.language_model.layers.20.mlp.halt_linear.weight": "model-00003-of-00005.safetensors",
|
| 375 |
+
"model.language_model.layers.20.mlp.residual_gates.0": "model-00003-of-00005.safetensors",
|
| 376 |
+
"model.language_model.layers.20.mlp.residual_gates.1": "model-00003-of-00005.safetensors",
|
| 377 |
+
"model.language_model.layers.20.mlp.residual_gates.2": "model-00003-of-00005.safetensors",
|
| 378 |
+
"model.language_model.layers.20.mlp.steps.0.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 379 |
+
"model.language_model.layers.20.mlp.steps.0.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 380 |
+
"model.language_model.layers.20.mlp.steps.0.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 381 |
+
"model.language_model.layers.20.mlp.steps.1.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 382 |
+
"model.language_model.layers.20.mlp.steps.1.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 383 |
+
"model.language_model.layers.20.mlp.steps.1.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 384 |
+
"model.language_model.layers.20.mlp.steps.2.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 385 |
+
"model.language_model.layers.20.mlp.steps.2.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 386 |
+
"model.language_model.layers.20.mlp.steps.2.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 387 |
+
"model.language_model.layers.20.mlp.steps.3.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 388 |
+
"model.language_model.layers.20.mlp.steps.3.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 389 |
+
"model.language_model.layers.20.mlp.steps.3.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 390 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 391 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 392 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00003-of-00005.safetensors",
|
| 393 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
|
| 394 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
|
| 395 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
|
| 396 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
|
| 397 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
|
| 398 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
|
| 399 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
|
| 400 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
|
| 401 |
+
"model.language_model.layers.21.mlp.halt_linear.bias": "model-00003-of-00005.safetensors",
|
| 402 |
+
"model.language_model.layers.21.mlp.halt_linear.weight": "model-00003-of-00005.safetensors",
|
| 403 |
+
"model.language_model.layers.21.mlp.residual_gates.0": "model-00003-of-00005.safetensors",
|
| 404 |
+
"model.language_model.layers.21.mlp.residual_gates.1": "model-00003-of-00005.safetensors",
|
| 405 |
+
"model.language_model.layers.21.mlp.residual_gates.2": "model-00003-of-00005.safetensors",
|
| 406 |
+
"model.language_model.layers.21.mlp.steps.0.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 407 |
+
"model.language_model.layers.21.mlp.steps.0.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 408 |
+
"model.language_model.layers.21.mlp.steps.0.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 409 |
+
"model.language_model.layers.21.mlp.steps.1.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 410 |
+
"model.language_model.layers.21.mlp.steps.1.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 411 |
+
"model.language_model.layers.21.mlp.steps.1.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 412 |
+
"model.language_model.layers.21.mlp.steps.2.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 413 |
+
"model.language_model.layers.21.mlp.steps.2.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 414 |
+
"model.language_model.layers.21.mlp.steps.2.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 415 |
+
"model.language_model.layers.21.mlp.steps.3.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 416 |
+
"model.language_model.layers.21.mlp.steps.3.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 417 |
+
"model.language_model.layers.21.mlp.steps.3.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 418 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 419 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 420 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00004-of-00005.safetensors",
|
| 421 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
|
| 422 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
|
| 423 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
|
| 424 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
|
| 425 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
|
| 426 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
|
| 427 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
|
| 428 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
|
| 429 |
+
"model.language_model.layers.22.mlp.halt_linear.bias": "model-00004-of-00005.safetensors",
|
| 430 |
+
"model.language_model.layers.22.mlp.halt_linear.weight": "model-00004-of-00005.safetensors",
|
| 431 |
+
"model.language_model.layers.22.mlp.residual_gates.0": "model-00004-of-00005.safetensors",
|
| 432 |
+
"model.language_model.layers.22.mlp.residual_gates.1": "model-00004-of-00005.safetensors",
|
| 433 |
+
"model.language_model.layers.22.mlp.residual_gates.2": "model-00004-of-00005.safetensors",
|
| 434 |
+
"model.language_model.layers.22.mlp.steps.0.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 435 |
+
"model.language_model.layers.22.mlp.steps.0.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 436 |
+
"model.language_model.layers.22.mlp.steps.0.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 437 |
+
"model.language_model.layers.22.mlp.steps.1.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 438 |
+
"model.language_model.layers.22.mlp.steps.1.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 439 |
+
"model.language_model.layers.22.mlp.steps.1.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 440 |
+
"model.language_model.layers.22.mlp.steps.2.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 441 |
+
"model.language_model.layers.22.mlp.steps.2.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 442 |
+
"model.language_model.layers.22.mlp.steps.2.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 443 |
+
"model.language_model.layers.22.mlp.steps.3.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 444 |
+
"model.language_model.layers.22.mlp.steps.3.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 445 |
+
"model.language_model.layers.22.mlp.steps.3.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 446 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 447 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 448 |
+
"model.language_model.layers.23.mlp.halt_linear.bias": "model-00004-of-00005.safetensors",
|
| 449 |
+
"model.language_model.layers.23.mlp.halt_linear.weight": "model-00004-of-00005.safetensors",
|
| 450 |
+
"model.language_model.layers.23.mlp.residual_gates.0": "model-00004-of-00005.safetensors",
|
| 451 |
+
"model.language_model.layers.23.mlp.residual_gates.1": "model-00004-of-00005.safetensors",
|
| 452 |
+
"model.language_model.layers.23.mlp.residual_gates.2": "model-00004-of-00005.safetensors",
|
| 453 |
+
"model.language_model.layers.23.mlp.steps.0.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 454 |
+
"model.language_model.layers.23.mlp.steps.0.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 455 |
+
"model.language_model.layers.23.mlp.steps.0.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 456 |
+
"model.language_model.layers.23.mlp.steps.1.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 457 |
+
"model.language_model.layers.23.mlp.steps.1.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 458 |
+
"model.language_model.layers.23.mlp.steps.1.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 459 |
+
"model.language_model.layers.23.mlp.steps.2.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 460 |
+
"model.language_model.layers.23.mlp.steps.2.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 461 |
+
"model.language_model.layers.23.mlp.steps.2.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 462 |
+
"model.language_model.layers.23.mlp.steps.3.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 463 |
+
"model.language_model.layers.23.mlp.steps.3.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 464 |
+
"model.language_model.layers.23.mlp.steps.3.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 465 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 466 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 467 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 468 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 469 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
|
| 470 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 471 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 472 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 473 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00004-of-00005.safetensors",
|
| 474 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
|
| 475 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
|
| 476 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
|
| 477 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
|
| 478 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
|
| 479 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
|
| 480 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
|
| 481 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
|
| 482 |
+
"model.language_model.layers.24.mlp.halt_linear.bias": "model-00004-of-00005.safetensors",
|
| 483 |
+
"model.language_model.layers.24.mlp.halt_linear.weight": "model-00004-of-00005.safetensors",
|
| 484 |
+
"model.language_model.layers.24.mlp.residual_gates.0": "model-00004-of-00005.safetensors",
|
| 485 |
+
"model.language_model.layers.24.mlp.residual_gates.1": "model-00004-of-00005.safetensors",
|
| 486 |
+
"model.language_model.layers.24.mlp.residual_gates.2": "model-00004-of-00005.safetensors",
|
| 487 |
+
"model.language_model.layers.24.mlp.steps.0.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 488 |
+
"model.language_model.layers.24.mlp.steps.0.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 489 |
+
"model.language_model.layers.24.mlp.steps.0.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 490 |
+
"model.language_model.layers.24.mlp.steps.1.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 491 |
+
"model.language_model.layers.24.mlp.steps.1.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 492 |
+
"model.language_model.layers.24.mlp.steps.1.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 493 |
+
"model.language_model.layers.24.mlp.steps.2.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 494 |
+
"model.language_model.layers.24.mlp.steps.2.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 495 |
+
"model.language_model.layers.24.mlp.steps.2.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 496 |
+
"model.language_model.layers.24.mlp.steps.3.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 497 |
+
"model.language_model.layers.24.mlp.steps.3.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 498 |
+
"model.language_model.layers.24.mlp.steps.3.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 499 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 500 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 501 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00004-of-00005.safetensors",
|
| 502 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
|
| 503 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
|
| 504 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
|
| 505 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
|
| 506 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
|
| 507 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
|
| 508 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
|
| 509 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
|
| 510 |
+
"model.language_model.layers.25.mlp.halt_linear.bias": "model-00004-of-00005.safetensors",
|
| 511 |
+
"model.language_model.layers.25.mlp.halt_linear.weight": "model-00004-of-00005.safetensors",
|
| 512 |
+
"model.language_model.layers.25.mlp.residual_gates.0": "model-00004-of-00005.safetensors",
|
| 513 |
+
"model.language_model.layers.25.mlp.residual_gates.1": "model-00004-of-00005.safetensors",
|
| 514 |
+
"model.language_model.layers.25.mlp.residual_gates.2": "model-00004-of-00005.safetensors",
|
| 515 |
+
"model.language_model.layers.25.mlp.steps.0.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 516 |
+
"model.language_model.layers.25.mlp.steps.0.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 517 |
+
"model.language_model.layers.25.mlp.steps.0.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 518 |
+
"model.language_model.layers.25.mlp.steps.1.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 519 |
+
"model.language_model.layers.25.mlp.steps.1.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 520 |
+
"model.language_model.layers.25.mlp.steps.1.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 521 |
+
"model.language_model.layers.25.mlp.steps.2.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 522 |
+
"model.language_model.layers.25.mlp.steps.2.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 523 |
+
"model.language_model.layers.25.mlp.steps.2.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 524 |
+
"model.language_model.layers.25.mlp.steps.3.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 525 |
+
"model.language_model.layers.25.mlp.steps.3.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 526 |
+
"model.language_model.layers.25.mlp.steps.3.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 527 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 528 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 529 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00004-of-00005.safetensors",
|
| 530 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
|
| 531 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
|
| 532 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
|
| 533 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
|
| 534 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
|
| 535 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
|
| 536 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
|
| 537 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
|
| 538 |
+
"model.language_model.layers.26.mlp.halt_linear.bias": "model-00004-of-00005.safetensors",
|
| 539 |
+
"model.language_model.layers.26.mlp.halt_linear.weight": "model-00004-of-00005.safetensors",
|
| 540 |
+
"model.language_model.layers.26.mlp.residual_gates.0": "model-00004-of-00005.safetensors",
|
| 541 |
+
"model.language_model.layers.26.mlp.residual_gates.1": "model-00004-of-00005.safetensors",
|
| 542 |
+
"model.language_model.layers.26.mlp.residual_gates.2": "model-00004-of-00005.safetensors",
|
| 543 |
+
"model.language_model.layers.26.mlp.steps.0.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 544 |
+
"model.language_model.layers.26.mlp.steps.0.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 545 |
+
"model.language_model.layers.26.mlp.steps.0.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 546 |
+
"model.language_model.layers.26.mlp.steps.1.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 547 |
+
"model.language_model.layers.26.mlp.steps.1.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 548 |
+
"model.language_model.layers.26.mlp.steps.1.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 549 |
+
"model.language_model.layers.26.mlp.steps.2.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 550 |
+
"model.language_model.layers.26.mlp.steps.2.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 551 |
+
"model.language_model.layers.26.mlp.steps.2.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 552 |
+
"model.language_model.layers.26.mlp.steps.3.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 553 |
+
"model.language_model.layers.26.mlp.steps.3.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 554 |
+
"model.language_model.layers.26.mlp.steps.3.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 555 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 556 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 557 |
+
"model.language_model.layers.27.mlp.halt_linear.bias": "model-00004-of-00005.safetensors",
|
| 558 |
+
"model.language_model.layers.27.mlp.halt_linear.weight": "model-00004-of-00005.safetensors",
|
| 559 |
+
"model.language_model.layers.27.mlp.residual_gates.0": "model-00004-of-00005.safetensors",
|
| 560 |
+
"model.language_model.layers.27.mlp.residual_gates.1": "model-00004-of-00005.safetensors",
|
| 561 |
+
"model.language_model.layers.27.mlp.residual_gates.2": "model-00004-of-00005.safetensors",
|
| 562 |
+
"model.language_model.layers.27.mlp.steps.0.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 563 |
+
"model.language_model.layers.27.mlp.steps.0.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 564 |
+
"model.language_model.layers.27.mlp.steps.0.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 565 |
+
"model.language_model.layers.27.mlp.steps.1.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 566 |
+
"model.language_model.layers.27.mlp.steps.1.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 567 |
+
"model.language_model.layers.27.mlp.steps.1.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 568 |
+
"model.language_model.layers.27.mlp.steps.2.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 569 |
+
"model.language_model.layers.27.mlp.steps.2.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 570 |
+
"model.language_model.layers.27.mlp.steps.2.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 571 |
+
"model.language_model.layers.27.mlp.steps.3.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 572 |
+
"model.language_model.layers.27.mlp.steps.3.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 573 |
+
"model.language_model.layers.27.mlp.steps.3.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 574 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 575 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 576 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 577 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 578 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
|
| 579 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 580 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 581 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 582 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00004-of-00005.safetensors",
|
| 583 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
|
| 584 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
|
| 585 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
|
| 586 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
|
| 587 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
|
| 588 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
|
| 589 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
|
| 590 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
|
| 591 |
+
"model.language_model.layers.28.mlp.halt_linear.bias": "model-00004-of-00005.safetensors",
|
| 592 |
+
"model.language_model.layers.28.mlp.halt_linear.weight": "model-00004-of-00005.safetensors",
|
| 593 |
+
"model.language_model.layers.28.mlp.residual_gates.0": "model-00004-of-00005.safetensors",
|
| 594 |
+
"model.language_model.layers.28.mlp.residual_gates.1": "model-00004-of-00005.safetensors",
|
| 595 |
+
"model.language_model.layers.28.mlp.residual_gates.2": "model-00004-of-00005.safetensors",
|
| 596 |
+
"model.language_model.layers.28.mlp.steps.0.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 597 |
+
"model.language_model.layers.28.mlp.steps.0.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 598 |
+
"model.language_model.layers.28.mlp.steps.0.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 599 |
+
"model.language_model.layers.28.mlp.steps.1.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 600 |
+
"model.language_model.layers.28.mlp.steps.1.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 601 |
+
"model.language_model.layers.28.mlp.steps.1.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 602 |
+
"model.language_model.layers.28.mlp.steps.2.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 603 |
+
"model.language_model.layers.28.mlp.steps.2.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 604 |
+
"model.language_model.layers.28.mlp.steps.2.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 605 |
+
"model.language_model.layers.28.mlp.steps.3.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 606 |
+
"model.language_model.layers.28.mlp.steps.3.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 607 |
+
"model.language_model.layers.28.mlp.steps.3.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 608 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 609 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 610 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00005-of-00005.safetensors",
|
| 611 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
|
| 612 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
|
| 613 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
|
| 614 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
|
| 615 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
|
| 616 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
|
| 617 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
|
| 618 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
|
| 619 |
+
"model.language_model.layers.29.mlp.halt_linear.bias": "model-00005-of-00005.safetensors",
|
| 620 |
+
"model.language_model.layers.29.mlp.halt_linear.weight": "model-00005-of-00005.safetensors",
|
| 621 |
+
"model.language_model.layers.29.mlp.residual_gates.0": "model-00005-of-00005.safetensors",
|
| 622 |
+
"model.language_model.layers.29.mlp.residual_gates.1": "model-00005-of-00005.safetensors",
|
| 623 |
+
"model.language_model.layers.29.mlp.residual_gates.2": "model-00005-of-00005.safetensors",
|
| 624 |
+
"model.language_model.layers.29.mlp.steps.0.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 625 |
+
"model.language_model.layers.29.mlp.steps.0.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 626 |
+
"model.language_model.layers.29.mlp.steps.0.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 627 |
+
"model.language_model.layers.29.mlp.steps.1.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 628 |
+
"model.language_model.layers.29.mlp.steps.1.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 629 |
+
"model.language_model.layers.29.mlp.steps.1.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 630 |
+
"model.language_model.layers.29.mlp.steps.2.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 631 |
+
"model.language_model.layers.29.mlp.steps.2.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 632 |
+
"model.language_model.layers.29.mlp.steps.2.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 633 |
+
"model.language_model.layers.29.mlp.steps.3.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 634 |
+
"model.language_model.layers.29.mlp.steps.3.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 635 |
+
"model.language_model.layers.29.mlp.steps.3.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 636 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 637 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 638 |
+
"model.language_model.layers.3.mlp.halt_linear.bias": "model-00001-of-00005.safetensors",
|
| 639 |
+
"model.language_model.layers.3.mlp.halt_linear.weight": "model-00001-of-00005.safetensors",
|
| 640 |
+
"model.language_model.layers.3.mlp.residual_gates.0": "model-00001-of-00005.safetensors",
|
| 641 |
+
"model.language_model.layers.3.mlp.residual_gates.1": "model-00001-of-00005.safetensors",
|
| 642 |
+
"model.language_model.layers.3.mlp.residual_gates.2": "model-00001-of-00005.safetensors",
|
| 643 |
+
"model.language_model.layers.3.mlp.steps.0.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 644 |
+
"model.language_model.layers.3.mlp.steps.0.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 645 |
+
"model.language_model.layers.3.mlp.steps.0.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 646 |
+
"model.language_model.layers.3.mlp.steps.1.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 647 |
+
"model.language_model.layers.3.mlp.steps.1.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 648 |
+
"model.language_model.layers.3.mlp.steps.1.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 649 |
+
"model.language_model.layers.3.mlp.steps.2.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 650 |
+
"model.language_model.layers.3.mlp.steps.2.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 651 |
+
"model.language_model.layers.3.mlp.steps.2.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 652 |
+
"model.language_model.layers.3.mlp.steps.3.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 653 |
+
"model.language_model.layers.3.mlp.steps.3.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 654 |
+
"model.language_model.layers.3.mlp.steps.3.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 655 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 656 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 657 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 658 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 659 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
|
| 660 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 661 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 662 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 663 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00005-of-00005.safetensors",
|
| 664 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
|
| 665 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
|
| 666 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
|
| 667 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
|
| 668 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
|
| 669 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
|
| 670 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
|
| 671 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
|
| 672 |
+
"model.language_model.layers.30.mlp.halt_linear.bias": "model-00005-of-00005.safetensors",
|
| 673 |
+
"model.language_model.layers.30.mlp.halt_linear.weight": "model-00005-of-00005.safetensors",
|
| 674 |
+
"model.language_model.layers.30.mlp.residual_gates.0": "model-00005-of-00005.safetensors",
|
| 675 |
+
"model.language_model.layers.30.mlp.residual_gates.1": "model-00005-of-00005.safetensors",
|
| 676 |
+
"model.language_model.layers.30.mlp.residual_gates.2": "model-00005-of-00005.safetensors",
|
| 677 |
+
"model.language_model.layers.30.mlp.steps.0.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 678 |
+
"model.language_model.layers.30.mlp.steps.0.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 679 |
+
"model.language_model.layers.30.mlp.steps.0.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 680 |
+
"model.language_model.layers.30.mlp.steps.1.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 681 |
+
"model.language_model.layers.30.mlp.steps.1.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 682 |
+
"model.language_model.layers.30.mlp.steps.1.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 683 |
+
"model.language_model.layers.30.mlp.steps.2.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 684 |
+
"model.language_model.layers.30.mlp.steps.2.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 685 |
+
"model.language_model.layers.30.mlp.steps.2.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 686 |
+
"model.language_model.layers.30.mlp.steps.3.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 687 |
+
"model.language_model.layers.30.mlp.steps.3.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 688 |
+
"model.language_model.layers.30.mlp.steps.3.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 689 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 690 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 691 |
+
"model.language_model.layers.31.mlp.halt_linear.bias": "model-00005-of-00005.safetensors",
|
| 692 |
+
"model.language_model.layers.31.mlp.halt_linear.weight": "model-00005-of-00005.safetensors",
|
| 693 |
+
"model.language_model.layers.31.mlp.residual_gates.0": "model-00005-of-00005.safetensors",
|
| 694 |
+
"model.language_model.layers.31.mlp.residual_gates.1": "model-00005-of-00005.safetensors",
|
| 695 |
+
"model.language_model.layers.31.mlp.residual_gates.2": "model-00005-of-00005.safetensors",
|
| 696 |
+
"model.language_model.layers.31.mlp.steps.0.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 697 |
+
"model.language_model.layers.31.mlp.steps.0.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 698 |
+
"model.language_model.layers.31.mlp.steps.0.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 699 |
+
"model.language_model.layers.31.mlp.steps.1.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 700 |
+
"model.language_model.layers.31.mlp.steps.1.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 701 |
+
"model.language_model.layers.31.mlp.steps.1.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 702 |
+
"model.language_model.layers.31.mlp.steps.2.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 703 |
+
"model.language_model.layers.31.mlp.steps.2.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 704 |
+
"model.language_model.layers.31.mlp.steps.2.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 705 |
+
"model.language_model.layers.31.mlp.steps.3.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 706 |
+
"model.language_model.layers.31.mlp.steps.3.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 707 |
+
"model.language_model.layers.31.mlp.steps.3.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 708 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 709 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
|
| 710 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 711 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 712 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
|
| 713 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 714 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 715 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 716 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00005.safetensors",
|
| 717 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
|
| 718 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00005.safetensors",
|
| 719 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00005.safetensors",
|
| 720 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00005.safetensors",
|
| 721 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00005.safetensors",
|
| 722 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00005.safetensors",
|
| 723 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00005.safetensors",
|
| 724 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 725 |
+
"model.language_model.layers.4.mlp.halt_linear.bias": "model-00001-of-00005.safetensors",
|
| 726 |
+
"model.language_model.layers.4.mlp.halt_linear.weight": "model-00001-of-00005.safetensors",
|
| 727 |
+
"model.language_model.layers.4.mlp.residual_gates.0": "model-00001-of-00005.safetensors",
|
| 728 |
+
"model.language_model.layers.4.mlp.residual_gates.1": "model-00001-of-00005.safetensors",
|
| 729 |
+
"model.language_model.layers.4.mlp.residual_gates.2": "model-00001-of-00005.safetensors",
|
| 730 |
+
"model.language_model.layers.4.mlp.steps.0.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 731 |
+
"model.language_model.layers.4.mlp.steps.0.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 732 |
+
"model.language_model.layers.4.mlp.steps.0.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 733 |
+
"model.language_model.layers.4.mlp.steps.1.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 734 |
+
"model.language_model.layers.4.mlp.steps.1.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 735 |
+
"model.language_model.layers.4.mlp.steps.1.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 736 |
+
"model.language_model.layers.4.mlp.steps.2.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 737 |
+
"model.language_model.layers.4.mlp.steps.2.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 738 |
+
"model.language_model.layers.4.mlp.steps.2.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 739 |
+
"model.language_model.layers.4.mlp.steps.3.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 740 |
+
"model.language_model.layers.4.mlp.steps.3.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 741 |
+
"model.language_model.layers.4.mlp.steps.3.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 742 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 743 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 744 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00005.safetensors",
|
| 745 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
|
| 746 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00005.safetensors",
|
| 747 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00005.safetensors",
|
| 748 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00005.safetensors",
|
| 749 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00005.safetensors",
|
| 750 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00005.safetensors",
|
| 751 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00005.safetensors",
|
| 752 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 753 |
+
"model.language_model.layers.5.mlp.halt_linear.bias": "model-00001-of-00005.safetensors",
|
| 754 |
+
"model.language_model.layers.5.mlp.halt_linear.weight": "model-00001-of-00005.safetensors",
|
| 755 |
+
"model.language_model.layers.5.mlp.residual_gates.0": "model-00001-of-00005.safetensors",
|
| 756 |
+
"model.language_model.layers.5.mlp.residual_gates.1": "model-00001-of-00005.safetensors",
|
| 757 |
+
"model.language_model.layers.5.mlp.residual_gates.2": "model-00001-of-00005.safetensors",
|
| 758 |
+
"model.language_model.layers.5.mlp.steps.0.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 759 |
+
"model.language_model.layers.5.mlp.steps.0.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 760 |
+
"model.language_model.layers.5.mlp.steps.0.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 761 |
+
"model.language_model.layers.5.mlp.steps.1.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 762 |
+
"model.language_model.layers.5.mlp.steps.1.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 763 |
+
"model.language_model.layers.5.mlp.steps.1.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 764 |
+
"model.language_model.layers.5.mlp.steps.2.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 765 |
+
"model.language_model.layers.5.mlp.steps.2.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 766 |
+
"model.language_model.layers.5.mlp.steps.2.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 767 |
+
"model.language_model.layers.5.mlp.steps.3.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 768 |
+
"model.language_model.layers.5.mlp.steps.3.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 769 |
+
"model.language_model.layers.5.mlp.steps.3.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 770 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 771 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 772 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00002-of-00005.safetensors",
|
| 773 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
|
| 774 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
|
| 775 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
|
| 776 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
|
| 777 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
|
| 778 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
|
| 779 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
|
| 780 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
|
| 781 |
+
"model.language_model.layers.6.mlp.halt_linear.bias": "model-00002-of-00005.safetensors",
|
| 782 |
+
"model.language_model.layers.6.mlp.halt_linear.weight": "model-00002-of-00005.safetensors",
|
| 783 |
+
"model.language_model.layers.6.mlp.residual_gates.0": "model-00002-of-00005.safetensors",
|
| 784 |
+
"model.language_model.layers.6.mlp.residual_gates.1": "model-00002-of-00005.safetensors",
|
| 785 |
+
"model.language_model.layers.6.mlp.residual_gates.2": "model-00002-of-00005.safetensors",
|
| 786 |
+
"model.language_model.layers.6.mlp.steps.0.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 787 |
+
"model.language_model.layers.6.mlp.steps.0.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 788 |
+
"model.language_model.layers.6.mlp.steps.0.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 789 |
+
"model.language_model.layers.6.mlp.steps.1.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 790 |
+
"model.language_model.layers.6.mlp.steps.1.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 791 |
+
"model.language_model.layers.6.mlp.steps.1.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 792 |
+
"model.language_model.layers.6.mlp.steps.2.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 793 |
+
"model.language_model.layers.6.mlp.steps.2.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 794 |
+
"model.language_model.layers.6.mlp.steps.2.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 795 |
+
"model.language_model.layers.6.mlp.steps.3.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 796 |
+
"model.language_model.layers.6.mlp.steps.3.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 797 |
+
"model.language_model.layers.6.mlp.steps.3.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 798 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 799 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 800 |
+
"model.language_model.layers.7.mlp.halt_linear.bias": "model-00002-of-00005.safetensors",
|
| 801 |
+
"model.language_model.layers.7.mlp.halt_linear.weight": "model-00002-of-00005.safetensors",
|
| 802 |
+
"model.language_model.layers.7.mlp.residual_gates.0": "model-00002-of-00005.safetensors",
|
| 803 |
+
"model.language_model.layers.7.mlp.residual_gates.1": "model-00002-of-00005.safetensors",
|
| 804 |
+
"model.language_model.layers.7.mlp.residual_gates.2": "model-00002-of-00005.safetensors",
|
| 805 |
+
"model.language_model.layers.7.mlp.steps.0.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 806 |
+
"model.language_model.layers.7.mlp.steps.0.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 807 |
+
"model.language_model.layers.7.mlp.steps.0.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 808 |
+
"model.language_model.layers.7.mlp.steps.1.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 809 |
+
"model.language_model.layers.7.mlp.steps.1.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 810 |
+
"model.language_model.layers.7.mlp.steps.1.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 811 |
+
"model.language_model.layers.7.mlp.steps.2.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 812 |
+
"model.language_model.layers.7.mlp.steps.2.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 813 |
+
"model.language_model.layers.7.mlp.steps.2.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 814 |
+
"model.language_model.layers.7.mlp.steps.3.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 815 |
+
"model.language_model.layers.7.mlp.steps.3.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 816 |
+
"model.language_model.layers.7.mlp.steps.3.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 817 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 818 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 819 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 820 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 821 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
|
| 822 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 823 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 824 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 825 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00005.safetensors",
|
| 826 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
|
| 827 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
|
| 828 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
|
| 829 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
|
| 830 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
|
| 831 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
|
| 832 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
|
| 833 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
|
| 834 |
+
"model.language_model.layers.8.mlp.halt_linear.bias": "model-00002-of-00005.safetensors",
|
| 835 |
+
"model.language_model.layers.8.mlp.halt_linear.weight": "model-00002-of-00005.safetensors",
|
| 836 |
+
"model.language_model.layers.8.mlp.residual_gates.0": "model-00002-of-00005.safetensors",
|
| 837 |
+
"model.language_model.layers.8.mlp.residual_gates.1": "model-00002-of-00005.safetensors",
|
| 838 |
+
"model.language_model.layers.8.mlp.residual_gates.2": "model-00002-of-00005.safetensors",
|
| 839 |
+
"model.language_model.layers.8.mlp.steps.0.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 840 |
+
"model.language_model.layers.8.mlp.steps.0.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 841 |
+
"model.language_model.layers.8.mlp.steps.0.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 842 |
+
"model.language_model.layers.8.mlp.steps.1.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 843 |
+
"model.language_model.layers.8.mlp.steps.1.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 844 |
+
"model.language_model.layers.8.mlp.steps.1.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 845 |
+
"model.language_model.layers.8.mlp.steps.2.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 846 |
+
"model.language_model.layers.8.mlp.steps.2.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 847 |
+
"model.language_model.layers.8.mlp.steps.2.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 848 |
+
"model.language_model.layers.8.mlp.steps.3.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 849 |
+
"model.language_model.layers.8.mlp.steps.3.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 850 |
+
"model.language_model.layers.8.mlp.steps.3.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 851 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 852 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 853 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00005.safetensors",
|
| 854 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
|
| 855 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
|
| 856 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
|
| 857 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
|
| 858 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
|
| 859 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
|
| 860 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
|
| 861 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
|
| 862 |
+
"model.language_model.layers.9.mlp.halt_linear.bias": "model-00002-of-00005.safetensors",
|
| 863 |
+
"model.language_model.layers.9.mlp.halt_linear.weight": "model-00002-of-00005.safetensors",
|
| 864 |
+
"model.language_model.layers.9.mlp.residual_gates.0": "model-00002-of-00005.safetensors",
|
| 865 |
+
"model.language_model.layers.9.mlp.residual_gates.1": "model-00002-of-00005.safetensors",
|
| 866 |
+
"model.language_model.layers.9.mlp.residual_gates.2": "model-00002-of-00005.safetensors",
|
| 867 |
+
"model.language_model.layers.9.mlp.steps.0.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 868 |
+
"model.language_model.layers.9.mlp.steps.0.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 869 |
+
"model.language_model.layers.9.mlp.steps.0.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 870 |
+
"model.language_model.layers.9.mlp.steps.1.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 871 |
+
"model.language_model.layers.9.mlp.steps.1.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 872 |
+
"model.language_model.layers.9.mlp.steps.1.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 873 |
+
"model.language_model.layers.9.mlp.steps.2.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 874 |
+
"model.language_model.layers.9.mlp.steps.2.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 875 |
+
"model.language_model.layers.9.mlp.steps.2.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 876 |
+
"model.language_model.layers.9.mlp.steps.3.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 877 |
+
"model.language_model.layers.9.mlp.steps.3.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 878 |
+
"model.language_model.layers.9.mlp.steps.3.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 879 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 880 |
+
"model.language_model.norm.weight": "model-00005-of-00005.safetensors"
|
| 881 |
+
}
|
| 882 |
+
}
|
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 |
+
}
|