初始化项目，由ModelHub XC社区提供模型
Model: tdlhl/MedSSR-Qwen3-8B-Base Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
140
README.md
Normal file
140
README.md
Normal file
@@ -0,0 +1,140 @@
|
|||||||
|
---
|
||||||
|
base_model:
|
||||||
|
- Qwen/Qwen3-8B-Base
|
||||||
|
tags:
|
||||||
|
- medical
|
||||||
|
library_name: transformers
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
---
|
||||||
|
|
||||||
|
# MedSSR-Qwen3-8B-Base
|
||||||
|
|
||||||
|
This is the model for our ACL 2026 Findings paper, "[Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach](https://huggingface.co/papers/2604.11547)". `MedSSR-Qwen3-8B-Base` is a medical reasoning-focused LLM built from `Qwen/Qwen3-8B-Base`.
|
||||||
|
|
||||||
|
## Model Summary
|
||||||
|
|
||||||
|
- **Base model**: `Qwen/Qwen3-8B-Base`
|
||||||
|
- **Model name**: `MedSSR-Qwen3-8B-Base`
|
||||||
|
- **Training framework**: [verl](https://github.com/verl-project/verl)
|
||||||
|
- **Paper link**: [https://arxiv.org/pdf/2604.11547](https://huggingface.co/papers/2604.11547)
|
||||||
|
- **Github repo**: [https://github.com/tdlhl/MedSSR](https://github.com/tdlhl/MedSSR)
|
||||||
|
- **Hugging Face training dataset**: [tdlhl/MedSSR-Synthetic-43K](https://huggingface.co/datasets/tdlhl/MedSSR-Synthetic-43K)
|
||||||
|
- **Hugging Face test dataset**: [tdlhl/RareDis-Sub](https://huggingface.co/datasets/tdlhl/RareDis-Sub)
|
||||||
|
|
||||||
|
## Quick Start (Transformers)
|
||||||
|
|
||||||
|
```python
|
||||||
|
import torch
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
model_id = "tdlhl/MedSSR-Qwen3-8B-Base"
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_id,
|
||||||
|
torch_dtype=torch.bfloat16,
|
||||||
|
device_map="auto",
|
||||||
|
trust_remote_code=True,
|
||||||
|
)
|
||||||
|
|
||||||
|
messages = [
|
||||||
|
{
|
||||||
|
"role": "user",
|
||||||
|
"content": (
|
||||||
|
"A 67-year-old man develops crushing substernal chest pain for 40 minutes. "
|
||||||
|
"ECG shows ST-segment elevation in leads II, III, and aVF. "
|
||||||
|
"Which coronary artery is most likely occluded?
|
||||||
|
"
|
||||||
|
"A. Left anterior descending artery
|
||||||
|
"
|
||||||
|
"B. Left circumflex artery
|
||||||
|
"
|
||||||
|
"C. Right coronary artery
|
||||||
|
"
|
||||||
|
"D. Posterior descending artery"
|
||||||
|
),
|
||||||
|
}
|
||||||
|
]
|
||||||
|
|
||||||
|
prompt = tokenizer.apply_chat_template(
|
||||||
|
messages,
|
||||||
|
tokenize=False,
|
||||||
|
add_generation_prompt=True,
|
||||||
|
)
|
||||||
|
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||||||
|
|
||||||
|
with torch.no_grad():
|
||||||
|
outputs = model.generate(
|
||||||
|
**inputs,
|
||||||
|
max_new_tokens=1024,
|
||||||
|
temperature=0.6,
|
||||||
|
top_p=0.95,
|
||||||
|
)
|
||||||
|
|
||||||
|
new_tokens = outputs[0][inputs["input_ids"].shape[-1]:]
|
||||||
|
print(tokenizer.decode(new_tokens, skip_special_tokens=True))
|
||||||
|
```
|
||||||
|
|
||||||
|
## Quick Start (vLLM)
|
||||||
|
|
||||||
|
```python
|
||||||
|
from vllm import LLM, SamplingParams
|
||||||
|
|
||||||
|
llm = LLM(
|
||||||
|
model="tdlhl/MedSSR-Qwen3-8B-Base",
|
||||||
|
trust_remote_code=True,
|
||||||
|
)
|
||||||
|
|
||||||
|
sampling = SamplingParams(
|
||||||
|
temperature=0.6,
|
||||||
|
top_p=0.95,
|
||||||
|
max_tokens=1024,
|
||||||
|
)
|
||||||
|
|
||||||
|
prompt = (
|
||||||
|
"A 24-year-old woman presents with fatigue, weight gain, constipation, and cold intolerance. "
|
||||||
|
"Which of the following laboratory findings is most consistent with primary hypothyroidism?
|
||||||
|
"
|
||||||
|
"A. Low TSH, low free T4
|
||||||
|
"
|
||||||
|
"B. High TSH, low free T4
|
||||||
|
"
|
||||||
|
"C. High TSH, high free T4
|
||||||
|
"
|
||||||
|
"D. Low TSH, high free T4"
|
||||||
|
)
|
||||||
|
|
||||||
|
outputs = llm.generate([prompt], sampling_params=sampling)
|
||||||
|
print(outputs[0].outputs[0].text)
|
||||||
|
```
|
||||||
|
|
||||||
|
## Suggested Decoding Setup
|
||||||
|
|
||||||
|
For evaluation settings similar to our paper, we follow the recommended setting of Qwen:
|
||||||
|
|
||||||
|
```text
|
||||||
|
temperature=0.6
|
||||||
|
top_p=0.95
|
||||||
|
top_k=20
|
||||||
|
max_tokens=2048
|
||||||
|
```
|
||||||
|
|
||||||
|
## Notes
|
||||||
|
|
||||||
|
- This model is intended for research use.
|
||||||
|
- The model may produce incorrect or unverifiable medical reasoning.
|
||||||
|
- Outputs should not be used as a substitute for professional medical judgment.
|
||||||
|
- For benchmark-style evaluation, please follow the released evaluation script in our repository.
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
|
||||||
|
If you find our model useful, please cite our paper:
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@article{li2025eliciting,
|
||||||
|
title={Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach},
|
||||||
|
author={Haolin Li, Shuyang Jiang, Ruipeng Zhang, Jiangchao Yao, Ya Zhang, Yanfeng Wang},
|
||||||
|
journal={arXiv preprint arXiv:2604.11547},
|
||||||
|
year={2026}
|
||||||
|
}
|
||||||
|
```
|
||||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"</think>": 151668,
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"</tool_response>": 151666,
|
||||||
|
"<think>": 151667,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<tool_response>": 151665,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
85
chat_template.jinja
Normal file
85
chat_template.jinja
Normal file
@@ -0,0 +1,85 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||||
|
{%- for message in messages[::-1] %}
|
||||||
|
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||||
|
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||||
|
{%- set ns.multi_step_tool = false %}
|
||||||
|
{%- set ns.last_query_index = index %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in message.content %}
|
||||||
|
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if loop.index0 > ns.last_query_index %}
|
||||||
|
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- message.content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||||
|
{{- '<think>\n\n</think>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151643,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 12288,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 36,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.52.4",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151643,
|
||||||
|
"max_new_tokens": 2048,
|
||||||
|
"transformers_version": "4.52.4"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:72e7cc69e7bb4aa5fc039bf670013b3ef19e6bc980d94f6f5c55b01a42fff14a
|
||||||
|
size 4983092304
|
||||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d61dd6bc167c5c2d4829c8c9947f5be27426e302d356d745e237a953fb06e37a
|
||||||
|
size 4944200408
|
||||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b9374a871644f11ec27e70cdda3f056a3def142b1b458ff2875bcab6bf342cba
|
||||||
|
size 4961019792
|
||||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:16fcc3270e9136ea1aa2b9f621e18498143feae62812674473d3c48941919019
|
||||||
|
size 1493204312
|
||||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 16381470720
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.norm.weight": "model-00002-of-00004.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151665": {
|
||||||
|
"content": "<tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151666": {
|
||||||
|
"content": "</tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151667": {
|
||||||
|
"content": "<think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151668": {
|
||||||
|
"content": "</think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user