初始化项目，由ModelHub XC社区提供模型
Model: Jianwen/Webshop-7B-SFT 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
|
||||
16
Modelfile
Normal file
16
Modelfile
Normal file
@@ -0,0 +1,16 @@
|
||||
# ollama modelfile auto-generated by llamafactory
|
||||
|
||||
FROM .
|
||||
|
||||
TEMPLATE """{{ if .System }}<|im_start|>system
|
||||
{{ .System }}<|im_end|>
|
||||
{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
|
||||
{{ .Content }}<|im_end|>
|
||||
<|im_start|>assistant
|
||||
{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
|
||||
{{ end }}{{ end }}"""
|
||||
|
||||
SYSTEM """You are Qwen, created by Alibaba Cloud. You are a helpful assistant."""
|
||||
|
||||
PARAMETER stop "<|im_end|>"
|
||||
PARAMETER num_ctx 4096
|
||||
44
README.md
Normal file
44
README.md
Normal file
@@ -0,0 +1,44 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- en
|
||||
metrics:
|
||||
- accuracy
|
||||
base_model:
|
||||
- Qwen/Qwen2.5-7B-Instruct
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
## Introduction
|
||||
|
||||
**SkillRL-Webshop-SFT** is a cold-start checkpoint for the webshop RL environment.
|
||||
|
||||
- Task: WebShop
|
||||
- Stage: SFT
|
||||
|
||||
## Key Features
|
||||
|
||||
- Experience-based Skill Distillation: Transforms successful trajectories into strategic patterns and failed ones into concise lessons from failure.
|
||||
|
||||
- Hierarchical SKILLBANK: Organizes knowledge into General Skills for universal strategic guidance and Task-Specific Skills for category-level heuristics.
|
||||
|
||||
- Recursive Skill Evolution: A dynamic mechanism where the skill library co-evolves with the agent's policy during RL by analyzing validation failures.
|
||||
|
||||
- Context Efficiency: Achieves 10-20% token compression compared to raw trajectory storage while enhancing reasoning utility.
|
||||
|
||||
## Download
|
||||
You can download the model then run the training scipts in https://github.com/aiming-lab/SkillRL.
|
||||
|
||||
## Citation
|
||||
|
||||
* [Model Paper](https://arxiv.org/abs/2602.08234)
|
||||
|
||||
```bibtex
|
||||
@article{xia2026skillrl,
|
||||
title={SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning},
|
||||
author={Xia, Peng and Chen, Jianwen and Wang, Hanyang and Liu, Jiaqi and Zeng, Kaide and Wang, Yu and Han, Siwei and Zhou, Yiyang and Zhao, Xujiang and Chen, Haifeng and others},
|
||||
journal={arXiv preprint arXiv:2602.08234},
|
||||
year={2026}
|
||||
}
|
||||
```
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|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
|
||||
}
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) 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' }}
|
||||
{%- endif %}
|
||||
58
config.json
Normal file
58
config.json
Normal file
@@ -0,0 +1,58 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00009.safetensors
Normal file
3
model-00001-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e0ca1569111664bf718631a9d4da221e8f114eb8507bcd805f0be79fc1ff6cca
|
||||
size 1886423520
|
||||
3
model-00002-of-00009.safetensors
Normal file
3
model-00002-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:93fe7b3556ce2e9499b6bb3dd31a7ef2db51f1e33a4b4cf45f22098f96ce2ae9
|
||||
size 1864467800
|
||||
3
model-00003-of-00009.safetensors
Normal file
3
model-00003-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f8751018ee4e680042e024dcb4f5823da976590d94eff00d803befc9c6d0ac3f
|
||||
size 1864467800
|
||||
3
model-00004-of-00009.safetensors
Normal file
3
model-00004-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7b4063f35c219c735a7fb3236a4798b587e56aacf254867faebbd68ff255ad78
|
||||
size 1864467824
|
||||
3
model-00005-of-00009.safetensors
Normal file
3
model-00005-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:47950d2677464ab1620cc48e75d0615cf55ba1309cf6e289045a00aeeb409dfe
|
||||
size 1864467848
|
||||
3
model-00006-of-00009.safetensors
Normal file
3
model-00006-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7407e8c138ff6d66719b260f35b2e067574560e523b34d8697bc8a4c645936bb
|
||||
size 1864467848
|
||||
3
model-00007-of-00009.safetensors
Normal file
3
model-00007-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a89046902ddf0e392e6a9d06926a220bdd8484ccd5e45aeec370da3c7f14de19
|
||||
size 1864467848
|
||||
3
model-00008-of-00009.safetensors
Normal file
3
model-00008-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:efa12cbecc6bd521ead761a60624ff05426194a0ef675c34fbb44e89b4287c67
|
||||
size 1068046456
|
||||
3
model-00009-of-00009.safetensors
Normal file
3
model-00009-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2
|
||||
size 1089994880
|
||||
347
model.safetensors.index.json
Normal file
347
model.safetensors.index.json
Normal file
@@ -0,0 +1,347 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 7615616512,
|
||||
"total_size": 15231233024
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00009-of-00009.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.norm.weight": "model-00008-of-00009.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": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"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": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"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