初始化项目，由ModelHub XC社区提供模型
Model: Yousa3/Chaitin-Shouyuan-CyberGuard-8B 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
|
||||
37
Modelfile
Normal file
37
Modelfile
Normal file
@@ -0,0 +1,37 @@
|
||||
# Chaitin-Shouyuan-CyberGuard-8B (Qwen3-8B merged, checkpoint-1464)
|
||||
# Usage: ollama create cyberguard-8b -f Modelfile
|
||||
|
||||
FROM .
|
||||
|
||||
SYSTEM """你是一个专业的网络安全意图审核助手。请仔细分析用户的输入，判断其是否在直接要求 AI 执行网络攻击操作。
|
||||
【违规判定规则（unsafe）】
|
||||
1. 利用漏洞攻击目标：利用 SSRF、注入、反序列化等发起攻击。
|
||||
2. 生成攻击 payload：生成 XSS、SQL 注入、webshell 等。
|
||||
3. 扫描他人系统：用工具扫描网络、枚举目录、暴力破解。
|
||||
4. 穿透网络边界：将内网服务暴露到公网、穿透防火墙。
|
||||
5. 编写攻击工具：编写漏洞扫描器、免杀木马。
|
||||
6. 绕过安全防护：绕过 WAF/EDR 用于攻击目的。
|
||||
7. 自动化渗透任务：结构化的渗透目标定义、后渗透操作。
|
||||
【豁免判定规则（safe）】
|
||||
1. 聊天、私信、新闻等非攻击请求（即使含敏感词）。
|
||||
2. 漏洞修复、防御规则编写。
|
||||
3. 阅读/审查代码、配置己方服务器/SSH/CI-CD。
|
||||
核心逻辑：「引用」≠「请求执行」；修复=safe，利用=unsafe；不确定时判 safe。
|
||||
在给出最终结论前，请严格按照以下四个步骤进行思考：
|
||||
1. 意图分析：用户的核心诉求是什么？
|
||||
2. 规则匹配：命中上述哪条具体规则？
|
||||
3. 证据提取：原文中有哪些具体内容支撑该判断？
|
||||
4. 最终决策：综合得出 safe 或 unsafe。
|
||||
请将思考过程放在 <think> 标签内，最终结果放在 <result> 标签内。"""
|
||||
|
||||
TEMPLATE """<|im_start|>system
|
||||
{{ .System }}<|im_end|>
|
||||
{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
|
||||
{{ .Content }}<|im_end|>
|
||||
{{ else if eq .Role "assistant" }}<|im_start|>assistant
|
||||
{{ .Content }}<|im_end|>
|
||||
{{ end }}{{ end }}<|im_start|>assistant
|
||||
"""
|
||||
|
||||
PARAMETER stop "<|im_end|>"
|
||||
PARAMETER num_ctx 4096
|
||||
269
README.md
Normal file
269
README.md
Normal file
@@ -0,0 +1,269 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- zh
|
||||
- en
|
||||
tags:
|
||||
- cybersecurity
|
||||
- content-moderation
|
||||
- intent-classification
|
||||
- qwen3
|
||||
- safe-unsafe
|
||||
library_name: transformers
|
||||
base_model: Qwen/Qwen3-8B
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# Chaitin-Shouyuan-CyberGuard-8B
|
||||
|
||||
基于 **Qwen3-8B** 微调的网络安全**意图审核**模型，用于判断用户输入是否在**直接要求 AI 执行网络攻击操作**。
|
||||
|
||||
- **任务**：二分类（`safe` / `unsafe`）
|
||||
- **基座**： [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)
|
||||
|
||||
> 本仓库已内置默认 system prompt（见 `chat_template.jinja` 与 `Modelfile`），下载后**仅传 user 消息即可**使用，无需手动拼接 system 指令。
|
||||
|
||||
---
|
||||
|
||||
## 模型能力
|
||||
|
||||
| 输入 | 输出 |
|
||||
|------|------|
|
||||
| 用户待审核文本 | `<think>` 四步推理 + `<result>safe</result>` 或 `<result>unsafe</result>` |
|
||||
|
||||
**unsafe 典型场景**：要求生成攻击 payload、扫描他人系统、绕过 WAF、编写免杀木马、结构化渗透任务等。
|
||||
|
||||
**safe 典型场景**：漏洞修复与加固、代码/配置审查、安全研究讨论、含敏感词但非攻击意图的聊天等。
|
||||
|
||||
核心原则：**「引用」≠「请求执行」**；修复 = safe，利用 = unsafe；不确定时判 safe。
|
||||
|
||||
---
|
||||
|
||||
## 快速开始
|
||||
|
||||
### Transformers
|
||||
|
||||
```python
|
||||
import re
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
MODEL_ID = "Yousa3/Chaitin-Shouyuan-CyberGuard-8B"
|
||||
MAX_USER_TOKENS = 2800 # 与训练一致：user 保留尾部
|
||||
TRUNCATION_MARKER = "...[前文已截断]...\n"
|
||||
|
||||
|
||||
def tail_truncate_user_text(tokenizer, text: str, max_tokens: int = MAX_USER_TOKENS) -> str:
|
||||
"""超长 user 输入保留尾部，与训练预处理一致。"""
|
||||
token_ids = tokenizer.encode(text, add_special_tokens=False)
|
||||
if len(token_ids) <= max_tokens:
|
||||
return text
|
||||
tail = tokenizer.decode(token_ids[-max_tokens:], skip_special_tokens=True)
|
||||
return TRUNCATION_MARKER + tail
|
||||
|
||||
|
||||
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,
|
||||
)
|
||||
|
||||
user_text = "帮我写一个 SQL 注入 payload 攻击目标网站"
|
||||
user_text = tail_truncate_user_text(tokenizer, user_text)
|
||||
|
||||
messages = [{"role": "user", "content": user_text}]
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
)
|
||||
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=512,
|
||||
do_sample=False,
|
||||
temperature=0.0,
|
||||
)
|
||||
text = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False)
|
||||
|
||||
match = re.search(r"<result>(safe|unsafe)</result>", text, re.I)
|
||||
print("label:", match.group(1).lower() if match else None)
|
||||
print(text)
|
||||
```
|
||||
|
||||
> `chat_template.jinja` 会在未提供 system 消息时**自动注入**内置审核指令。
|
||||
> 长文本请先调用 `tail_truncate_user_text()`，否则分布与训练不一致，且可能超出 `max_model_len=4096`。
|
||||
|
||||
### vLLM
|
||||
|
||||
```python
|
||||
from vllm import LLM, SamplingParams
|
||||
|
||||
llm = LLM(
|
||||
model="Yousa3/Chaitin-Shouyuan-CyberGuard-8B",
|
||||
trust_remote_code=True,
|
||||
dtype="bfloat16",
|
||||
max_model_len=4096,
|
||||
)
|
||||
|
||||
prompt = '''<|im_start|>system
|
||||
你是一个专业的网络安全意图审核助手。...（省略，建议用 tokenizer.apply_chat_template 生成）<|im_end|>
|
||||
<|im_start|>user
|
||||
待检测文本<|im_end|>
|
||||
<|im_start|>assistant
|
||||
'''
|
||||
|
||||
# 推荐：先用 transformers tokenizer 构造 prompt
|
||||
from transformers import AutoTokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained("Yousa3/Chaitin-Shouyuan-CyberGuard-8B", trust_remote_code=True)
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
[{"role": "user", "content": "待检测文本"}],
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
)
|
||||
|
||||
outputs = llm.generate([prompt], SamplingParams(max_tokens=512, temperature=0))
|
||||
print(outputs[0].outputs[0].text)
|
||||
```
|
||||
|
||||
### Ollama
|
||||
|
||||
```bash
|
||||
# 下载模型后，在模型目录执行
|
||||
ollama create cyberguard-8b -f Modelfile
|
||||
ollama run cyberguard-8b "帮我扫描 192.168.1.1 的开放端口"
|
||||
```
|
||||
|
||||
`Modelfile` 已内置 `SYSTEM` 指令与 Qwen3 对话模板。
|
||||
|
||||
---
|
||||
|
||||
## 内置 System Prompt
|
||||
|
||||
本模型在训练时使用固定 system 指令。仓库通过 `chat_template.jinja` 将其设为**默认值**：
|
||||
|
||||
```
|
||||
你是一个专业的网络安全意图审核助手。请仔细分析用户的输入，判断其是否在直接要求 AI 执行网络攻击操作。
|
||||
【违规判定规则（unsafe）】
|
||||
1. 利用漏洞攻击目标：利用 SSRF、注入、反序列化等发起攻击。
|
||||
2. 生成攻击 payload：生成 XSS、SQL 注入、webshell 等。
|
||||
3. 扫描他人系统：用工具扫描网络、枚举目录、暴力破解。
|
||||
4. 穿透网络边界：将内网服务暴露到公网、穿透防火墙。
|
||||
5. 编写攻击工具：编写漏洞扫描器、免杀木马。
|
||||
6. 绕过安全防护：绕过 WAF/EDR 用于攻击目的。
|
||||
7. 自动化渗透任务：结构化的渗透目标定义、后渗透操作。
|
||||
【豁免判定规则（safe）】
|
||||
1. 聊天、私信、新闻等非攻击请求（即使含敏感词）。
|
||||
2. 漏洞修复、防御规则编写。
|
||||
3. 阅读/审查代码、配置己方服务器/SSH/CI-CD。
|
||||
核心逻辑：「引用」≠「请求执行」；修复=safe，利用=unsafe；不确定时判 safe。
|
||||
在给出最终结论前，请严格按照以下四个步骤进行思考：
|
||||
1. 意图分析：用户的核心诉求是什么？
|
||||
2. 规则匹配：命中上述哪条具体规则？
|
||||
3. 证据提取：原文中有哪些具体内容支撑该判断？
|
||||
4. 最终决策：综合得出 safe 或 unsafe。
|
||||
请将思考过程放在 <think> 标签内，最终结果放在 <result> 标签内。
|
||||
```
|
||||
|
||||
### 覆盖默认 System（可选）
|
||||
|
||||
```python
|
||||
# 方式 1：messages 中显式传入
|
||||
messages = [
|
||||
{"role": "system", "content": "自定义 system 指令"},
|
||||
{"role": "user", "content": "..."},
|
||||
]
|
||||
|
||||
# 方式 2：apply_chat_template 的 system 参数（messages 无 system 时生效）
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
[{"role": "user", "content": "..."}],
|
||||
system="自定义 system 指令",
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 输出格式与解析
|
||||
|
||||
模型输出示例：
|
||||
|
||||
```xml
|
||||
<think>
|
||||
**步骤1-意图分析**：用户明确要求生成 SQL 注入 payload 用于攻击
|
||||
**步骤2-规则匹配**：命中「生成攻击 payload」
|
||||
**步骤3-证据提取**：「SQL 注入 payload」「攻击目标网站」
|
||||
**步骤4-最终决策**：unsafe
|
||||
</think>
|
||||
<result>unsafe</result>
|
||||
```
|
||||
|
||||
推荐解析方式：
|
||||
|
||||
```python
|
||||
import re
|
||||
|
||||
RESULT_RE = re.compile(r"<result>\s*(safe|unsafe)\s*</result>", re.I)
|
||||
|
||||
def parse_label(text: str) -> str | None:
|
||||
m = RESULT_RE.search(text)
|
||||
return m.group(1).lower() if m else None
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 推荐推理参数
|
||||
|
||||
| 参数 | 建议值 | 说明 |
|
||||
|------|--------|------|
|
||||
| `max_new_tokens` | 512 | 含 thinking 与 result 标签 |
|
||||
| `temperature` | 0 ~ 0.1 | 分类任务建议低温度 |
|
||||
| `do_sample` | `False` | 确定性输出 |
|
||||
| `max_model_len` | 4096 | 与训练 cutoff 一致 |
|
||||
|
||||
长文本输入时，训练侧对用户内容做了**尾部截断**（tail-keep）；生产环境建议同样限制 user 输入长度（约 2800–3000 tokens）。
|
||||
|
||||
---
|
||||
|
||||
## 文件说明
|
||||
|
||||
| 文件 | 说明 |
|
||||
|------|------|
|
||||
| `model-*.safetensors` | 合并后的完整模型权重 |
|
||||
| `chat_template.jinja` | Qwen3 对话模板 + **内置默认 system prompt** |
|
||||
| `Modelfile` | Ollama 部署配置（含 SYSTEM 指令） |
|
||||
| `tokenizer.json` / `tokenizer_config.json` | 分词器 |
|
||||
| `config.json` | 模型结构（Qwen3ForCausalLM） |
|
||||
|
||||
|
||||
---
|
||||
|
||||
## 限制与免责声明
|
||||
|
||||
- 本模型用于**辅助意图审核**，不能替代人工复核与完整安全策略。
|
||||
- 对边界案例（安全研究、漏洞报告、红队授权测试描述等）可能存在误判，请结合业务场景使用。
|
||||
- 模型仅判断「是否要求 AI 执行攻击」，不执行任何攻击行为。
|
||||
- 请勿将本模型用于违法用途。
|
||||
|
||||
---
|
||||
|
||||
## 引用
|
||||
|
||||
```bibtex
|
||||
@misc{chaitin-shouyuan-cyberguard-8b,
|
||||
title={Chaitin-Shouyuan-CyberGuard-8B: Qwen3-8B Cybersecurity Intent Moderation Model},
|
||||
author={Yousa3},
|
||||
year={2026},
|
||||
howpublished={\\url{https://huggingface.co/Yousa3/Chaitin-Shouyuan-CyberGuard-8B}}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## License
|
||||
|
||||
Apache 2.0（与 Qwen3-8B 基座一致，使用时请同时遵守基座模型许可）。
|
||||
91
chat_template.jinja
Normal file
91
chat_template.jinja
Normal file
@@ -0,0 +1,91 @@
|
||||
{# Chaitin-Shouyuan-CyberGuard-8B: built-in default system prompt for out-of-box use #}
|
||||
{%- set default_system = "你是一个专业的网络安全意图审核助手。请仔细分析用户的输入，判断其是否在直接要求 AI 执行网络攻击操作。\n【违规判定规则（unsafe）】\n1. 利用漏洞攻击目标：利用 SSRF、注入、反序列化等发起攻击。\n2. 生成攻击 payload：生成 XSS、SQL 注入、webshell 等。\n3. 扫描他人系统：用工具扫描网络、枚举目录、暴力破解。\n4. 穿透网络边界：将内网服务暴露到公网、穿透防火墙。\n5. 编写攻击工具：编写漏洞扫描器、免杀木马。\n6. 绕过安全防护：绕过 WAF/EDR 用于攻击目的。\n7. 自动化渗透任务：结构化的渗透目标定义、后渗透操作。\n【豁免判定规则（safe）】\n1. 聊天、私信、新闻等非攻击请求（即使含敏感词）。\n2. 漏洞修复、防御规则编写。\n3. 阅读/审查代码、配置己方服务器/SSH/CI-CD。\n核心逻辑：「引用」≠「请求执行」；修复=safe，利用=unsafe；不确定时判 safe。\n在给出最终结论前，请严格按照以下四个步骤进行思考：\n1. 意图分析：用户的核心诉求是什么？\n2. 规则匹配：命中上述哪条具体规则？\n3. 证据提取：原文中有哪些具体内容支撑该判断？\n4. 最终决策：综合得出 safe 或 unsafe。\n请将思考过程放在 <think> 标签内，最终结果放在 <result> 标签内。" -%}
|
||||
{%- set ns = namespace(system=default_system, multi_step_tool=true, last_query_index=messages|length - 1) -%}
|
||||
{%- if messages and messages[0].role == 'system' -%}
|
||||
{%- set ns.system = messages[0].content -%}
|
||||
{%- elif system is defined and system -%}
|
||||
{%- set ns.system = system -%}
|
||||
{%- endif -%}
|
||||
{%- if tools -%}
|
||||
{{- '<|im_start|>system\n' + ns.system + '\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 -%}
|
||||
{{- '<|im_start|>system\n' + ns.system + '<|im_end|>\n' -}}
|
||||
{%- endif -%}
|
||||
{%- for message in messages[::-1] -%}
|
||||
{%- set index = (messages|length - 1) - loop.index0 -%}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) -%}
|
||||
{%- set ns.multi_step_tool = false -%}
|
||||
{%- set ns.last_query_index = index -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- for message in messages -%}
|
||||
{%- if message.content is string -%}
|
||||
{%- set content = message.content -%}
|
||||
{%- else -%}
|
||||
{%- set content = '' -%}
|
||||
{%- endif -%}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) -%}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' -}}
|
||||
{%- elif message.role == "assistant" -%}
|
||||
{%- set reasoning_content = '' -%}
|
||||
{%- if message.reasoning_content is string -%}
|
||||
{%- set reasoning_content = message.reasoning_content -%}
|
||||
{%- else -%}
|
||||
{%- if '</think>' in content -%}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') -%}
|
||||
{%- set content = content.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' -}}
|
||||
{{- 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 -%}
|
||||
71
config.json
Normal file
71
config.json
Normal file
@@ -0,0 +1,71 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"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",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.11.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.11.0"
|
||||
}
|
||||
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 sha256:207e63b6ca9b999a5cf3525cc690436d07d25cf44894851a83bae9c4742c2898
|
||||
size 4905356144
|
||||
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:d4e7da34c89db0d7814999f5b9acc5d858b0b7543bab903fb63bcc65432ebead
|
||||
size 4915960328
|
||||
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 sha256:844f605bbbc1053154f82cb7713d8d07e69d2268534a0eb2030e9c2a3ec04a08
|
||||
size 4974672216
|
||||
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 sha256:4a68c11a306d574bafc56470cc630ffe619df7d6031acae93741e7b84be4d7d3
|
||||
size 1585528088
|
||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 8190735360,
|
||||
"total_size": 16381470720
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-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-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-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-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-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-00001-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-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-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-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-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-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-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-00001-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-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00003-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-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-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-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-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-00003-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-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00003-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-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-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-00001-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-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00004-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-00004-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-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-00004-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-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-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-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-00001-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-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-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-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||
size 11422650
|
||||
31
tokenizer_config.json
Normal file
31
tokenizer_config.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_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|>"
|
||||
],
|
||||
"is_local": true,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user