初始化项目，由ModelHub XC社区提供模型
Model: flylcw/seq_monkey_pretrain_sft_optimization_1.5B 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
|
||||
68
README.md
Normal file
68
README.md
Normal file
@@ -0,0 +1,68 @@
|
||||
|
||||
---
|
||||
license: mit
|
||||
library_name: transformers
|
||||
base_model:
|
||||
- flylcw/seq_monkey_pretrain_base_1.5B
|
||||
language:
|
||||
- zh
|
||||
tags:
|
||||
- qwen2
|
||||
- qwen
|
||||
- sft
|
||||
- instruction-tuning
|
||||
- chinese
|
||||
- chat
|
||||
datasets:
|
||||
- BelleGroup/train_3.5M_CN
|
||||
- m-a-p/COIG-CQIA
|
||||
---
|
||||
|
||||
# seq_monkey_pretrain_sft_optimization_1.5B（中文指令微调模型）
|
||||
|
||||
在 [seq_monkey_pretrain_base_1.5B](https://huggingface.co/flylcw/seq_monkey_pretrain_base_1.5B) 之上，经过 **两阶段全参 SFT** 得到的中文指令对话模型：第一阶段用 BelleGroup 通用指令数据建立指令跟随能力，第二阶段用 COIG-CQIA 高质量数据进一步对齐。
|
||||
|
||||
## 模型结构（与 Base 完全一致）
|
||||
|
||||
**SFT 仅更新权重，不改变模型架构**，因此本模型的 `config.json` 与 Base 模型**完全相同**：
|
||||
|
||||
| 项目 | 值 |
|
||||
|---|---|
|
||||
| 架构 | Qwen2ForCausalLM |
|
||||
| 参数量 | 1.5B 级（HF 统计约 2B） |
|
||||
| hidden / layers / heads / kv_heads | 1536 / 28 / 12 / 2 |
|
||||
| intermediate / vocab / max_pos | 8960 / 151936 / 131072 |
|
||||
| 激活 / 归一化 / 位置编码 | SiLU(SwiGLU) / RMSNorm / RoPE |
|
||||
|
||||
|
||||
## 两阶段 SFT 流程
|
||||
|
||||
| 阶段 | 数据 | 规模 | 学习率 | epoch | 目的 |
|
||||
|---|---|---|---|---|---|
|
||||
| 阶段一 | [BelleGroup/train_3.5M_CN](https://huggingface.co/datasets/BelleGroup/train_3.5M_CN) | 3.5M 中文指令 | 2e-5 | 3 | 建立通用指令跟随 |
|
||||
| 阶段二 | [m-a-p/COIG-CQIA](https://huggingface.co/datasets/m-a-p/COIG-CQIA) | 数万条高质量中文指令 | 5e-6 | 3 | 高质量对齐、提升回答质量 |
|
||||
|
||||
- **训练方式**：全参 SFT（非 LoRA），Causal LM，仅对 assistant 回答部分计算 loss
|
||||
- **对话模板**：Qwen ChatML（`<|im_start|> / <|im_end|>`）
|
||||
- **序列长度**：1024
|
||||
- **优化**：bf16，cosine 学习率调度
|
||||
- **第二阶段说明**：在阶段一 checkpoint 基础上继续 SFT，学习率调小以防破坏已学能力
|
||||
|
||||
|
||||
## 快速开始（对话）
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
import torch
|
||||
|
||||
name = "flylcw/seq_monkey_pretrain_sft_optimization_1.5B"
|
||||
tok = AutoTokenizer.from_pretrained(name, trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
name, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
|
||||
|
||||
messages = [{"role": "user", "content": "用三句话介绍一下序列猴子数据集"}]
|
||||
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
ids = tok(text, return_tensors="pt").to(model.device)
|
||||
out = model.generate(**ids, max_new_tokens=256, do_sample=True,
|
||||
temperature=0.7, top_p=0.9, repetition_penalty=1.1)
|
||||
print(tok.decode(out[0], skip_special_tokens=True))
|
||||
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 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 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 %}
|
||||
62
config.json
Normal file
62
config.json
Normal file
@@ -0,0 +1,62 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151643,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8960,
|
||||
"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": 131072,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.14.1",
|
||||
"use_cache": false,
|
||||
"use_mrope": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"transformers_version": "5.14.1",
|
||||
"use_cache": true
|
||||
}
|
||||
151387
merges.txt
Normal file
151387
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:23789befdb1db46f00686661a9f733bee2062e7259c0645377f03b65d0e67b09
|
||||
size 3087467144
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
||||
size 11421892
|
||||
30
tokenizer_config.json
Normal file
30
tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"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|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:629dd923d25db0ba7fb8f284c7ccafe42fe05ae2453a7286dd7a45a006772c5a
|
||||
size 5201
|
||||
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