Instructions to use flylcw/seq_monkey_pretrain_sft_optimization_1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flylcw/seq_monkey_pretrain_sft_optimization_1.5B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="flylcw/seq_monkey_pretrain_sft_optimization_1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flylcw/seq_monkey_pretrain_sft_optimization_1.5B")
model = AutoModelForCausalLM.from_pretrained("flylcw/seq_monkey_pretrain_sft_optimization_1.5B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use flylcw/seq_monkey_pretrain_sft_optimization_1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flylcw/seq_monkey_pretrain_sft_optimization_1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flylcw/seq_monkey_pretrain_sft_optimization_1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/flylcw/seq_monkey_pretrain_sft_optimization_1.5B

SGLang

How to use flylcw/seq_monkey_pretrain_sft_optimization_1.5B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "flylcw/seq_monkey_pretrain_sft_optimization_1.5B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flylcw/seq_monkey_pretrain_sft_optimization_1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "flylcw/seq_monkey_pretrain_sft_optimization_1.5B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flylcw/seq_monkey_pretrain_sft_optimization_1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use flylcw/seq_monkey_pretrain_sft_optimization_1.5B with Docker Model Runner:
```
docker model run hf.co/flylcw/seq_monkey_pretrain_sft_optimization_1.5B
```

seq_monkey_pretrain_sft_optimization_1.5B / README.md

flylcw

Update README.md

5c62793 verified 12 days ago

preview code

Raw

History Blame Contribute Delete

2.65 kB


	---
	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))