Instructions to use flylcw/seq_monkey_pretrain_base_1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flylcw/seq_monkey_pretrain_base_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_base_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_base_1.5B")
model = AutoModelForCausalLM.from_pretrained("flylcw/seq_monkey_pretrain_base_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_base_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_base_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_base_1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/flylcw/seq_monkey_pretrain_base_1.5B

SGLang

How to use flylcw/seq_monkey_pretrain_base_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_base_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_base_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_base_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_base_1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use flylcw/seq_monkey_pretrain_base_1.5B with Docker Model Runner:
```
docker model run hf.co/flylcw/seq_monkey_pretrain_base_1.5B
```

seq_monkey_pretrain_base_1.5B / README.md

flylcw

Update README.md

5dfe2fc verified 13 days ago

preview code

Raw

History Blame Contribute Delete

2.43 kB

	---
	license: mit
	library_name: transformers
	language:
	- zh
	tags:
	- qwen2
	- qwen
	- base-model
	- pretrained
	- chinese
	- from-scratch
	datasets:
	- ddzhu123/seq-monkey
	---

	# seq_monkey_pretrain_base_1.5B（中文 Base 预训练模型）

	基于 Qwen2.5-1.5B 架构、在出门问问「序列猴子」中文通用语料上 from-scratch（随机初始化）预训练的中文 Base 模型。本模型为 Base（续写）模型，未经指令微调，适合下游继续预训练 / SFT，或直接做文本续写。

	## 模型结构

	\| 项目 \| 值 \|
	\|---\|---\|
	\| 架构 \| Qwen2ForCausalLM（Decoder-only，LLaMA 同族） \|
	\| 参数量 \| 1.5B 级（含 15 万词表 embedding，HF 统计约 2B） \|
	\| hidden_size \| 1536 \|
	\| num_hidden_layers \| 28 \|
	\| num_attention_heads \| 12 \|
	\| num_key_value_heads \| 2（GQA） \|
	\| intermediate_size \| 8960 \|
	\| vocab_size \| 151936 \|
	\| max_position_embeddings \| 131072 \|
	\| 激活函数 \| SiLU（SwiGLU） \|
	\| 归一化 \| RMSNorm（eps=1e-6） \|
	\| 位置编码 \| RoPE \|
	\| 精度 \| BF16 \|

	## 预训练细节

	- 训练方式：from-scratch 随机初始化（非加载官方权重），Causal LM
	- 训练数据：[ddzhu123/seq-monkey](https://www.modelscope.cn/datasets/ddzhu123/seq-monkey) 的 `mobvoi_seq_monkey_general_open_corpus`——序列猴子中文通用文本语料，约 1300 万份中文文本，来源涵盖网页、百科、书籍等，许可 Apache-2.0
	- 分词器：Qwen2.5 Tokenizer（vocab 151936）
	- 序列长度：block_size = 1024
	- 优化：bf16 + DeepSpeed ZeRO-2，8×NVIDIA A800-40G
	- 学习率：2e-4，warmup + cosine
	- 训练规模：1 epoch
	- 收敛情况：loss 从 ~12（≈ln(151936)，随机初始化理论起点）平滑收敛至 ~3.x，grad_norm 稳定

	## 快速开始（Base = 续写，不用 chat template）

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	import torch

	name = "flylcw/seq_monkey_pretrain_base_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)

	prompt = "人工智能正在改变"
	ids = tok(prompt, return_tensors="pt").to(model.device)
	out = model.generate(**ids, max_new_tokens=128, do_sample=True,
	temperature=0.7, top_p=0.9, repetition_penalty=1.1)
	print(tok.decode(out[0], skip_special_tokens=True))