Text Generation
Transformers
Safetensors
English
Chinese
qwen3
haidass
npu
bilingual
mindspeed-llm
conversational
text-generation-inference
Instructions to use DALabCommunity/Haidass-143M-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DALabCommunity/Haidass-143M-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DALabCommunity/Haidass-143M-v1") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DALabCommunity/Haidass-143M-v1") model = AutoModelForCausalLM.from_pretrained("DALabCommunity/Haidass-143M-v1", 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 DALabCommunity/Haidass-143M-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DALabCommunity/Haidass-143M-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DALabCommunity/Haidass-143M-v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/DALabCommunity/Haidass-143M-v1
- SGLang
How to use DALabCommunity/Haidass-143M-v1 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 "DALabCommunity/Haidass-143M-v1" \ --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": "DALabCommunity/Haidass-143M-v1", "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 "DALabCommunity/Haidass-143M-v1" \ --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": "DALabCommunity/Haidass-143M-v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use DALabCommunity/Haidass-143M-v1 with Docker Model Runner:
docker model run hf.co/DALabCommunity/Haidass-143M-v1
| <div align="center"> | |
| <img src="logo.png" width="400"/> | |
| </div> | |
| # Haidass-143M | |
| <p align="center"> | |
| <a href="https://huggingface.co/DALabCommunity/Haidass-143M-v1/blob/main/README.md">English</a> | | |
| 中文 | |
| </p> | |
| 中英双语小语言模型,在**华为昇腾**生态上进行全流程训练。 | |
| ## 模型简介 | |
| Haidass-143M 是一个 143M 参数的中英双语语言模型,在约 100B token 的中英文数据上训练完成。模型在华为昇腾生态上进行全流程训练,整体流程基于 **MindSpeed-LLM** 框架和 Atlas A2 服务器(910B)。同时配套训练了大小为 64,000 的中英双语词表。该模型在 150M 以下参数规模的多语言模型中具有较强竞争力,并在多个评测指标中排名靠前。 | |
| ## 模型架构 | |
| | 参数 | 值 | | |
| |------|-----| | |
| | 架构 | Qwen3 | | |
| | 层数 | 30 | | |
| | 隐层维度 | 576 | | |
| | 注意力头数 | 9 | | |
| | KV 头数 (GQA) | 3 | | |
| | 头维度 | 64 | | |
| | FFN 中间维度 | 1,536 | | |
| | 词表大小 | 64,000 | | |
| | 最大序列长度 | 4,096 | | |
| | 绑定嵌入 | 是 | | |
| | 位置编码 | RoPE (θ=100,000) | | |
| | 注意力偏置 | 无 | | |
| | 精度 | BF16 | | |
| | 总参数量 | ~143M | | |
| ## 训练数据 | |
| 模型在约 100B token 的中英文混合数据上训练。主要数据来源为: | |
| - [openbmb/Ultra-FineWeb](https://huggingface.co/datasets/openbmb/Ultra-FineWeb) (ultrafineweb-en + ultrafineweb-zh) | |
| - [mlfoundations/dclm-baseline-1.0-parquet](https://huggingface.co/datasets/mlfoundations/dclm-baseline-1.0-parquet) (dclm) | |
| - [HuggingFaceTB/finemath](https://huggingface.co/datasets/HuggingFaceTB/finemath) (finemath-4plus) | |
| ## 训练配置 | |
| | 参数 | 值 | | |
| |------|------| | |
| | 框架 | MindSpeed-LLM (v2.3.0) | | |
| | 硬件 | 8 台 Atlas A2 服务器 (每台 8 卡 NPU,256 核) | | |
| | NPU 型号 | 华为昇腾 910B | | |
| | 总 NPU 数 | 64 (8 节点 × 8 卡) | | |
| | 序列长度 | 4,096 | | |
| ## 优化器 | |
| | 参数 | 值 | | |
| |------|------| | |
| | 优化器 | AdamW | | |
| | 峰值学习率 | 3e-4 | | |
| | 最低学习率 | 3e-5 | | |
| ## 词表 | |
| | 属性 | 值 | | |
| |------|------| | |
| | 类型 | SentencePiece BPE | | |
| | 词表大小 | 64,000 | | |
| | 语言覆盖 | 英文 + 中文 | | |
| ## 测评 | |
| 在 checkpoint (~98B tokens) 上基于 lighteval 框架(v0.9.2)测评。 | |
| | Benchmark | Score | | |
| |------|------| | |
| | ARC-Easy | 60.44 | | |
| | ARC-Challenge | 27.13 | | |
| | PIQA | 67.25 | | |
| | HellaSwag | 37.91 | | |
| | OpenBookQA | 31.8 | | |
| | Winogrande | 52.17 | | |
| | agi_eval | 23.78 | | |
| ## 核心特点 | |
| - **全昇腾原生**: 完全在华为昇腾 910B NPU 上训练,使用 MindSpeed-LLM 框架 | |
| - **中英双语**: 模型基于中英混合数据集训练 | |
| ## 预期用途 | |
| 本模型为研究型模型,适用于: | |
| - 研究小模型在昇腾 NPU 上的训练动态 | |
| - 中英文语言建模研究 | |
| - 作为后续微调或退火实验的基础模型 | |
| ## 局限性 | |
| - 模型规模较小,推理和生成能力有限 | |
| - 仅为原始预训练模型 | |
| ## Citation | |
| ```bibtex | |
| @misc{haidass-143m, | |
| title={haidass-143M: A Bilingual Small Language Model Trained on Ascend 910B}, | |
| year={2026}, | |
| note={Based on Qwen3 architecture, trained from scratch on 100B tokens using MindSpeed-LLM on 64× Ascend 910B NPUs} | |
| } | |
| ``` | |
| ## License | |
| Apache 2.0 | |