Instructions to use fireballoon/baichuan-llama-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fireballoon/baichuan-llama-7b with Transformers:

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

pipe = pipeline("text-generation", model="fireballoon/baichuan-llama-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fireballoon/baichuan-llama-7b")
model = AutoModelForCausalLM.from_pretrained("fireballoon/baichuan-llama-7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use fireballoon/baichuan-llama-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fireballoon/baichuan-llama-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fireballoon/baichuan-llama-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fireballoon/baichuan-llama-7b

SGLang

How to use fireballoon/baichuan-llama-7b 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 "fireballoon/baichuan-llama-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fireballoon/baichuan-llama-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "fireballoon/baichuan-llama-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fireballoon/baichuan-llama-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fireballoon/baichuan-llama-7b with Docker Model Runner:
```
docker model run hf.co/fireballoon/baichuan-llama-7b
```

请问验证过转完的llama格式权重能够用于sft吗

by nnyao - opened Jun 20, 2023

Discussion

nnyao

Jun 20, 2023

请问验证过转完的llama格式权重能够用于sft吗

fireballoon

Owner Jun 20, 2023

可以的。转换之后的模型和llama是一样的，所有支持llama的代码都可以直接使用。
我使用转换后的模型已经成功训练了sft模型：baichuan-vicuna-7b, baichuan-vicuna-chinese-7b。

Kuaixueshiqing

Jul 3, 2023

可以的。转换之后的模型和llama是一样的，所有支持llama的代码都可以直接使用。
我使用转换后的模型已经成功训练了sft模型：baichuan-vicuna-7b, baichuan-vicuna-chinese-7b。

请问使用这个模型做sft和baichuan官方的有什么区别？只是lora的module name不一样吗？

fireballoon

Owner Jul 3, 2023

对。本模型只是把baichuan的w_pack恢复回了llama的qkv矩阵，其他未做任何改动。转化代码：https://huggingface.co/fireballoon/baichuan-llama-7b/blob/main/convert_baichuan_to_llama.py
训练超参数设置成训练llama-7b的参数就行。

hzq010103

Nov 20, 2023

•

edited Nov 20, 2023

请问用https://github.com/hiyouga/LLaMA-Factory 训练这个fireballoon/baichuan-llama-7b会报错是什么原因呢：
File "/home/tiger/.local/lib/python3.9/site-packages/peft/tuners/lora/layer.py", line 296, in _linear
return F.linear(input, transpose(self.weight, self.fan_in_fan_out), bias=self.bias)
RuntimeError: CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling cublasCreate(handle)
../aten/src/ATen/native/cuda/Indexing.cu:1292: indexSelectLargeIndex: block: [486,0,0], thread: [32,0,0] Assertion srcIndex < srcSelectDimSize failed.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment