Instructions to use WangZeJun/bloom-396m-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WangZeJun/bloom-396m-chat with Transformers:

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

pipe = pipeline("text-generation", model="WangZeJun/bloom-396m-chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WangZeJun/bloom-396m-chat")
model = AutoModelForCausalLM.from_pretrained("WangZeJun/bloom-396m-chat")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WangZeJun/bloom-396m-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WangZeJun/bloom-396m-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WangZeJun/bloom-396m-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WangZeJun/bloom-396m-chat

SGLang

How to use WangZeJun/bloom-396m-chat 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 "WangZeJun/bloom-396m-chat" \
    --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": "WangZeJun/bloom-396m-chat",
		"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 "WangZeJun/bloom-396m-chat" \
        --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": "WangZeJun/bloom-396m-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WangZeJun/bloom-396m-chat with Docker Model Runner:
```
docker model run hf.co/WangZeJun/bloom-396m-chat
```

https://github.com/zejunwang1/bloom_tuning

可以通过如下代码调用 bloom-396m-chat 模型来生成对话：

from transformers import BloomTokenizerFast, BloomForCausalLM

model_name_or_path = "WangZeJun/bloom-396m-chat"

tokenizer = BloomTokenizerFast.from_pretrained(model_name_or_path)
model = BloomForCausalLM.from_pretrained(model_name_or_path).cuda()
model = model.eval()

input_pattern = "{}</s>"
text = "你好"
input_ids = tokenizer(input_pattern.format(text), return_tensors="pt").input_ids
input_ids = input_ids.cuda()

outputs = model.generate(input_ids, do_sample=True, max_new_tokens=1024, top_p=0.85,
    temperature=0.3, repetition_penalty=1.2, eos_token_id=tokenizer.eos_token_id)

input_ids_len = input_ids.size(1)
response_ids = outputs[0][input_ids_len:]
response = tokenizer.decode(response_ids)
print(response)

Downloads last month: 11

Safetensors

Model size

0.3B params

Tensor type

F32