Instructions to use RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits with Transformers:

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

pipe = pipeline("text-generation", model="RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits

SGLang

How to use RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits 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 "RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits" \
    --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": "RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits",
		"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 "RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits" \
        --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": "RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/WangZeJun_-_bloom-820m-chat-8bits
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

bloom-820m-chat - bnb 8bits

Model creator: https://huggingface.co/WangZeJun/
Original model: https://huggingface.co/WangZeJun/bloom-820m-chat/

Original model description:

license: bigscience-bloom-rail-1.0

https://github.com/zejunwang1/bloom_tuning

可以通过如下代码调用 bloom-820m-chat 模型来生成对话：

from transformers import BloomTokenizerFast, BloomForCausalLM

model_name_or_path = "WangZeJun/bloom-820m-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: 2

Safetensors

Model size

0.8B params

Tensor type

F32

F16