Instructions to use model-attribution-challenge/bloom-2b5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use model-attribution-challenge/bloom-2b5 with Transformers:

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

pipe = pipeline("text-generation", model="model-attribution-challenge/bloom-2b5")

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("model-attribution-challenge/bloom-2b5")
model = AutoModel.from_pretrained("model-attribution-challenge/bloom-2b5", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use model-attribution-challenge/bloom-2b5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "model-attribution-challenge/bloom-2b5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "model-attribution-challenge/bloom-2b5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/model-attribution-challenge/bloom-2b5

SGLang

How to use model-attribution-challenge/bloom-2b5 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 "model-attribution-challenge/bloom-2b5" \
    --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": "model-attribution-challenge/bloom-2b5",
		"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 "model-attribution-challenge/bloom-2b5" \
        --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": "model-attribution-challenge/bloom-2b5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use model-attribution-challenge/bloom-2b5 with Docker Model Runner:
```
docker model run hf.co/model-attribution-challenge/bloom-2b5
```

Muennighoff commited on Sep 27, 2022

Commit

515ae96

1 Parent(s): 1c5992f

Update config.json (#9)

Browse files

- Update config.json (c59381abbf01b42e86d2bd52c4410c329c2a09aa)

Files changed (1) hide show

config.json +0 -1

config.json CHANGED Viewed

@@ -21,7 +21,6 @@
   "num_attention_heads": 32,
   "offset_alibi": 100,
   "pretraining_tp": 4,
-  "seq_length": 2048,
   "skip_bias_add": true,
   "skip_bias_add_qkv": false,
   "transformers_version": "4.20.0",

   "num_attention_heads": 32,
   "offset_alibi": 100,
   "pretraining_tp": 4,
   "skip_bias_add": true,
   "skip_bias_add_qkv": false,
   "transformers_version": "4.20.0",