Instructions to use MultiTrickFox/bloom-2b5_Zen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MultiTrickFox/bloom-2b5_Zen with Transformers:

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

pipe = pipeline("text-generation", model="MultiTrickFox/bloom-2b5_Zen")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MultiTrickFox/bloom-2b5_Zen")
model = AutoModelForCausalLM.from_pretrained("MultiTrickFox/bloom-2b5_Zen", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MultiTrickFox/bloom-2b5_Zen with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MultiTrickFox/bloom-2b5_Zen"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MultiTrickFox/bloom-2b5_Zen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MultiTrickFox/bloom-2b5_Zen

SGLang

How to use MultiTrickFox/bloom-2b5_Zen 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 "MultiTrickFox/bloom-2b5_Zen" \
    --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": "MultiTrickFox/bloom-2b5_Zen",
		"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 "MultiTrickFox/bloom-2b5_Zen" \
        --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": "MultiTrickFox/bloom-2b5_Zen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MultiTrickFox/bloom-2b5_Zen with Docker Model Runner:
```
docker model run hf.co/MultiTrickFox/bloom-2b5_Zen
```

MultiTrickFox commited on Jul 16, 2022

Commit

25ebbf6

1 Parent(s): 7f25e3b

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -2

README.md CHANGED Viewed

@@ -13,12 +13,17 @@ Bloom (2.5 B) Scientific Model fine-tuned on Zen knowledge
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 tokenizer = AutoTokenizer.from_pretrained("MultiTrickFox/bloom-2b5_Zen")
 model = AutoModelForCausalLM.from_pretrained("MultiTrickFox/bloom-2b5_Zen")
-model
 tokenizer.pad_token_id = tokenizer.eos_token_id
 generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
@@ -26,7 +31,7 @@ generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
 inp = [ """Today""", """Yesterday""" ]
 out = generator(
-    inp, do_sample=True,
     temperature=.6,
     typical_p=.7,

 ```python
+cuda = False
 from transformers import AutoTokenizer, AutoModelForCausalLM
 tokenizer = AutoTokenizer.from_pretrained("MultiTrickFox/bloom-2b5_Zen")
 model = AutoModelForCausalLM.from_pretrained("MultiTrickFox/bloom-2b5_Zen")
+model.cuda() if cuda else None
 tokenizer.pad_token_id = tokenizer.eos_token_id
 generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
 inp = [ """Today""", """Yesterday""" ]
 out = generator(
+    inp.cuda() if cuda else inp, do_sample=True,
     temperature=.6,
     typical_p=.7,