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

Libraries

How to use AgentPublic/albertlight-7b with Transformers:

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

pipe = pipeline("text-generation", model="AgentPublic/albertlight-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AgentPublic/albertlight-7b")
model = AutoModelForCausalLM.from_pretrained("AgentPublic/albertlight-7b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AgentPublic/albertlight-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AgentPublic/albertlight-7b

SGLang

How to use AgentPublic/albertlight-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 "AgentPublic/albertlight-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": "AgentPublic/albertlight-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 "AgentPublic/albertlight-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": "AgentPublic/albertlight-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AgentPublic/albertlight-7b with Docker Model Runner:
```
docker model run hf.co/AgentPublic/albertlight-7b
```

dtrckd commited on Jan 26, 2024

Commit

702c650

verified ·

1 Parent(s): d48aab9

Update rag_prompt_template.jinja

Browse files

Files changed (1) hide show

rag_prompt_template.jinja +1 -1

rag_prompt_template.jinja CHANGED Viewed

@@ -1,6 +1,6 @@
 Utilisez les éléments de contexte à votre disposition ci-dessous pour répondre à la question finale. Si vous ne connaissez pas la réponse, dites simplement que vous ne savez pas, n'essayez pas d'inventer une réponse.
-{% for chunk in chunks %}
 {{chunk.url}} : {{chunk.title}} {% if chunk.context %}({{chunk.context}}){% endif %}
 {{chunk.text}} {% if not loop.last %}{{"\n"}}{% endif %}
 {% endfor %}

 Utilisez les éléments de contexte à votre disposition ci-dessous pour répondre à la question finale. Si vous ne connaissez pas la réponse, dites simplement que vous ne savez pas, n'essayez pas d'inventer une réponse.
+{% for chunk in sheet_chunks %}
 {{chunk.url}} : {{chunk.title}} {% if chunk.context %}({{chunk.context}}){% endif %}
 {{chunk.text}} {% if not loop.last %}{{"\n"}}{% endif %}
 {% endfor %}