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

Libraries

How to use FinchResearch/MarLin-7b with Transformers:

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

pipe = pipeline("text-generation", model="FinchResearch/MarLin-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FinchResearch/MarLin-7b")
model = AutoModelForCausalLM.from_pretrained("FinchResearch/MarLin-7b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FinchResearch/MarLin-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/FinchResearch/MarLin-7b

SGLang

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

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

chew commited on Aug 26, 2023

Commit

11982ae

1 Parent(s): 4cb72d1

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -5,7 +5,8 @@ tags:
 - llama
 - llama2
 ---
-### Status: Training In Progress
 # MarLin: Multilingual and Responsive Language Interface

 - llama
 - llama2
 ---
+## Not all MarLin versions are created equal. The HuggingFace model might not have all the features you need, like "Adapt to Your Style". For the full range of capabilities, visit our website (Being Built) where we've implemented these advanced features.
 # MarLin: Multilingual and Responsive Language Interface