Instructions to use teilomillet/MiniMerlin-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use teilomillet/MiniMerlin-3B with Transformers:

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

pipe = pipeline("text-generation", model="teilomillet/MiniMerlin-3B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("teilomillet/MiniMerlin-3B")
model = AutoModelForCausalLM.from_pretrained("teilomillet/MiniMerlin-3B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use teilomillet/MiniMerlin-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "teilomillet/MiniMerlin-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teilomillet/MiniMerlin-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/teilomillet/MiniMerlin-3B

SGLang

How to use teilomillet/MiniMerlin-3B 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 "teilomillet/MiniMerlin-3B" \
    --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": "teilomillet/MiniMerlin-3B",
		"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 "teilomillet/MiniMerlin-3B" \
        --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": "teilomillet/MiniMerlin-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use teilomillet/MiniMerlin-3B with Docker Model Runner:
```
docker model run hf.co/teilomillet/MiniMerlin-3B
```

teilomillet commited on Dec 29, 2023

Commit

d13cdbc

1 Parent(s): 8bb5a2d

Update README.md

Browse files

Files changed (1) hide show

README.md +25 -1

README.md CHANGED Viewed

@@ -9,4 +9,28 @@ widget:
 - text: "<s> [|User|] Comment faire un bon plat ? </s>[|Assistant|]"
 ---
 SFT on a synthetic custom (french) dataset (2k), from general question answering, problem solving to code question.
-It's a POC.

 - text: "<s> [|User|] Comment faire un bon plat ? </s>[|Assistant|]"
 ---
 SFT on a synthetic custom (french) dataset (2k), from general question answering, problem solving to code question.
+It's a POC.
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+model = AutoModelForCausalLM.from_pretrained(
+    "teilomillet/MiniMerlin-3B",
+    revision="0.1",
+    return_dict=True,
+    torch_dtype=torch.bfloat16,
+    device_map='auto'
+)
+tokenizer = AutoTokenizer.from_pretrained("teilomillet/MiniMerlin-3B")
+tokenizer.pad_token = tokenizer.eos_token
+text = "[|User|] Comment faire un bon plat ? </s>[|Assistant|]"
+inputs = tokenizer(text, return_tensors="pt").to(0)
+outputs = model.generate(**inputs, max_new_tokens=800)
+print(tokenizer.decode(outputs[0], skip_special_tokens=False))
+```