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
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

SFT on a synthetic custom (french) dataset (2k), from general question answering, problem solving to code question. It's a POC.

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))

Downloads last month: 113

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for teilomillet/MiniMerlin-3B

Quantizations

1 model

Collection including teilomillet/MiniMerlin-3B

Merlin

Collection

4 items • Updated Jan 6, 2024