Instructions to use Lebossoti/MODEL_M3_FINETUNED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lebossoti/MODEL_M3_FINETUNED with Transformers:

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

pipe = pipeline("text-generation", model="Lebossoti/MODEL_M3_FINETUNED")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lebossoti/MODEL_M3_FINETUNED")
model = AutoModelForCausalLM.from_pretrained("Lebossoti/MODEL_M3_FINETUNED")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Lebossoti/MODEL_M3_FINETUNED with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lebossoti/MODEL_M3_FINETUNED"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lebossoti/MODEL_M3_FINETUNED",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lebossoti/MODEL_M3_FINETUNED

SGLang

How to use Lebossoti/MODEL_M3_FINETUNED 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 "Lebossoti/MODEL_M3_FINETUNED" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lebossoti/MODEL_M3_FINETUNED",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Lebossoti/MODEL_M3_FINETUNED" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lebossoti/MODEL_M3_FINETUNED",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Lebossoti/MODEL_M3_FINETUNED with Docker Model Runner:
```
docker model run hf.co/Lebossoti/MODEL_M3_FINETUNED
```

Lebossoti commited on Jun 7, 2025

Commit

b2264eb

verified ·

1 Parent(s): 2770066

Model save

Browse files

Files changed (1) hide show

README.md +5 -6

README.md CHANGED Viewed

@@ -1,8 +1,7 @@
 ---
-base_model: Qwen/Qwen3-0.6B-Base
-datasets: youssefbelghmi/MNLP_M3_mcqa_dataset
 library_name: transformers
-model_name: MNLP_M3_mcqa_small_model
 tags:
 - generated_from_trainer
 - trl
@@ -10,9 +9,9 @@ tags:
 licence: license
 ---
-# Model Card for MNLP_M3_mcqa_small_model
-This model is a fine-tuned version of [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) on the [youssefbelghmi/MNLP_M3_mcqa_dataset](https://huggingface.co/datasets/youssefbelghmi/MNLP_M3_mcqa_dataset) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
@@ -21,7 +20,7 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="Lebossoti/MNLP_M3_mcqa_small_model", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```

 ---
+base_model: youssefbelghmi/MNLP_M3_mcqa_model
 library_name: transformers
+model_name: MNLP_M3_rag_model
 tags:
 - generated_from_trainer
 - trl
 licence: license
 ---
+# Model Card for MNLP_M3_rag_model
+This model is a fine-tuned version of [youssefbelghmi/MNLP_M3_mcqa_model](https://huggingface.co/youssefbelghmi/MNLP_M3_mcqa_model).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 from transformers import pipeline
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Lebossoti/MNLP_M3_rag_model", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```