Instructions to use cam-1000/MNLP_M3_rag_model_v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cam-1000/MNLP_M3_rag_model_v4 with Transformers:

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

pipe = pipeline("text-generation", model="cam-1000/MNLP_M3_rag_model_v4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cam-1000/MNLP_M3_rag_model_v4")
model = AutoModelForCausalLM.from_pretrained("cam-1000/MNLP_M3_rag_model_v4")
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 cam-1000/MNLP_M3_rag_model_v4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cam-1000/MNLP_M3_rag_model_v4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cam-1000/MNLP_M3_rag_model_v4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cam-1000/MNLP_M3_rag_model_v4

SGLang

How to use cam-1000/MNLP_M3_rag_model_v4 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 "cam-1000/MNLP_M3_rag_model_v4" \
    --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": "cam-1000/MNLP_M3_rag_model_v4",
		"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 "cam-1000/MNLP_M3_rag_model_v4" \
        --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": "cam-1000/MNLP_M3_rag_model_v4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cam-1000/MNLP_M3_rag_model_v4 with Docker Model Runner:
```
docker model run hf.co/cam-1000/MNLP_M3_rag_model_v4
```

MNLP_M3_rag_model_v4

This model is a fine-tuned version of sophiargh/MNLP_M3_mcqa_model on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.8707

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.01
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
0.7279	0.0228	100	0.8089
0.7328	0.0456	200	0.7907
0.584	0.0683	300	0.8175
0.6671	0.0911	400	0.8707

Framework versions

Transformers 4.52.3
Pytorch 2.7.0+cu126
Datasets 3.2.0
Tokenizers 0.21.0

Downloads last month: 4

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for cam-1000/MNLP_M3_rag_model_v4

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

sophiargh/MNLP_M3_mcqa_model

Finetuned

(1)

this model