Instructions to use cam-1000/MNLP_M3_rag_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cam-1000/MNLP_M3_rag_model 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")
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")
model = AutoModelForCausalLM.from_pretrained("cam-1000/MNLP_M3_rag_model")
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 Settings

vLLM

How to use cam-1000/MNLP_M3_rag_model 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"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cam-1000/MNLP_M3_rag_model

SGLang

How to use cam-1000/MNLP_M3_rag_model 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" \
    --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",
		"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" \
        --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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cam-1000/MNLP_M3_rag_model with Docker Model Runner:
```
docker model run hf.co/cam-1000/MNLP_M3_rag_model
```

cam-1000 commited on Jun 5, 2025

Commit

fa6b2e1

verified ·

1 Parent(s): 54e0d1e

End of training

Browse files

Files changed (4) hide show

README.md +6 -7
config.json +1 -1
model.safetensors +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -1,7 +1,6 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: Qwen/Qwen3-0.6B-Base
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 # MNLP_M3_rag_model
-This model is a fine-tuned version of [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0000
 ## Model description
@@ -50,9 +49,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.0           | 0.0228 | 100  | 0.0000          |
-| 0.0           | 0.0456 | 200  | 0.0000          |
-| 0.0           | 0.0683 | 300  | 0.0000          |
 ### Framework versions

 ---
 library_name: transformers
+base_model: cam-1000/MNLP_M3_mcqa_model
 tags:
 - generated_from_trainer
 model-index:
 # MNLP_M3_rag_model
+This model is a fine-tuned version of [cam-1000/MNLP_M3_mcqa_model](https://huggingface.co/cam-1000/MNLP_M3_mcqa_model) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.8564
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
+| 0.8275        | 0.0228 | 100  | 0.8105          |
+| 0.7663        | 0.0456 | 200  | 0.8251          |
+| 0.5896        | 0.0683 | 300  | 0.8564          |
 ### Framework versions

config.json CHANGED Viewed

@@ -3,7 +3,7 @@
     "Qwen3ForCausalLM"
   ],
   "attention_bias": false,
-  "attention_dropout": 0.0,
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "head_dim": 128,

     "Qwen3ForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.1,
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "head_dim": 128,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95a855ef063a62a7db7a084ba0731f83f8ba671fcad58e393c6fba2264e021d6
 size 1192135096

 version https://git-lfs.github.com/spec/v1
+oid sha256:9c3fef9685203b9f660eacccb274de06644cda9c54f59e6a08b88dce69e363af
 size 1192135096

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb53288efc2ba5bed71f1270d0cc845cac5b26653e6a53f2850b42035e6acecd
 size 5713

 version https://git-lfs.github.com/spec/v1
+oid sha256:62eb3b5582a5d668757dda6894f7cdaaa74fa00eb64371185180a22602e99425
 size 5713