Instructions to use swadhindas324/Mistral-NWPU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use swadhindas324/Mistral-NWPU with Transformers:

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

pipe = pipeline("text-generation", model="swadhindas324/Mistral-NWPU")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("swadhindas324/Mistral-NWPU")
model = AutoModelForMultimodalLM.from_pretrained("swadhindas324/Mistral-NWPU")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use swadhindas324/Mistral-NWPU with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "swadhindas324/Mistral-NWPU"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "swadhindas324/Mistral-NWPU",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/swadhindas324/Mistral-NWPU

SGLang

How to use swadhindas324/Mistral-NWPU 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 "swadhindas324/Mistral-NWPU" \
    --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": "swadhindas324/Mistral-NWPU",
		"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 "swadhindas324/Mistral-NWPU" \
        --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": "swadhindas324/Mistral-NWPU",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use swadhindas324/Mistral-NWPU with Docker Model Runner:
```
docker model run hf.co/swadhindas324/Mistral-NWPU
```

Mistral-NWPU

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

Loss: 0.8049

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: 0.0001
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 64
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.3107	1.0	2215	1.0127
0.9907	2.0	4430	0.9383
0.9338	3.0	6645	0.9026
0.9008	4.0	8860	0.8811
0.8784	5.0	11075	0.8699
0.8630	6.0	13290	0.8576
0.8522	7.0	15505	0.8509
0.8438	8.0	17720	0.8450
0.8369	9.0	19935	0.8403
0.8313	10.0	22150	0.8374
0.8269	11.0	24365	0.8347
0.8230	12.0	26580	0.8303
0.8194	13.0	28795	0.8286
0.8163	14.0	31010	0.8283
0.8134	15.0	33225	0.8254
0.8112	16.0	35440	0.8228
0.8090	17.0	37655	0.8210
0.8066	18.0	39870	0.8219
0.8047	19.0	42085	0.8199
0.8027	20.0	44300	0.8183
0.8013	21.0	46515	0.8171
0.7999	22.0	48730	0.8168
0.7982	23.0	50945	0.8152
0.7970	24.0	53160	0.8146
0.7955	25.0	55375	0.8144
0.7948	26.0	57590	0.8137
0.7932	27.0	59805	0.8134
0.7923	28.0	62020	0.8119
0.7910	29.0	64235	0.8116
0.7901	30.0	66450	0.8111
0.7894	31.0	68665	0.8099
0.7881	32.0	70880	0.8102
0.7874	33.0	73095	0.8102
0.7864	34.0	75310	0.8087
0.7858	35.0	77525	0.8086
0.7849	36.0	79740	0.8079
0.7840	37.0	81955	0.8083
0.7831	38.0	84170	0.8075
0.7825	39.0	86385	0.8080
0.7821	40.0	88600	0.8073
0.7813	41.0	90815	0.8074
0.7805	42.0	93030	0.8062
0.7796	43.0	95245	0.8067
0.7789	44.0	97460	0.8066
0.7783	45.0	99675	0.8062
0.7779	46.0	101890	0.8059
0.7770	47.0	104105	0.8061
0.7765	48.0	106320	0.8053
0.7760	49.0	108535	0.8053
0.7752	50.0	110750	0.8053
0.7746	51.0	112965	0.8052
0.7741	52.0	115180	0.8052
0.7733	53.0	117395	0.8050
0.7729	54.0	119610	0.8049
0.7720	55.0	121825	0.8048
0.7714	56.0	124040	0.8048
0.7705	57.0	126255	0.8044
0.7698	58.0	128470	0.8045
0.7690	59.0	130685	0.8045
0.7684	60.0	132900	0.8046
0.7675	61.0	135115	0.8047
0.7666	62.0	137330	0.8047
0.7657	63.0	139545	0.8048
0.7649	64.0	141760	0.8049

Framework versions

Transformers 5.12.0
Pytorch 2.12.0+cu130
Datasets 4.8.5
Tokenizers 0.22.2

Downloads last month: -

Safetensors

Model size

0.1B params

Tensor type

F32