Instructions to use twanghcmut/mistral-mixlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use twanghcmut/mistral-mixlora with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("twanghcmut/mistral-mixlora")
model = AutoModelForCausalLM.from_pretrained("twanghcmut/mistral-mixlora")
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 twanghcmut/mistral-mixlora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/twanghcmut/mistral-mixlora

SGLang

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

Docker Model Runner
How to use twanghcmut/mistral-mixlora with Docker Model Runner:
```
docker model run hf.co/twanghcmut/mistral-mixlora
```

mistral-mixlora

This model is a fine-tuned version of mistralai/Mistral-Nemo-Instruct-2407 on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.5970

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: 0.0002
train_batch_size: 32
eval_batch_size: 32
seed: 42
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: linear
lr_scheduler_warmup_steps: 100
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
1.7845	1.0	13	1.6758
1.6831	2.0	26	1.3898
1.3904	3.0	39	1.1781
1.1167	4.0	52	1.1148
1.0526	5.0	65	1.1112
1.0133	6.0	78	1.1350
0.8554	7.0	91	1.2262
0.7009	8.0	104	1.3168
0.5859	9.0	117	1.5106
0.3654	10.0	130	1.5970

Framework versions

Transformers 4.57.1
Pytorch 2.9.1+cu128
Datasets 4.4.1
Tokenizers 0.22.1

Downloads last month: 1

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for twanghcmut/mistral-mixlora

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

mistralai/Mistral-Nemo-Instruct-2407

Finetuned

(210)

this model