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

Libraries

How to use LBenoit/MyMistralEUClassifier with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
model = PeftModel.from_pretrained(base_model, "LBenoit/MyMistralEUClassifier")

Transformers

How to use LBenoit/MyMistralEUClassifier with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("LBenoit/MyMistralEUClassifier", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LBenoit/MyMistralEUClassifier with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/LBenoit/MyMistralEUClassifier

SGLang

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

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

MyMistralEUClassifier

File size: 1,926 Bytes

b57feef

{
  "best_global_step": 50,
  "best_metric": 0.4482579529285431,
  "best_model_checkpoint": "/content/drive/MyDrive/FDG/fine_tuned_model/checkpoint-50",
  "epoch": 2.1758241758241756,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 1.8231751918792725,
      "learning_rate": 8.695652173913044e-05,
      "loss": 1.0735,
      "step": 10
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 0.6162029504776001,
      "learning_rate": 7.246376811594203e-05,
      "loss": 0.507,
      "step": 20
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.5667868256568909,
      "learning_rate": 5.797101449275363e-05,
      "loss": 0.4857,
      "step": 30
    },
    {
      "epoch": 1.7472527472527473,
      "grad_norm": 0.7305045127868652,
      "learning_rate": 4.347826086956522e-05,
      "loss": 0.4648,
      "step": 40
    },
    {
      "epoch": 2.1758241758241756,
      "grad_norm": 0.6166667342185974,
      "learning_rate": 2.8985507246376814e-05,
      "loss": 0.4168,
      "step": 50
    },
    {
      "epoch": 2.1758241758241756,
      "eval_loss": 0.4482579529285431,
      "eval_runtime": 21.3432,
      "eval_samples_per_second": 1.921,
      "eval_steps_per_second": 0.515,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 69,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7322178882043904e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}