Instructions to use hllj/sft-mistral-v2-clean-valid with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hllj/sft-mistral-v2-clean-valid with Transformers:

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

pipe = pipeline("text-generation", model="hllj/sft-mistral-v2-clean-valid")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hllj/sft-mistral-v2-clean-valid")
model = AutoModelForCausalLM.from_pretrained("hllj/sft-mistral-v2-clean-valid")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hllj/sft-mistral-v2-clean-valid with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hllj/sft-mistral-v2-clean-valid"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hllj/sft-mistral-v2-clean-valid",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hllj/sft-mistral-v2-clean-valid

SGLang

How to use hllj/sft-mistral-v2-clean-valid 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 "hllj/sft-mistral-v2-clean-valid" \
    --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": "hllj/sft-mistral-v2-clean-valid",
		"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 "hllj/sft-mistral-v2-clean-valid" \
        --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": "hllj/sft-mistral-v2-clean-valid",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hllj/sft-mistral-v2-clean-valid with Docker Model Runner:
```
docker model run hf.co/hllj/sft-mistral-v2-clean-valid
```

sft-mistral-v2-clean-valid

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

Loss: 0.3176

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: 3e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.3163	0.23	500	0.4199
0.2988	1.02	1000	0.3697
0.2716	1.25	1500	0.3408

Framework versions

Transformers 4.35.2
Pytorch 2.1.0
Datasets 2.15.0
Tokenizers 0.15.0

Downloads last month: 3

Model tree for hllj/sft-mistral-v2-clean-valid

Base model

hllj/mistral-vi-math

Finetuned

(5)

this model