Instructions to use hbin0701/Mistral_VStar_iter1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hbin0701/Mistral_VStar_iter1 with Transformers:

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

pipe = pipeline("text-generation", model="hbin0701/Mistral_VStar_iter1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hbin0701/Mistral_VStar_iter1")
model = AutoModelForCausalLM.from_pretrained("hbin0701/Mistral_VStar_iter1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hbin0701/Mistral_VStar_iter1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hbin0701/Mistral_VStar_iter1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hbin0701/Mistral_VStar_iter1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hbin0701/Mistral_VStar_iter1

SGLang

How to use hbin0701/Mistral_VStar_iter1 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 "hbin0701/Mistral_VStar_iter1" \
    --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": "hbin0701/Mistral_VStar_iter1",
		"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 "hbin0701/Mistral_VStar_iter1" \
        --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": "hbin0701/Mistral_VStar_iter1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hbin0701/Mistral_VStar_iter1 with Docker Model Runner:
```
docker model run hf.co/hbin0701/Mistral_VStar_iter1
```

mistral_7b_gsm8k_ep2_1e-5_dpo

This model is a fine-tuned version of /home/hyeonbin/self_train/Verifiers/models/mistral_7b_gsm8k_ep2_1e-5_rft_round1 on the GSM8K Train Set. It achieves the following results on the evaluation set (=GSM8K Train subset):

Loss: 0.0005
Rewards/chosen: -1.7120
Rewards/rejected: -14.3548
Rewards/accuracies: 1.0
Rewards/margins: 12.6428
Logps/rejected: -1466.6733
Logps/chosen: -208.2280
Logits/rejected: -3.2168
Logits/chosen: -2.3996

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: 1e-07
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.014	1.0	7066	0.0005	-1.7120	-14.3548	1.0	12.6428	-1466.6733	-208.2280	-3.2168	-2.3996

Framework versions

Transformers 4.41.0
Pytorch 2.3.0+cu121
Datasets 2.14.6
Tokenizers 0.19.1

Downloads last month: 6

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for hbin0701/Mistral_VStar_iter1

Base model

mistralai/Mistral-7B-v0.1

Finetuned

(1033)

this model

hbin0701
/

Mistral_VStar_iter1

mistral_7b_gsm8k_ep2_1e-5_dpo

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for hbin0701/Mistral_VStar_iter1

Dataset used to train hbin0701/Mistral_VStar_iter1