Instructions to use EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
model = PeftModel.from_pretrained(base_model, "EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2")

Transformers

How to use EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2 with Transformers:

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

pipe = pipeline("text-generation", model="EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2

SGLang

How to use EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2 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 "EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2" \
    --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": "EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2",
		"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 "EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2" \
        --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": "EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2 with Docker Model Runner:
```
docker model run hf.co/EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2
```

Mistral-7B-v0.1-QLoRA-MathReasoning2

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3043

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: 2
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
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
lr_scheduler_warmup_steps: 50
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.3072	0.2667	100	0.3165
0.3151	0.5333	200	0.3099
0.3127	0.8	300	0.3046
0.2744	1.0667	400	0.3043
0.2518	1.3333	500	0.3068
0.2517	1.6	600	0.3058
0.2427	1.8667	700	0.3059
0.1853	2.1333	800	0.3269
0.1754	2.4	900	0.3293
0.1767	2.6667	1000	0.3328
0.1773	2.9333	1100	0.3314

Framework versions

PEFT 0.17.1
Transformers 4.57.0
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Downloads last month: 12

Model tree for EshAhm/Mistral-7B-v0.1-QLoRA-MathReasoning2

Base model

mistralai/Mistral-7B-v0.1

Adapter

(2465)

this model