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

Libraries

How to use iamnotpalak/mistral-qlora-banking with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("iamnotpalak/mistral-qlora-banking", dtype="auto")

PEFT
How to use iamnotpalak/mistral-qlora-banking with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use iamnotpalak/mistral-qlora-banking with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/iamnotpalak/mistral-qlora-banking

SGLang

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

Docker Model Runner
How to use iamnotpalak/mistral-qlora-banking with Docker Model Runner:
```
docker model run hf.co/iamnotpalak/mistral-qlora-banking
```

Mistral-7B QLoRA Fine-Tuned (Retail Banking Chatbot)

Overview

This model is a fine-tuned version of Mistral-7B using QLoRA for domain-specific conversational tasks in retail banking.

Model Details

Base Model: mistralai/Mistral-7B
Fine-tuning Method: QLoRA (4-bit NF4 quantization)
Framework: Hugging Face Transformers + PEFT
Task: Banking chatbot / conversational QA

Training

Dataset: Custom retail banking dataset
Approach: Parameter-Efficient Fine-Tuning (PEFT)
Objective: Improve domain-specific response generation

Evaluation

ROUGE-1: 0.47
ROUGE-L: 0.34
BLEU: 0.11

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

model_id = "iamnotpalak/mistral-qlora-banking"

tokenizer = AutoTokenizer.from_pretrained(model_id)
base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B")

model = PeftModel.from_pretrained(base_model, model_id)

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for iamnotpalak/mistral-qlora-banking

Base model

mistralai/Mistral-7B-v0.3

Finetuned

mistralai/Mistral-7B-Instruct-v0.3

Finetuned

(489)

this model

iamnotpalak
/

mistral-qlora-banking