cjoslin22/ Finetuned_Mistral-7.2B-Q8_0:latest

36 Downloads Updated 11 months ago

This model summarizes High Performance Computing (HPC) support tickets using a structured format.

ollama run cjoslin22/Finetuned_Mistral-7.2B-Q8_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "cjoslin22/Finetuned_Mistral-7.2B-Q8_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='cjoslin22/Finetuned_Mistral-7.2B-Q8_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'cjoslin22/Finetuned_Mistral-7.2B-Q8_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 11 months ago

11 months ago

5582f39c6edf · 7.7GB ·

model

archllama

·

parameters7.25B

·

quantizationQ8_0

7.7GB

Readme

Finetuned Mistral-7B Ticket Summarizer

This model is a fine-tuned version of Mistral-7B Instruct v3, designed to clean and concisely summarize structured support ticket entries. Each output follows a strict, two-part format:

Issue Summary: A brief overview of the user-reported issue
Resolution: A concise description of the support team’s response

Key Features

Consistent formatting for downstream automation (e.g., clustering, FAQ generation)
Low hallucination rate through role-based prompt tuning
Lightweight deployment enabled by 8-bit quantization (Q8_0)
Instruction-following fine-tuning via LoRA adapters

Prompt Format

The model was fine-tuned using a role-based instruction prompt designed to enforce strict summarization structure:

Deployment Options

Ollama (Local Deployment) Run the quantized model locally
GenAI Studio API (Hosted Access) This model is accessible via Purdue’s GenAI Studio for programmatic summarization.
HuggingFace Model weights available at cjoslin22/hpc-ticket/summarizer/mistral7b (private repository)

Intended Use

This model is intended for structured summarization of internal or enterprise-level support tickets, where brevity, consistency, and format control are essential.

It is not intended for open-ended conversation, creative generation, or use with unfiltered or public-facing content

Author

Christina Joslin RCAC Intern, June 2025

# Finetuned Mistral-7B Ticket Summarizer

This model is a fine-tuned version of **Mistral-7B Instruct v3**, designed to clean and concisely summarize structured support ticket entries. Each output follows a strict, two-part format:

1. **Issue Summary**:  A brief overview of the user-reported issue  
2. **Resolution**:  A concise description of the support team’s response

---

## Key Features

- **Consistent formatting** for downstream automation (e.g., clustering, FAQ generation)  
- **Low hallucination rate** through role-based prompt tuning  
- **Lightweight deployment** enabled by 8-bit quantization (Q8_0)  
- **Instruction-following** fine-tuning via LoRA adapters

---

## Prompt Format

The model was fine-tuned using a role-based instruction prompt designed to enforce strict summarization structure:

![Ticket Summarization Prompt.png](/assets/cjoslin22/Finetuned_Mistral-7.2B-Q8_0/74a993f7-cd4b-4061-9135-adeabc921729)

---

## Deployment Options

- **Ollama** (Local Deployment) Run the quantized model locally 
- **GenAI Studio API** (Hosted Access) This model is accessible via Purdue's GenAI Studio for programmatic summarization. 
- **HuggingFace** Model weights available at `cjoslin22/hpc-ticket/summarizer/mistral7b` *(private repository)*

---

## Intended Use

This model is intended for **structured summarization** of internal or enterprise-level support tickets, where **brevity, consistency**, and **format control** are essential.

It is **not intended** for open-ended conversation, creative generation, or use with unfiltered or public-facing content

---

## Author 
Christina Joslin 
RCAC Intern, June 2025

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)