You can deploy this model and start earning money today!

leonard-milo/
Qwen3.5-2B-SFT-AutoConv-InstagramChat-Smart

Name: Qwen3.5-2B-SFT-AutoConv-InstagramChat-Smart
Availability: InStock

Views

No views yet

Qwen3.5-2B-SFT-AutoConv-InstagramChat-Smart

A personalized conversational AI fine-tuned on Instagram chat history using SFT. Designed to generate style-consistent, multi-turn responses that mimic the user's conversational behavior.

This model follows the same training pipeline as Qwen3.5-2B-SFT-AutoConv-InstagramChat-Stupid, but achieves improved response quality and coherence.

Model Details

Model Description

Developed by: leonard-milo
Funded by: leonard-milo

Model type: Causal language model, conversational AI

License: [More Information Needed]
Finetuned from model: Qwen-3.5-2B

Model Sources

Repository: https://github.com/leonard-cs/Conversation-SFT/tree/main

Demo: https://huggingface.co/spaces/leonard-milo/LeonardGPT-chat

Uses

Direct Use

Generating personalized chat responses
Mimicking a specific conversational style for research or personal chatbot use
Multi-turn conversation modeling

Downstream Use

Integration into chatbots or digital assistants
Experimental research in style-consistent dialogue generation

Out-of-Scope Use

This model should not be used for public-facing automated messaging on social media without consent.
Not suitable for factual question answering, safety-critical tasks, or general-purpose LLM replacement.

Bias, Risks, and Limitations

Trained on a personal chat dataset, so output reflects only the user’s style.
Limited generalization outside the context of personal messaging.
May reproduce idiosyncrasies, slang, or informal expressions.
Risk of generating biased or offensive content inherent in informal personal chats.

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

python

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

MODEL_NAME = "leonard-milo/Qwen3.5-2B-SFT-AutoConv-InstagramChat-Smart"

tok = AutoTokenizer.from_pretrained(MODEL_NAME, device_map="auto")
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="auto")

messages = [
    {"role": "user", "content": "User message"},
]

tokenized_chat = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, return_tensors="pt")

inputs = tok(tokenized_chat, return_tensors="pt")
streamer = TextStreamer(tok)
_ = model.generate(**inputs, streamer=streamer)

Training Details

Training Data

Personal Instagram chat history exported via “Download Your Data”
Preprocessed to remove system messages, attachments, and irrelevant content
Formatted for multi-turn dialogue with clear role separation (Friend: / Me:)
Dataset includes ~32k cleaned message turns

Training Procedure

Preprocessing

Removed system messages, attachments, reactions.
Merged consecutive messages of mine (many to one)
Constructed conversation samples using a sliding window of 10 messages per conversation to preserve multi-turn context.
Converted conversations into a structured chat format:
python
1{ 2 "messages": [ 3 {"role": "user", "content": "..."}, 4 {"role": "assistant", "content": "..."} 5 ] 6}
Mapped roles:
- user → other participant (friend)
- assistant → target user (model persona)

Training Hyperparameters

Learning rate: 5e-5
Batch size: 8
epoch: 3

Environmental Impact

Hardware Type: Nvidia A30 (24GB)
Hours used: ~22 hours

Carbon Emitted: 0.67 kg Estimated using Machine Learning Impact calculator

Technical Specifications

Compute Infrastructure

Hardware

Nvidia A30 (24GB)

Model Card Authors

leonard-milo

Model Card Contact

leonard-milo