metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - mistral
  - trl
  - sft
base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit

Model Specifications

Max Sequence Length: 16384 (with auto support for RoPE Scaling)
Data Type: Auto detection, with options for Float16 and Bfloat16
Quantization: 4bit, to reduce memory usage

Training Data

Used a private dataset with hundreds of technical tutorials and associated summaries.

Implementation Highlights

Efficiency: Emphasis on reducing memory usage and accelerating download speeds through 4bit quantization.
Adaptability: Auto detection of data types and support for advanced configuration options like RoPE scaling, LoRA, and gradient checkpointing.

Uploaded Model

Developed by: ndebuhr
License: apache-2.0
Finetuned from model : unsloth/mistral-7b-instruct-v0.2-bnb-4bit

Configuration and Usage

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import torch

input_text = ""

# Set device based on CUDA availability
device = "cuda" if torch.cuda.is_available() else "cpu"

# Load the model and tokenizer
model_name = "ndebuhr/Mistral-7B-Technical-Tutorial-Summarization-QLoRA"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name).to(device)

instruction = "Clarify and summarize this tutorial transcript"
prompt = """{}

### Raw Transcript:
{}

### Summary:
"""

# Tokenize the input text
inputs = tokenizer(
    prompt.format(instruction, input_text),
    return_tensors="pt",
    truncation=True,
    max_length=16384
).to(device)

# Generate outputs
outputs = model.generate(
    **inputs,
    max_length=16384,
    num_return_sequences=1,
    use_cache=True
)

# Decode the generated text
generated_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)

Compute Infrastructure

Fine-tuning: used 1xA100 (40GB)
Inference: recommend 1xL4 (24GB)

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.