RichardErkhov/ndebuhr_-_Mistral-7B-Technical-Tutorial-Summarization-QLoRA-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-7B-Technical-Tutorial-Summarization-QLoRA - GGUF

• Model creator: https://huggingface.co/ndebuhr/
• Original model: https://huggingface.co/ndebuhr/Mistral-7B-Technical-Tutorial-Summarization-QLoRA/

Name	Quant method	Size
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q2_K.gguf	Q2_K	2.53GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.IQ3_XS.gguf	IQ3_XS	2.81GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.IQ3_S.gguf	IQ3_S	2.96GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q3_K_S.gguf	Q3_K_S	2.95GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q3_K.gguf	Q3_K	3.28GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q3_K_M.gguf	Q3_K_M	3.28GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q3_K_L.gguf	Q3_K_L	3.56GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q4_0.gguf	Q4_0	3.83GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.IQ4_NL.gguf	IQ4_NL	3.87GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q4_K_S.gguf	Q4_K_S	3.86GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q4_K.gguf	Q4_K	4.07GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q4_K_M.gguf	Q4_K_M	4.07GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q4_1.gguf	Q4_1	4.24GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q5_0.gguf	Q5_0	4.65GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q5_K_S.gguf	Q5_K_S	4.65GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q5_K.gguf	Q5_K	4.78GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q5_K_M.gguf	Q5_K_M	4.78GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q5_1.gguf	Q5_1	5.07GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q6_K.gguf	Q6_K	5.53GB
Mistral-7B-Technical-Tutorial-Summarization-QLoRA.Q8_0.gguf	Q8_0	7.17GB

Original model description:

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.