You can deploy this model and start earning money today!

RichardErkhov/
savanladani_-_week2-llama3.2-1B-gguf

Name: savanladani_-_week2-llama3.2-1B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

week2-llama3.2-1B - GGUF

Model creator: https://huggingface.co/savanladani/
Original model: https://huggingface.co/savanladani/week2-llama3.2-1B/

Name	Quant method	Size
week2-llama3.2-1B.Q2_K.gguf	Q2_K	0.54GB
week2-llama3.2-1B.IQ3_XS.gguf	IQ3_XS	0.58GB
week2-llama3.2-1B.IQ3_S.gguf	IQ3_S	0.6GB
week2-llama3.2-1B.Q3_K_S.gguf	Q3_K_S	0.6GB
week2-llama3.2-1B.IQ3_M.gguf	IQ3_M	0.61GB
week2-llama3.2-1B.Q3_K.gguf	Q3_K	0.64GB
week2-llama3.2-1B.Q3_K_M.gguf	Q3_K_M	0.64GB
week2-llama3.2-1B.Q3_K_L.gguf	Q3_K_L	0.68GB
week2-llama3.2-1B.IQ4_XS.gguf	IQ4_XS	0.7GB
week2-llama3.2-1B.Q4_0.gguf	Q4_0	0.72GB
week2-llama3.2-1B.IQ4_NL.gguf	IQ4_NL	0.72GB
week2-llama3.2-1B.Q4_K_S.gguf	Q4_K_S	0.72GB
week2-llama3.2-1B.Q4_K.gguf	Q4_K	0.75GB
week2-llama3.2-1B.Q4_K_M.gguf	Q4_K_M	0.75GB
week2-llama3.2-1B.Q4_1.gguf	Q4_1	0.77GB
week2-llama3.2-1B.Q5_0.gguf	Q5_0	0.83GB
week2-llama3.2-1B.Q5_K_S.gguf	Q5_K_S	0.83GB
week2-llama3.2-1B.Q5_K.gguf	Q5_K	0.85GB
week2-llama3.2-1B.Q5_K_M.gguf	Q5_K_M	0.85GB
week2-llama3.2-1B.Q5_1.gguf	Q5_1	0.89GB
week2-llama3.2-1B.Q6_K.gguf	Q6_K	0.95GB
week2-llama3.2-1B.Q8_0.gguf	Q8_0	1.23GB

Original model description:

license: llama3.2 datasets:

mlabonne/orpo-dpo-mix-40k language:
en base_model:
meta-llama/Llama-3.2-1B library_name: transformers pipeline_tag: text-generation model-index:
name: week2-llama3-1B results:
- task: type: text-generation dataset: name: mlabonne/orpo-dpo-mix-40k type: mlabonne/orpo-dpo-mix-40k metrics:
  - name: EQ-Bench (0-Shot) type: EQ-Bench (0-Shot) value: 1.5355

Model Overview

This model is a fine-tuned variant of Llama-3.2-1B, leveraging ORPO (Optimized Regularization for Prompt Optimization) for enhanced performance. It has been fine-tuned using the mlabonne/orpo-dpo-mix-40k dataset as part of the Finetuning Open Source LLMs Course - Week 2 Project.

Intended Use

This model is optimized for general-purpose language tasks, including text parsing, understanding contextual prompts, and enhanced interpretability in natural language processing applications.

Evaluation Results

The model was evaluated on the following benchmarks, with the following performance metrics:

Tasks	Version	Filter	Metric		Value		Stderr
eq_bench	2.1	none	eqbench	↑	1.5355	±	0.9174
		none	percent_parseable	↑	16.9591	±	2.8782
hellaswag	1	none	acc	↑	0.4812	±	0.0050
		none	acc_norm	↑	0.6467	±	0.0048
ifeval	4	none	inst_level_loose_acc	↑	0.3993	±	N/A
		none	inst_level_strict_acc	↑	0.2974	±	N/A
		none	prompt_level_loose_acc	↑	0.2754	±	0.0192
		none	prompt_level_strict_acc	↑	0.1848	±	0.0167
tinyMMLU	0	none	acc_norm	↑	0.3996	±	N/A

Key Features

Model Size: 1 Billion parameters
Fine-tuning Method: ORPO
Dataset: mlabonne/orpo-dpo-mix-40k

RichardErkhov/savanladani_-_week2-llama3.2-1B-gguf