barc0_-_Llama-3.1-ARC-Heavy-Transduction-8B-gguf

RichardErkhov/barc0_-_Llama-3.1-ARC-Heavy-Transduction-8B-gguf

barc0_-_Llama-3.1-ARC-Heavy-Transduction-8B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

Downloads · 30 days

3% of all-time downloads

All-time downloads

1.6K

Public

Repo size

81.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf96.6 GB · 100%

At a glance

Access: Public
Created: Nov 13, 2024
Updated: Nov 13, 2024
SHA: b217428a

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.1-ARC-Heavy-Transduction-8B - GGUF

Model creator: https://huggingface.co/barc0/
Original model: https://huggingface.co/barc0/Llama-3.1-ARC-Heavy-Transduction-8B/

Name	Quant method	Size
Llama-3.1-ARC-Heavy-Transduction-8B.Q2_K.gguf	Q2_K	2.96GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q3_K.gguf	Q3_K	3.74GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
Llama-3.1-ARC-Heavy-Transduction-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q4_0.gguf	Q4_0	4.34GB
Llama-3.1-ARC-Heavy-Transduction-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q4_K.gguf	Q4_K	4.58GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q4_1.gguf	Q4_1	4.78GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q5_0.gguf	Q5_0	5.21GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q5_K.gguf	Q5_K	5.34GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q5_1.gguf	Q5_1	5.65GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q6_K.gguf	Q6_K	6.14GB
Llama-3.1-ARC-Heavy-Transduction-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers license: llama3.1 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct tags:

alignment-handbook
trl
sft
generated_from_trainer
trl
sft
generated_from_trainer datasets:
barc0/transduction_heavy_100k_jsonl
barc0/transduction_heavy_suggestfunction_100k_jsonl model-index:
name: heavy-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3 results: []

heavy-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the barc0/transduction_heavy_100k_jsonl and the barc0/transduction_heavy_suggestfunction_100k_jsonl datasets. It achieves the following results on the evaluation set:

Loss: 0.0319

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 128
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.0446	1.0	1478	0.0433
0.0229	2.0	2956	0.0323
0.014	3.0	4434	0.0319

Framework versions

Transformers 4.45.0.dev0
Pytorch 2.4.0+cu121
Datasets 3.0.2
Tokenizers 0.19.1

Created: Nov 13, 2024
Updated: Nov 13, 2024