tanliboy_-_llama-3.2-3b-sft-gguf

RichardErkhov/tanliboy_-_llama-3.2-3b-sft-gguf

tanliboy_-_llama-3.2-3b-sft-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

4% of all-time downloads

All-time downloads

1.3K

Public

Repo size

38.1 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf44.2 GB · 100%

At a glance

Access: Public
Created: Oct 2, 2024
Updated: Oct 2, 2024
SHA: fa0d9d7e

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3.2-3b-sft - GGUF

Model creator: https://huggingface.co/tanliboy/
Original model: https://huggingface.co/tanliboy/llama-3.2-3b-sft/

Name	Quant method	Size
llama-3.2-3b-sft.Q2_K.gguf	Q2_K	1.27GB
llama-3.2-3b-sft.IQ3_XS.gguf	IQ3_XS	1.38GB
llama-3.2-3b-sft.IQ3_S.gguf	IQ3_S	1.44GB
llama-3.2-3b-sft.Q3_K_S.gguf	Q3_K_S	1.44GB
llama-3.2-3b-sft.IQ3_M.gguf	IQ3_M	1.49GB
llama-3.2-3b-sft.Q3_K.gguf	Q3_K	1.57GB
llama-3.2-3b-sft.Q3_K_M.gguf	Q3_K_M	1.57GB
llama-3.2-3b-sft.Q3_K_L.gguf	Q3_K_L	1.69GB
llama-3.2-3b-sft.IQ4_XS.gguf	IQ4_XS	1.71GB
llama-3.2-3b-sft.Q4_0.gguf	Q4_0	1.79GB
llama-3.2-3b-sft.IQ4_NL.gguf	IQ4_NL	1.79GB
llama-3.2-3b-sft.Q4_K_S.gguf	Q4_K_S	1.8GB
llama-3.2-3b-sft.Q4_K.gguf	Q4_K	1.88GB
llama-3.2-3b-sft.Q4_K_M.gguf	Q4_K_M	1.88GB
llama-3.2-3b-sft.Q4_1.gguf	Q4_1	1.95GB
llama-3.2-3b-sft.Q5_0.gguf	Q5_0	2.11GB
llama-3.2-3b-sft.Q5_K_S.gguf	Q5_K_S	2.11GB
llama-3.2-3b-sft.Q5_K.gguf	Q5_K	2.16GB
llama-3.2-3b-sft.Q5_K_M.gguf	Q5_K_M	2.16GB
llama-3.2-3b-sft.Q5_1.gguf	Q5_1	2.28GB
llama-3.2-3b-sft.Q6_K.gguf	Q6_K	2.46GB
llama-3.2-3b-sft.Q8_0.gguf	Q8_0	3.19GB

Original model description:

library_name: transformers license: llama3.2 base_model: tanliboy/llama-3.2-3b tags:

alignment-handbook
trl
sft
generated_from_trainer
trl
sft
alignment-handbook
generated_from_trainer datasets:
tanliboy/OpenHermes-2.5-reformat model-index:
name: llama-3.2-3b-sft results: []

llama-3.2-3b-sft

This model is a fine-tuned version of tanliboy/llama-3.2-3b on the tanliboy/OpenHermes-2.5-reformat dataset. It achieves the following results on the evaluation set:

Loss: 0.7216

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: 3e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 128
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.8741	0.0448	100	0.8600
0.8038	0.0897	200	0.8095
0.7937	0.1345	300	0.7789
0.7712	0.1794	400	0.7644
0.7393	0.2242	500	0.7565
0.7458	0.2691	600	0.7506
0.7694	0.3139	700	0.7458
0.713	0.3587	800	0.7422
0.7347	0.4036	900	0.7387
0.7243	0.4484	1000	0.7356
0.7161	0.4933	1100	0.7331
0.7247	0.5381	1200	0.7308
0.7477	0.5830	1300	0.7288
0.7429	0.6278	1400	0.7273
0.7317	0.6726	1500	0.7256
0.7226	0.7175	1600	0.7243
0.695	0.7623	1700	0.7234
0.7167	0.8072	1800	0.7226
0.686	0.8520	1900	0.7221
0.7214	0.8969	2000	0.7218
0.7358	0.9417	2100	0.7216
0.7259	0.9865	2200	0.7216

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Created: Oct 2, 2024
Updated: Oct 2, 2024