terry69_-_llama3.2_feedback_3b-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
terry69_-_llama3.2_feedback_3b-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

llama3.2_feedback_3b - GGUF

Model creator: https://huggingface.co/terry69/
Original model: https://huggingface.co/terry69/llama3.2_feedback_3b/

Name	Quant method	Size
llama3.2_feedback_3b.Q2_K.gguf	Q2_K	1.27GB
llama3.2_feedback_3b.Q3_K_S.gguf	Q3_K_S	1.44GB
llama3.2_feedback_3b.Q3_K.gguf	Q3_K	1.57GB
llama3.2_feedback_3b.Q3_K_M.gguf	Q3_K_M	1.57GB
llama3.2_feedback_3b.Q3_K_L.gguf	Q3_K_L	1.69GB
llama3.2_feedback_3b.IQ4_XS.gguf	IQ4_XS	1.71GB
llama3.2_feedback_3b.Q4_0.gguf	Q4_0	1.79GB
llama3.2_feedback_3b.IQ4_NL.gguf	IQ4_NL	1.79GB
llama3.2_feedback_3b.Q4_K_S.gguf	Q4_K_S	1.8GB
llama3.2_feedback_3b.Q4_K.gguf	Q4_K	1.88GB
llama3.2_feedback_3b.Q4_K_M.gguf	Q4_K_M	1.88GB
llama3.2_feedback_3b.Q4_1.gguf	Q4_1	1.95GB
llama3.2_feedback_3b.Q5_0.gguf	Q5_0	2.11GB
llama3.2_feedback_3b.Q5_K_S.gguf	Q5_K_S	2.11GB
llama3.2_feedback_3b.Q5_K.gguf	Q5_K	2.16GB
llama3.2_feedback_3b.Q5_K_M.gguf	Q5_K_M	2.16GB
llama3.2_feedback_3b.Q5_1.gguf	Q5_1	2.28GB
llama3.2_feedback_3b.Q6_K.gguf	Q6_K	2.46GB
llama3.2_feedback_3b.Q8_0.gguf	Q8_0	3.19GB

Original model description:

library_name: transformers license: llama3.2 base_model: meta-llama/Llama-3.2-3B-Instruct tags:

alignment-handbook
trl
sft
generated_from_trainer
trl
sft
generated_from_trainer datasets:
preference-data model-index:
name: llama3.2_feedback_3b results: []

llama3.2_feedback_3b

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the preference-data dataset.

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: 4
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 16
total_eval_batch_size: 4
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

Framework versions

Transformers 4.45.1
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.0