You can deploy this model and start earning money today!

RichardErkhov/
tanliboy_-_llama-3.2-3b-sft-2-gguf

Name: tanliboy_-_llama-3.2-3b-sft-2-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3.2-3b-sft-2 - GGUF

Model creator: https://huggingface.co/tanliboy/
Original model: https://huggingface.co/tanliboy/llama-3.2-3b-sft-2/

Name	Quant method	Size
llama-3.2-3b-sft-2.Q2_K.gguf	Q2_K	1.27GB
llama-3.2-3b-sft-2.IQ3_XS.gguf	IQ3_XS	1.38GB
llama-3.2-3b-sft-2.IQ3_S.gguf	IQ3_S	1.44GB
llama-3.2-3b-sft-2.Q3_K_S.gguf	Q3_K_S	1.44GB
llama-3.2-3b-sft-2.IQ3_M.gguf	IQ3_M	1.49GB
llama-3.2-3b-sft-2.Q3_K.gguf	Q3_K	1.57GB
llama-3.2-3b-sft-2.Q3_K_M.gguf	Q3_K_M	1.57GB
llama-3.2-3b-sft-2.Q3_K_L.gguf	Q3_K_L	1.69GB
llama-3.2-3b-sft-2.IQ4_XS.gguf	IQ4_XS	1.71GB
llama-3.2-3b-sft-2.Q4_0.gguf	Q4_0	1.79GB
llama-3.2-3b-sft-2.IQ4_NL.gguf	IQ4_NL	1.79GB
llama-3.2-3b-sft-2.Q4_K_S.gguf	Q4_K_S	1.8GB
llama-3.2-3b-sft-2.Q4_K.gguf	Q4_K	1.88GB
llama-3.2-3b-sft-2.Q4_K_M.gguf	Q4_K_M	1.88GB
llama-3.2-3b-sft-2.Q4_1.gguf	Q4_1	1.95GB
llama-3.2-3b-sft-2.Q5_0.gguf	Q5_0	2.11GB
llama-3.2-3b-sft-2.Q5_K_S.gguf	Q5_K_S	2.11GB
llama-3.2-3b-sft-2.Q5_K.gguf	Q5_K	2.16GB
llama-3.2-3b-sft-2.Q5_K_M.gguf	Q5_K_M	2.16GB
llama-3.2-3b-sft-2.Q5_1.gguf	Q5_1	2.28GB
llama-3.2-3b-sft-2.Q6_K.gguf	Q6_K	2.46GB
llama-3.2-3b-sft-2.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
generated_from_trainer datasets:
tanliboy/OpenHermes-2.5-reformat model-index:
name: llama-3.2-3b-sft-2 results: []

llama-3.2-3b-sft-2

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: 0.6744

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: 5e-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_steps: 1000
training_steps: 10000

Training results

Training Loss	Epoch	Step	Validation Loss
0.7792	0.0673	500	0.7726
0.7496	0.1345	1000	0.7444
0.7243	0.2018	1500	0.7296
0.7178	0.2691	2000	0.7197
0.7077	0.3363	2500	0.7127
0.6992	0.4036	3000	0.7066
0.6992	0.4708	3500	0.7012
0.6945	0.5381	4000	0.6965
0.6879	0.6054	4500	0.6920
0.6901	0.6726	5000	0.6879
0.6759	0.7399	5500	0.6844
0.6752	0.8072	6000	0.6812
0.6826	0.8744	6500	0.6783
0.6804	0.9417	7000	0.6758
0.6131	1.0089	7500	0.6764
0.6012	1.0762	8000	0.6758
0.6136	1.1435	8500	0.6751
0.6127	1.2107	9000	0.6747
0.6076	1.2780	9500	0.6745
0.6033	1.3453	10000	0.6744

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

RichardErkhov/tanliboy_-_llama-3.2-3b-sft-2-gguf

Original model description:

llama-3.2-3b-sft-2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
tanliboy_-_llama-3.2-3b-sft-2-gguf