You can deploy this model and start earning money today!

RichardErkhov/
tongliuphysics_-_Llama0-3-8b-v0.1-p-2-lr5e-6-e1-gguf

Name: tongliuphysics_-_Llama0-3-8b-v0.1-p-2-lr5e-6-e1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama0-3-8b-v0.1-p-2-lr5e-6-e1 - GGUF

Model creator: https://huggingface.co/tongliuphysics/
Original model: https://huggingface.co/tongliuphysics/Llama0-3-8b-v0.1-p-2-lr5e-6-e1/

Name	Quant method	Size
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q2_K.gguf	Q2_K	2.96GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.IQ3_XS.gguf	IQ3_XS	3.28GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.IQ3_S.gguf	IQ3_S	3.43GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q3_K_S.gguf	Q3_K_S	3.41GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.IQ3_M.gguf	IQ3_M	3.52GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q3_K.gguf	Q3_K	3.74GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q3_K_L.gguf	Q3_K_L	4.03GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q4_0.gguf	Q4_0	4.34GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q4_K.gguf	Q4_K	4.58GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q4_1.gguf	Q4_1	4.78GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q5_0.gguf	Q5_0	5.21GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q5_K.gguf	Q5_K	5.34GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q5_1.gguf	Q5_1	5.65GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q6_K.gguf	Q6_K	6.14GB
Llama0-3-8b-v0.1-p-2-lr5e-6-e1.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers license: llama3 base_model: meta-llama/Meta-Llama-3-8B-Instruct tags:

trl
dpo
generated_from_trainer model-index:
name: Llama0-3-8b-v0.1-p-2-lr5e-6-e1 results: []

Llama0-3-8b-v0.1-p-2-lr5e-6-e1

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0071
Rewards/chosen: -325.0106
Rewards/rejected: -326.4964
Rewards/accuracies: 0.4839
Rewards/margins: 1.4858
Logps/rejected: -32736.4023
Logps/chosen: -32589.3574
Logits/rejected: 15.2095
Logits/chosen: 15.1707

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: 2
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
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: linear
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.0157	0.2137	100	0.0113	-210.0611	-211.0992	0.4597	1.0381	-21196.6719	-21094.4004	13.2797	13.2492
0.0103	0.4275	200	0.0100	-295.4855	-293.2994	0.5081	-2.1861	-29416.6973	-29636.8457	14.5637	14.5474
0.0074	0.6412	300	0.0081	-286.9739	-284.4362	0.4718	-2.5377	-28530.3730	-28785.6816	14.5532	14.6383
0.0061	0.8549	400	0.0073	-253.9528	-254.9697	0.5040	1.0169	-25583.7266	-25483.5762	13.4697	13.4536

Framework versions

Transformers 4.45.1
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.20.0

RichardErkhov/tongliuphysics_-_Llama0-3-8b-v0.1-p-2-lr5e-6-e1-gguf

Original model description:

Llama0-3-8b-v0.1-p-2-lr5e-6-e1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
tongliuphysics_-_Llama0-3-8b-v0.1-p-2-lr5e-6-e1-gguf