You can deploy this model and start earning money today!

RichardErkhov/
jbjeong91_-_llama3.1-cpo_j-full-0911-gguf

Name: jbjeong91_-_llama3.1-cpo_j-full-0911-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama3.1-cpo_j-full-0911 - GGUF

Model creator: https://huggingface.co/jbjeong91/
Original model: https://huggingface.co/jbjeong91/llama3.1-cpo_j-full-0911/

Name	Quant method	Size
llama3.1-cpo_j-full-0911.Q2_K.gguf	Q2_K	2.96GB
llama3.1-cpo_j-full-0911.IQ3_XS.gguf	IQ3_XS	3.28GB
llama3.1-cpo_j-full-0911.IQ3_S.gguf	IQ3_S	3.43GB
llama3.1-cpo_j-full-0911.Q3_K_S.gguf	Q3_K_S	3.41GB
llama3.1-cpo_j-full-0911.IQ3_M.gguf	IQ3_M	3.52GB
llama3.1-cpo_j-full-0911.Q3_K.gguf	Q3_K	3.74GB
llama3.1-cpo_j-full-0911.Q3_K_M.gguf	Q3_K_M	3.74GB
llama3.1-cpo_j-full-0911.Q3_K_L.gguf	Q3_K_L	4.03GB
llama3.1-cpo_j-full-0911.IQ4_XS.gguf	IQ4_XS	4.18GB
llama3.1-cpo_j-full-0911.Q4_0.gguf	Q4_0	4.34GB
llama3.1-cpo_j-full-0911.IQ4_NL.gguf	IQ4_NL	4.38GB
llama3.1-cpo_j-full-0911.Q4_K_S.gguf	Q4_K_S	4.37GB
llama3.1-cpo_j-full-0911.Q4_K.gguf	Q4_K	4.58GB
llama3.1-cpo_j-full-0911.Q4_K_M.gguf	Q4_K_M	4.58GB
llama3.1-cpo_j-full-0911.Q4_1.gguf	Q4_1	4.78GB
llama3.1-cpo_j-full-0911.Q5_0.gguf	Q5_0	5.21GB
llama3.1-cpo_j-full-0911.Q5_K_S.gguf	Q5_K_S	5.21GB
llama3.1-cpo_j-full-0911.Q5_K.gguf	Q5_K	5.34GB
llama3.1-cpo_j-full-0911.Q5_K_M.gguf	Q5_K_M	5.34GB
llama3.1-cpo_j-full-0911.Q5_1.gguf	Q5_1	5.65GB
llama3.1-cpo_j-full-0911.Q6_K.gguf	Q6_K	6.14GB
llama3.1-cpo_j-full-0911.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
cpo
generated_from_trainer
trl
cpo
generated_from_trainer datasets:
princeton-nlp/llama3-ultrafeedback model-index:
name: llama3.1-cpo_j-full-0911 results: []

llama3.1-cpo_j-full-0911

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the princeton-nlp/llama3-ultrafeedback dataset. It achieves the following results on the evaluation set:

Loss: 1.4373
Rewards/chosen: -14.1493
Rewards/rejected: -15.5710
Rewards/accuracies: 0.6543
Rewards/margins: 1.4217
Logps/rejected: -155.7095
Logps/chosen: -141.4926
Logits/rejected: -0.1136
Logits/chosen: -0.1476
Nll Loss: 0.1725

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-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen	Nll Loss
1.4367	0.9986	432	1.3926	-17.0679	-18.0962	0.6565	1.0283	-180.9624	-170.6792	-0.4080	-0.4373	0.3200
0.5472	1.9994	865	1.2973	-16.2909	-17.5852	0.6587	1.2944	-175.8523	-162.9086	-0.5434	-0.5688	0.2148
0.2244	2.9980	1297	1.3861	-15.7105	-17.2195	0.6565	1.5089	-172.1945	-157.1052	-0.3428	-0.3715	0.2034
0.1472	3.9988	1730	1.4029	-14.6462	-16.1385	0.6522	1.4923	-161.3849	-146.4623	-0.2701	-0.3029	0.1876
0.1143	4.9928	2160	1.4373	-14.1493	-15.5710	0.6543	1.4217	-155.7095	-141.4926	-0.1136	-0.1476	0.1725

Framework versions

Transformers 4.44.2
Pytorch 2.3.1
Datasets 2.21.0
Tokenizers 0.19.1

RichardErkhov/jbjeong91_-_llama3.1-cpo_j-full-0911-gguf

Original model description:

llama3.1-cpo_j-full-0911

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
jbjeong91_-_llama3.1-cpo_j-full-0911-gguf