You can deploy this model and start earning money today!

RichardErkhov/
simonycl_-_llama-3-8b-instruct-armorm-judge-gguf

Name: simonycl_-_llama-3-8b-instruct-armorm-judge-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3-8b-instruct-armorm-judge - GGUF

Model creator: https://huggingface.co/simonycl/
Original model: https://huggingface.co/simonycl/llama-3-8b-instruct-armorm-judge/

Name	Quant method	Size
llama-3-8b-instruct-armorm-judge.Q2_K.gguf	Q2_K	2.96GB
llama-3-8b-instruct-armorm-judge.IQ3_XS.gguf	IQ3_XS	3.28GB
llama-3-8b-instruct-armorm-judge.IQ3_S.gguf	IQ3_S	3.43GB
llama-3-8b-instruct-armorm-judge.Q3_K_S.gguf	Q3_K_S	3.41GB
llama-3-8b-instruct-armorm-judge.IQ3_M.gguf	IQ3_M	3.52GB
llama-3-8b-instruct-armorm-judge.Q3_K.gguf	Q3_K	3.74GB
llama-3-8b-instruct-armorm-judge.Q3_K_M.gguf	Q3_K_M	3.74GB
llama-3-8b-instruct-armorm-judge.Q3_K_L.gguf	Q3_K_L	4.03GB
llama-3-8b-instruct-armorm-judge.IQ4_XS.gguf	IQ4_XS	4.18GB
llama-3-8b-instruct-armorm-judge.Q4_0.gguf	Q4_0	4.34GB
llama-3-8b-instruct-armorm-judge.IQ4_NL.gguf	IQ4_NL	4.38GB
llama-3-8b-instruct-armorm-judge.Q4_K_S.gguf	Q4_K_S	4.37GB
llama-3-8b-instruct-armorm-judge.Q4_K.gguf	Q4_K	4.58GB
llama-3-8b-instruct-armorm-judge.Q4_K_M.gguf	Q4_K_M	4.58GB
llama-3-8b-instruct-armorm-judge.Q4_1.gguf	Q4_1	4.78GB
llama-3-8b-instruct-armorm-judge.Q5_0.gguf	Q5_0	5.21GB
llama-3-8b-instruct-armorm-judge.Q5_K_S.gguf	Q5_K_S	5.21GB
llama-3-8b-instruct-armorm-judge.Q5_K.gguf	Q5_K	5.34GB
llama-3-8b-instruct-armorm-judge.Q5_K_M.gguf	Q5_K_M	5.34GB
llama-3-8b-instruct-armorm-judge.Q5_1.gguf	Q5_1	5.65GB
llama-3-8b-instruct-armorm-judge.Q6_K.gguf	Q6_K	6.14GB
llama-3-8b-instruct-armorm-judge.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:

alignment-handbook
generated_from_trainer datasets:
simonycl/Llama-3-8B-Instruct-ultrafeedback-armorm-annotate model-index:
name: llama-3-8b-instruct-armorm-judge results: []

llama-3-8b-instruct-armorm-judge

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

Loss: 0.4834
Rewards/chosen: -2.9573
Rewards/rejected: -4.4536
Rewards/accuracies: 0.7760
Rewards/margins: 1.4963
Logps/rejected: -597.7948
Logps/chosen: -448.3257
Logits/rejected: -0.6484
Logits/chosen: -0.6989

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-07
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 32
total_train_batch_size: 128
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

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.5062	0.8529	400	0.4834	-2.9573	-4.4536	0.7760	1.4963	-597.7948	-448.3257	-0.6484	-0.6989

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

RichardErkhov/simonycl_-_llama-3-8b-instruct-armorm-judge-gguf

Original model description:

llama-3-8b-instruct-armorm-judge

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
simonycl_-_llama-3-8b-instruct-armorm-judge-gguf