simonycl_-_llama-3-8b-instruct-single-judge-gguf

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

simonycl_-_llama-3-8b-instruct-single-judge-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

Downloads · 30 days

122

4% of all-time downloads

All-time downloads

2.9K

Public

Repo size

92.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf108 GB · 100%

At a glance

Access: Public
Created: Sep 24, 2024
Updated: Sep 24, 2024
SHA: 24bcb828

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

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

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

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

llama-3-8b-instruct-single-judge

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

Loss: 0.6593
Rewards/chosen: -1.3185
Rewards/rejected: -1.5107
Rewards/accuracies: 0.5935
Rewards/margins: 0.1922
Logps/rejected: -301.4192
Logps/chosen: -283.3882
Logits/rejected: -1.3226
Logits/chosen: -1.3593

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: 2
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 32
total_train_batch_size: 128
total_eval_batch_size: 8
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
0.5714	0.8528	400	0.6593	-1.3185	-1.5107	0.5935	0.1922	-301.4192	-283.3882	-1.3226	-1.3593

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Created: Sep 24, 2024
Updated: Sep 24, 2024