You can deploy this model and start earning money today!

RichardErkhov/
tongliuphysics_-_Llama0-3-8b-ultra-p-0.05-gguf

Name: tongliuphysics_-_Llama0-3-8b-ultra-p-0.05-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama0-3-8b-ultra-p-0.05 - GGUF

Model creator: https://huggingface.co/tongliuphysics/
Original model: https://huggingface.co/tongliuphysics/Llama0-3-8b-ultra-p-0.05/

Name	Quant method	Size
Llama0-3-8b-ultra-p-0.05.Q2_K.gguf	Q2_K	2.96GB
Llama0-3-8b-ultra-p-0.05.IQ3_XS.gguf	IQ3_XS	3.28GB
Llama0-3-8b-ultra-p-0.05.IQ3_S.gguf	IQ3_S	3.43GB
Llama0-3-8b-ultra-p-0.05.Q3_K_S.gguf	Q3_K_S	3.41GB
Llama0-3-8b-ultra-p-0.05.IQ3_M.gguf	IQ3_M	3.52GB
Llama0-3-8b-ultra-p-0.05.Q3_K.gguf	Q3_K	3.74GB
Llama0-3-8b-ultra-p-0.05.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama0-3-8b-ultra-p-0.05.Q3_K_L.gguf	Q3_K_L	4.03GB
Llama0-3-8b-ultra-p-0.05.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama0-3-8b-ultra-p-0.05.Q4_0.gguf	Q4_0	4.34GB
Llama0-3-8b-ultra-p-0.05.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama0-3-8b-ultra-p-0.05.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama0-3-8b-ultra-p-0.05.Q4_K.gguf	Q4_K	4.58GB
Llama0-3-8b-ultra-p-0.05.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama0-3-8b-ultra-p-0.05.Q4_1.gguf	Q4_1	4.78GB
Llama0-3-8b-ultra-p-0.05.Q5_0.gguf	Q5_0	5.21GB
Llama0-3-8b-ultra-p-0.05.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama0-3-8b-ultra-p-0.05.Q5_K.gguf	Q5_K	5.34GB
Llama0-3-8b-ultra-p-0.05.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama0-3-8b-ultra-p-0.05.Q5_1.gguf	Q5_1	5.65GB
Llama0-3-8b-ultra-p-0.05.Q6_K.gguf	Q6_K	6.14GB
Llama0-3-8b-ultra-p-0.05.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-ultra-p-0.05 results: []

Llama0-3-8b-ultra-p-0.05

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: 0.5203
Rewards/chosen: -0.9516
Rewards/rejected: -1.8713
Rewards/accuracies: 0.7344
Rewards/margins: 0.9197
Logps/rejected: -451.7943
Logps/chosen: -351.7126
Logits/rejected: 0.7305
Logits/chosen: 0.5934

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: 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: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.6104	0.2060	100	0.6071	-0.3701	-0.6034	0.6719	0.2333	-325.0017	-293.5632	0.3051	0.2437
0.5839	0.4119	200	0.5788	-0.4556	-0.8422	0.6875	0.3867	-348.8867	-302.1120	0.3006	0.2201
0.561	0.6179	300	0.5644	-0.5556	-1.0628	0.6953	0.5072	-370.9420	-312.1160	0.4520	0.3342
0.5489	0.8239	400	0.5474	-0.6136	-1.2310	0.7188	0.6174	-387.7600	-317.9102	0.5350	0.4135
0.5112	1.0299	500	0.5325	-0.8101	-1.5835	0.7344	0.7734	-423.0114	-337.5664	0.6096	0.4735
0.4577	1.2358	600	0.5291	-1.0553	-1.9636	0.7109	0.9083	-461.0272	-362.0868	0.7787	0.6411
0.4688	1.4418	700	0.5220	-0.9496	-1.8535	0.7266	0.9040	-450.0144	-351.5097	0.7421	0.6045
0.4684	1.6478	800	0.5194	-0.9894	-1.9115	0.7344	0.9221	-455.8119	-355.4933	0.7759	0.6367
0.4731	1.8538	900	0.5202	-0.9713	-1.9015	0.7344	0.9303	-454.8165	-353.6810	0.7319	0.5955

Framework versions

Transformers 4.45.1
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.20.0

RichardErkhov/tongliuphysics_-_Llama0-3-8b-ultra-p-0.05-gguf

Original model description:

Llama0-3-8b-ultra-p-0.05

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
tongliuphysics_-_Llama0-3-8b-ultra-p-0.05-gguf