You can deploy this model and start earning money today!

RichardErkhov/
OpenLeecher_-_llama_8b_lima_10-gguf

Name: OpenLeecher_-_llama_8b_lima_10-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama_8b_lima_10 - GGUF

Model creator: https://huggingface.co/OpenLeecher/
Original model: https://huggingface.co/OpenLeecher/llama_8b_lima_10/

Name	Quant method	Size
llama_8b_lima_10.Q2_K.gguf	Q2_K	2.96GB
llama_8b_lima_10.IQ3_XS.gguf	IQ3_XS	3.28GB
llama_8b_lima_10.IQ3_S.gguf	IQ3_S	3.43GB
llama_8b_lima_10.Q3_K_S.gguf	Q3_K_S	3.41GB
llama_8b_lima_10.IQ3_M.gguf	IQ3_M	3.52GB
llama_8b_lima_10.Q3_K.gguf	Q3_K	2.33GB
llama_8b_lima_10.Q3_K_M.gguf	Q3_K_M	3.74GB
llama_8b_lima_10.Q3_K_L.gguf	Q3_K_L	4.03GB
llama_8b_lima_10.IQ4_XS.gguf	IQ4_XS	4.18GB
llama_8b_lima_10.Q4_0.gguf	Q4_0	4.34GB
llama_8b_lima_10.IQ4_NL.gguf	IQ4_NL	4.38GB
llama_8b_lima_10.Q4_K_S.gguf	Q4_K_S	4.37GB
llama_8b_lima_10.Q4_K.gguf	Q4_K	4.58GB
llama_8b_lima_10.Q4_K_M.gguf	Q4_K_M	4.58GB
llama_8b_lima_10.Q4_1.gguf	Q4_1	4.78GB
llama_8b_lima_10.Q5_0.gguf	Q5_0	5.21GB
llama_8b_lima_10.Q5_K_S.gguf	Q5_K_S	5.21GB
llama_8b_lima_10.Q5_K.gguf	Q5_K	5.34GB
llama_8b_lima_10.Q5_K_M.gguf	Q5_K_M	5.34GB
llama_8b_lima_10.Q5_1.gguf	Q5_1	5.65GB
llama_8b_lima_10.Q6_K.gguf	Q6_K	6.14GB
llama_8b_lima_10.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers license: llama3.1 base_model: meta-llama/Llama-3.1-8B tags:

llama-factory
full
generated_from_trainer model-index:
name: llama_8b_lima_10 results: []

llama_8b_lima_10

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the open_webui_dataset dataset. It achieves the following results on the evaluation set:

Loss: 0.6850

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: 7e-06
train_batch_size: 3
eval_batch_size: 3
seed: 66
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 3
total_train_batch_size: 18
total_eval_batch_size: 6
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: polynomial
lr_scheduler_warmup_steps: 30
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.6395	0.1109	39	0.8886
0.6501	0.2218	78	0.8122
0.5236	0.3327	117	0.7785
0.6038	0.4436	156	0.7441
0.5659	0.5545	195	0.7215
0.6737	0.6654	234	0.7047
0.7081	0.7763	273	0.6978
0.6465	0.8872	312	0.6915
0.6191	0.9981	351	0.6850

Framework versions

Transformers 4.45.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.20.0

RichardErkhov/OpenLeecher_-_llama_8b_lima_10-gguf

Original model description:

llama_8b_lima_10

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
OpenLeecher_-_llama_8b_lima_10-gguf