You can deploy this model and start earning money today!

RichardErkhov/
kevin1010607_-_llama2-7b-sft-full-llama2-gguf

Name: kevin1010607_-_llama2-7b-sft-full-llama2-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama2-7b-sft-full-llama2 - GGUF

Model creator: https://huggingface.co/kevin1010607/
Original model: https://huggingface.co/kevin1010607/llama2-7b-sft-full-llama2/

Name	Quant method	Size
llama2-7b-sft-full-llama2.Q2_K.gguf	Q2_K	2.36GB
llama2-7b-sft-full-llama2.IQ3_XS.gguf	IQ3_XS	2.6GB
llama2-7b-sft-full-llama2.IQ3_S.gguf	IQ3_S	2.75GB
llama2-7b-sft-full-llama2.Q3_K_S.gguf	Q3_K_S	2.75GB
llama2-7b-sft-full-llama2.IQ3_M.gguf	IQ3_M	2.9GB
llama2-7b-sft-full-llama2.Q3_K.gguf	Q3_K	3.07GB
llama2-7b-sft-full-llama2.Q3_K_M.gguf	Q3_K_M	3.07GB
llama2-7b-sft-full-llama2.Q3_K_L.gguf	Q3_K_L	3.35GB
llama2-7b-sft-full-llama2.IQ4_XS.gguf	IQ4_XS	3.4GB
llama2-7b-sft-full-llama2.Q4_0.gguf	Q4_0	3.56GB
llama2-7b-sft-full-llama2.IQ4_NL.gguf	IQ4_NL	3.58GB
llama2-7b-sft-full-llama2.Q4_K_S.gguf	Q4_K_S	3.59GB
llama2-7b-sft-full-llama2.Q4_K.gguf	Q4_K	3.8GB
llama2-7b-sft-full-llama2.Q4_K_M.gguf	Q4_K_M	3.8GB
llama2-7b-sft-full-llama2.Q4_1.gguf	Q4_1	3.95GB
llama2-7b-sft-full-llama2.Q5_0.gguf	Q5_0	4.33GB
llama2-7b-sft-full-llama2.Q5_K_S.gguf	Q5_K_S	4.33GB
llama2-7b-sft-full-llama2.Q5_K.gguf	Q5_K	4.45GB
llama2-7b-sft-full-llama2.Q5_K_M.gguf	Q5_K_M	4.45GB
llama2-7b-sft-full-llama2.Q5_1.gguf	Q5_1	4.72GB
llama2-7b-sft-full-llama2.Q6_K.gguf	Q6_K	5.15GB
llama2-7b-sft-full-llama2.Q8_0.gguf	Q8_0	6.67GB

Original model description:

license: llama2 base_model: meta-llama/Llama-2-7b-hf tags:

alignment-handbook
trl
sft
generated_from_trainer
trl
sft
generated_from_trainer datasets:
HuggingFaceH4/ultrafeedback_binarized model-index:
name: llama2-7b-sft-full-llama2 results: []

llama2-7b-sft-full-llama2

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

Loss: 1.0380

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: 2e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 8
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: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.0183	0.9980	126	1.0127
0.869	1.9960	252	1.0026
0.714	2.9941	378	1.0380

Framework versions

Transformers 4.41.2
Pytorch 2.3.0a0+ebedce2
Datasets 2.19.2
Tokenizers 0.19.1

RichardErkhov/kevin1010607_-_llama2-7b-sft-full-llama2-gguf

Original model description:

llama2-7b-sft-full-llama2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
kevin1010607_-_llama2-7b-sft-full-llama2-gguf