You can deploy this model and start earning money today!

RichardErkhov/
mlfoundations-dev_-_llama3-1_8b_webinstruct_750k-gguf

Name: mlfoundations-dev_-_llama3-1_8b_webinstruct_750k-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama3-1_8b_webinstruct_750k - GGUF

Model creator: https://huggingface.co/mlfoundations-dev/
Original model: https://huggingface.co/mlfoundations-dev/llama3-1_8b_webinstruct_750k/

Name	Quant method	Size
llama3-1_8b_webinstruct_750k.Q2_K.gguf	Q2_K	2.96GB
llama3-1_8b_webinstruct_750k.IQ3_XS.gguf	IQ3_XS	3.28GB
llama3-1_8b_webinstruct_750k.IQ3_S.gguf	IQ3_S	3.43GB
llama3-1_8b_webinstruct_750k.Q3_K_S.gguf	Q3_K_S	3.41GB
llama3-1_8b_webinstruct_750k.IQ3_M.gguf	IQ3_M	3.52GB
llama3-1_8b_webinstruct_750k.Q3_K.gguf	Q3_K	3.74GB
llama3-1_8b_webinstruct_750k.Q3_K_M.gguf	Q3_K_M	3.74GB
llama3-1_8b_webinstruct_750k.Q3_K_L.gguf	Q3_K_L	4.03GB
llama3-1_8b_webinstruct_750k.IQ4_XS.gguf	IQ4_XS	4.18GB
llama3-1_8b_webinstruct_750k.Q4_0.gguf	Q4_0	4.34GB
llama3-1_8b_webinstruct_750k.IQ4_NL.gguf	IQ4_NL	4.38GB
llama3-1_8b_webinstruct_750k.Q4_K_S.gguf	Q4_K_S	4.37GB
llama3-1_8b_webinstruct_750k.Q4_K.gguf	Q4_K	4.58GB
llama3-1_8b_webinstruct_750k.Q4_K_M.gguf	Q4_K_M	4.58GB
llama3-1_8b_webinstruct_750k.Q4_1.gguf	Q4_1	4.78GB
llama3-1_8b_webinstruct_750k.Q5_0.gguf	Q5_0	5.21GB
llama3-1_8b_webinstruct_750k.Q5_K_S.gguf	Q5_K_S	5.21GB
llama3-1_8b_webinstruct_750k.Q5_K.gguf	Q5_K	5.34GB
llama3-1_8b_webinstruct_750k.Q5_K_M.gguf	Q5_K_M	5.34GB
llama3-1_8b_webinstruct_750k.Q5_1.gguf	Q5_1	5.65GB
llama3-1_8b_webinstruct_750k.Q6_K.gguf	Q6_K	6.14GB
llama3-1_8b_webinstruct_750k.Q8_0.gguf	Q8_0	7.95GB

Original model description:

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

llama-factory
full
generated_from_trainer model-index:
name: llama3-1_8b_webinstruct_750k results: []

llama3-1_8b_webinstruct_750k

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the mlfoundations-dev/webinstruct_stage_3 dataset. It achieves the following results on the evaluation set:

Loss: 0.9555

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-06
train_batch_size: 16
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 32
total_train_batch_size: 512
total_eval_batch_size: 256
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.1
lr_scheduler_warmup_steps: 1738
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.9551	1.0	100	0.9629
0.8934	2.0	200	0.9497
0.841	3.0	300	0.9555

Framework versions

Transformers 4.46.1
Pytorch 2.4.0
Datasets 3.0.2
Tokenizers 0.20.3

RichardErkhov/mlfoundations-dev_-_llama3-1_8b_webinstruct_750k-gguf

Original model description:

llama3-1_8b_webinstruct_750k

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
mlfoundations-dev_-_llama3-1_8b_webinstruct_750k-gguf