Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Dynosaur_-_llama3-8b-math-sft-full-combine-paraphrase-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
Dynosaur_-_llama3-8b-math-sft-full-combine-paraphrase-gguf
like
0
conversational
endpoints_compatible
gguf
template
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Quantization made by Richard Erkhov.
Github
Discord
Request more models
llama3-8b-math-sft-full-combine-paraphrase - GGUF
Model creator:
https://huggingface.co/Dynosaur/
Original model:
https://huggingface.co/Dynosaur/llama3-8b-math-sft-full-combine-paraphrase/
Name
Quant method
Size
llama3-8b-math-sft-full-combine-paraphrase.Q2_K.gguf
Q2_K
2.96GB
llama3-8b-math-sft-full-combine-paraphrase.IQ3_XS.gguf
IQ3_XS
3.28GB
llama3-8b-math-sft-full-combine-paraphrase.IQ3_S.gguf
IQ3_S
3.43GB
llama3-8b-math-sft-full-combine-paraphrase.Q3_K_S.gguf
Q3_K_S
3.41GB
llama3-8b-math-sft-full-combine-paraphrase.IQ3_M.gguf
IQ3_M
3.52GB
llama3-8b-math-sft-full-combine-paraphrase.Q3_K.gguf
Q3_K
3.74GB
llama3-8b-math-sft-full-combine-paraphrase.Q3_K_M.gguf
Q3_K_M
3.74GB
llama3-8b-math-sft-full-combine-paraphrase.Q3_K_L.gguf
Q3_K_L
4.03GB
llama3-8b-math-sft-full-combine-paraphrase.IQ4_XS.gguf
IQ4_XS
4.18GB
llama3-8b-math-sft-full-combine-paraphrase.Q4_0.gguf
Q4_0
4.34GB
llama3-8b-math-sft-full-combine-paraphrase.IQ4_NL.gguf
IQ4_NL
4.38GB
llama3-8b-math-sft-full-combine-paraphrase.Q4_K_S.gguf
Q4_K_S
4.37GB
llama3-8b-math-sft-full-combine-paraphrase.Q4_K.gguf
Q4_K
4.58GB
llama3-8b-math-sft-full-combine-paraphrase.Q4_K_M.gguf
Q4_K_M
4.58GB
llama3-8b-math-sft-full-combine-paraphrase.Q4_1.gguf
Q4_1
4.78GB
llama3-8b-math-sft-full-combine-paraphrase.Q5_0.gguf
Q5_0
5.21GB
llama3-8b-math-sft-full-combine-paraphrase.Q5_K_S.gguf
Q5_K_S
5.21GB
llama3-8b-math-sft-full-combine-paraphrase.Q5_K.gguf
Q5_K
5.34GB
llama3-8b-math-sft-full-combine-paraphrase.Q5_K_M.gguf
Q5_K_M
5.34GB
llama3-8b-math-sft-full-combine-paraphrase.Q5_1.gguf
Q5_1
5.65GB
llama3-8b-math-sft-full-combine-paraphrase.Q6_K.gguf
Q6_K
6.14GB
llama3-8b-math-sft-full-combine-paraphrase.Q8_0.gguf
Q8_0
7.95GB
Original model description:
library_name: transformers license: llama3 base_model: Dynosaur/llama3-8b-math-sft tags:
alignment-handbook
trl
sft
generated_from_trainer
trl
sft
generated_from_trainer datasets:
Dynosaur/math-sft-full-combine-paraphrase model-index:
name: llama3-8b-math-sft-full-combine-paraphrase results: []
llama3-8b-math-sft-full-combine-paraphrase
This model is a fine-tuned version of
Dynosaur/llama3-8b-math-sft
on the Dynosaur/math-sft-full-combine-paraphrase dataset.
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: 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: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2
Training results
Framework versions
Transformers 4.45.1
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.0
