Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mlfoundations-dev_-_oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
mlfoundations-dev_-_oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-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
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr - GGUF
Model creator:
https://huggingface.co/mlfoundations-dev/
Original model:
https://huggingface.co/mlfoundations-dev/oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr/
Name
Quant method
Size
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q2_K.gguf
Q2_K
2.54GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.IQ3_XS.gguf
IQ3_XS
2.82GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.IQ3_S.gguf
IQ3_S
2.97GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_S.gguf
Q3_K_S
2.95GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.IQ3_M.gguf
IQ3_M
3.06GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K.gguf
Q3_K
3.28GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_M.gguf
Q3_K_M
3.28GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_L.gguf
Q3_K_L
3.56GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.IQ4_XS.gguf
IQ4_XS
3.68GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_0.gguf
Q4_0
3.83GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.IQ4_NL.gguf
IQ4_NL
3.87GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K_S.gguf
Q4_K_S
3.86GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K.gguf
Q4_K
4.07GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K_M.gguf
Q4_K_M
4.07GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_1.gguf
Q4_1
4.24GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_0.gguf
Q5_0
4.66GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K_S.gguf
Q5_K_S
4.66GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K.gguf
Q5_K
4.78GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K_M.gguf
Q5_K_M
4.78GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_1.gguf
Q5_1
5.07GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q6_K.gguf
Q6_K
5.54GB
oh-mistral-bs2048_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q8_0.gguf
Q8_0
7.17GB
Original model description:
library_name: transformers license: other base_model: mistralai/Mistral-7B-v0.3 tags:
llama-factory
full
generated_from_trainer model-index:
name: oh-mistral-bs2048_lr2.00E-06_schedulerconstant_warmup5.00E-02_minlr results: []
oh-mistral-bs2048_lr2.00E-06_schedulerconstant_warmup5.00E-02_minlr
This model is a fine-tuned version of
mistralai/Mistral-7B-v0.3
on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini 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-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 128
gradient_accumulation_steps: 2
total_train_batch_size: 2048
total_eval_batch_size: 1024
optimizer: Use 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: 0.05
num_epochs: 3.0
Training results
Framework versions
Transformers 4.46.1
Pytorch 2.5.0a0+b465a5843b.nv24.09
Datasets 3.0.2
Tokenizers 0.20.3
