RyanYr_-_gemma-2-2b-it_CoT-it_SFT-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
RyanYr_-_gemma-2-2b-it_CoT-it_SFT-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

gemma-2-2b-it_CoT-it_SFT - GGUF

Model creator: https://huggingface.co/RyanYr/
Original model: https://huggingface.co/RyanYr/gemma-2-2b-it_CoT-it_SFT/

Name	Quant method	Size
gemma-2-2b-it_CoT-it_SFT.Q2_K.gguf	Q2_K	1.15GB
gemma-2-2b-it_CoT-it_SFT.IQ3_XS.gguf	IQ3_XS	1.22GB
gemma-2-2b-it_CoT-it_SFT.IQ3_S.gguf	IQ3_S	1.27GB
gemma-2-2b-it_CoT-it_SFT.Q3_K_S.gguf	Q3_K_S	1.27GB
gemma-2-2b-it_CoT-it_SFT.IQ3_M.gguf	IQ3_M	1.3GB
gemma-2-2b-it_CoT-it_SFT.Q3_K.gguf	Q3_K	1.36GB
gemma-2-2b-it_CoT-it_SFT.Q3_K_M.gguf	Q3_K_M	1.36GB
gemma-2-2b-it_CoT-it_SFT.Q3_K_L.gguf	Q3_K_L	1.44GB
gemma-2-2b-it_CoT-it_SFT.IQ4_XS.gguf	IQ4_XS	1.47GB
gemma-2-2b-it_CoT-it_SFT.Q4_0.gguf	Q4_0	1.52GB
gemma-2-2b-it_CoT-it_SFT.IQ4_NL.gguf	IQ4_NL	1.53GB
gemma-2-2b-it_CoT-it_SFT.Q4_K_S.gguf	Q4_K_S	1.53GB
gemma-2-2b-it_CoT-it_SFT.Q4_K.gguf	Q4_K	1.59GB
gemma-2-2b-it_CoT-it_SFT.Q4_K_M.gguf	Q4_K_M	1.59GB
gemma-2-2b-it_CoT-it_SFT.Q4_1.gguf	Q4_1	1.64GB
gemma-2-2b-it_CoT-it_SFT.Q5_0.gguf	Q5_0	1.75GB
gemma-2-2b-it_CoT-it_SFT.Q5_K_S.gguf	Q5_K_S	1.75GB
gemma-2-2b-it_CoT-it_SFT.Q5_K.gguf	Q5_K	1.79GB
gemma-2-2b-it_CoT-it_SFT.Q5_K_M.gguf	Q5_K_M	1.79GB
gemma-2-2b-it_CoT-it_SFT.Q5_1.gguf	Q5_1	1.87GB
gemma-2-2b-it_CoT-it_SFT.Q6_K.gguf	Q6_K	2.0GB
gemma-2-2b-it_CoT-it_SFT.Q8_0.gguf	Q8_0	2.59GB

Original model description:

library_name: transformers license: gemma base_model: google/gemma-2-2b-it tags:

trl
sft
generated_from_trainer model-index:
name: gemma-2-2b-it_CoT-it_SFT results: []

gemma-2-2b-it_CoT-it_SFT

This model is a fine-tuned version of google/gemma-2-2b-it on an unknown 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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 64
total_train_batch_size: 256
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 1

Training results

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 3.0.0
Tokenizers 0.19.1