edinlp_-_mistral-7b-v0.3-dpo-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
edinlp_-_mistral-7b-v0.3-dpo-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

mistral-7b-v0.3-dpo - GGUF

Model creator: https://huggingface.co/edinlp/
Original model: https://huggingface.co/edinlp/mistral-7b-v0.3-dpo/

Name	Quant method	Size
mistral-7b-v0.3-dpo.Q2_K.gguf	Q2_K	2.54GB
mistral-7b-v0.3-dpo.IQ3_XS.gguf	IQ3_XS	2.82GB
mistral-7b-v0.3-dpo.IQ3_S.gguf	IQ3_S	2.97GB
mistral-7b-v0.3-dpo.Q3_K_S.gguf	Q3_K_S	2.95GB
mistral-7b-v0.3-dpo.IQ3_M.gguf	IQ3_M	3.06GB
mistral-7b-v0.3-dpo.Q3_K.gguf	Q3_K	3.28GB
mistral-7b-v0.3-dpo.Q3_K_M.gguf	Q3_K_M	3.28GB
mistral-7b-v0.3-dpo.Q3_K_L.gguf	Q3_K_L	3.56GB
mistral-7b-v0.3-dpo.IQ4_XS.gguf	IQ4_XS	3.68GB
mistral-7b-v0.3-dpo.Q4_0.gguf	Q4_0	3.83GB
mistral-7b-v0.3-dpo.IQ4_NL.gguf	IQ4_NL	3.87GB
mistral-7b-v0.3-dpo.Q4_K_S.gguf	Q4_K_S	3.86GB
mistral-7b-v0.3-dpo.Q4_K.gguf	Q4_K	4.07GB
mistral-7b-v0.3-dpo.Q4_K_M.gguf	Q4_K_M	4.07GB
mistral-7b-v0.3-dpo.Q4_1.gguf	Q4_1	4.24GB
mistral-7b-v0.3-dpo.Q5_0.gguf	Q5_0	4.66GB
mistral-7b-v0.3-dpo.Q5_K_S.gguf	Q5_K_S	4.66GB
mistral-7b-v0.3-dpo.Q5_K.gguf	Q5_K	4.78GB
mistral-7b-v0.3-dpo.Q5_K_M.gguf	Q5_K_M	4.78GB
mistral-7b-v0.3-dpo.Q5_1.gguf	Q5_1	5.07GB
mistral-7b-v0.3-dpo.Q6_K.gguf	Q6_K	5.54GB
mistral-7b-v0.3-dpo.Q8_0.gguf	Q8_0	7.17GB

Original model description:

library_name: transformers license: other base_model: edinlp/mistral-7b-v0.3-sft tags:

llama-factory
full
generated_from_trainer model-index:
name: mistral-dpo results: []

mistral-dpo

This model is a fine-tuned version of edinlp/mistral-7b-v0.3-sft on the ultrafeedback 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: 5e-07
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 1.0

Training results

Framework versions

Transformers 4.45.0
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.20.0