Hugging Face's logo

umarigan
/
Trendyol-LLM-7b-chat-v1.0-RLHF

Question Answering
Adapters
Safetensors
Transformers
English
Turkish
mistral
text-generation
text-generation-inference
unsloth
trl
dpo
rlhf
turkish
llama2
Model card Files Community
Edit model card

Uploaded model

  • Developed by: umarigan
  • License: apache-2.0
  • Finetuned from model : Trendyol/Trendyol-LLM-7b-chat-v1.0

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

I used 10k pair of Turkish rlhf dataset.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Framework versions

  • PEFT 0.9.0
  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
0
Safetensors
Model size
7.34B params
Tensor type
BF16
·
Inference Examples
Question Answering
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for umarigan/Trendyol-LLM-7b-chat-v1.0-RLHF

Base model

mistralai/Mistral-7B-v0.1
Finetuned
Trendyol/Trendyol-LLM-7b-base-v1.0
Finetuned
Trendyol/Trendyol-LLM-7b-chat-v1.0
Adapter
(4)
this model

Collection including umarigan/Trendyol-LLM-7b-chat-v1.0-RLHF