Model Card for decruz07/kellemar-DPO-Orca-Distilled-7B
This model was created using mlabonne/Marcoro14-7B-slerp as the base, and finetuned with argilla/distilabel-intel-orca-dpo-pairs
These are the GGUF versions. Both qk4m and qk5m variations are available for download.
Model Details
Finetuned with these specific parameters: Steps: 200 Learning Rate: 5e5 Beta: 0.1
Model Description
- Developed by: @decruz
- Funded by [optional]: my full-time job
- Finetuned from model [optional]: mlabonne/Marcoro14-7B-slerp
Benchmarks
Top 5 in OpenLLM Benchmarks as of 2024/01/17
OpenLLM
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|---|---|---|---|---|---|---|---|
| kellemar-DPO-Orca-Distilled-7B-SLERP | 73.71 | 70.48 | 87.56 | 65.33 | 64.97 | 81.93 | 72.02 |
Nous
| Model | AGIEval | GPT4All | TruthfulQA | Bigbench | Average |
|---|---|---|---|---|---|
| kellemar-DPO-Orca-Distilled-7B-SLERP | 45.27 | 76.42 | 65.48 | 47.21 | 58.6 |
| Marcoro14-7B-slerp | 44.66 | 76.24 | 64.15 | 45.64 | 57.67 |
| kellemar-DPO-Orca-Distilled-7B | 43.61 | 73.14 | 55.73 | 42.28 | 53.69 |
| kellemar-Orca-DPO-7B | 43.35 | 73.43 | 54.02 | 42.24 | 53.26 |
| OpenHermes-2.5-Mistral-7B | 43.07 | 73.12 | 53.04 | 40.96 | 52.38 |
Uses
You can use this for basic inference. You could probably finetune with this if you want to.
How to Get Started with the Model
You can create a space out of this, or use basic python code to call the model directly and make inferences to it.
[More Information Needed]
Training Details
The following was used: `training_args = TrainingArguments( per_device_train_batch_size=4, gradient_accumulation_steps=4, gradient_checkpointing=True, learning_rate=5e-5, lr_scheduler_type="cosine", max_steps=200, save_strategy="no", logging_steps=1, output_dir=new_model, optim="paged_adamw_32bit", warmup_steps=100, bf16=True, report_to="wandb", )
Create DPO trainer
dpo_trainer = DPOTrainer( model, ref_model, args=training_args, train_dataset=dataset, tokenizer=tokenizer, peft_config=peft_config, beta=0.1, max_prompt_length=1024, max_length=1536, )`
Training Data
This was trained with https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs
Training Procedure
Trained with Labonne's Google Colab Notebook on Finetuning Mistral 7B with DPO.
Model Card Authors [optional]
@decruz
Model Card Contact
@decruz on X/Twitter
- Downloads last month
- 6
Model tree for decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP-GGUF
Base model
mlabonne/Marcoro14-7B-slerp