abhinav302019
/

falcon-7b-custom-dpo-lora-lablebox

Generated from Trainer

direct-preference-optimization-(custom-dpo-with-proper-loss)

Model card Files Files and versions

falcon-7b-custom-dpo-lora-lablebox

7.02 MB

1 contributor

History: 2 commits

abhinav302019's picture

Upload falcon-7b-custom-dpo-lora-lablebox - LoRA fine-tuned Falcon-7B

0dec499 verified about 2 months ago

.gitattributes

1.52 kB

initial commit about 2 months ago
README.md

2.37 kB

Upload falcon-7b-custom-dpo-lora-lablebox - LoRA fine-tuned Falcon-7B about 2 months ago
adapter_config.json

853 Bytes

Upload falcon-7b-custom-dpo-lora-lablebox - LoRA fine-tuned Falcon-7B about 2 months ago
adapter_model.safetensors

2.37 MB
xet

Upload falcon-7b-custom-dpo-lora-lablebox - LoRA fine-tuned Falcon-7B about 2 months ago
chat_template.jinja

804 Bytes

Upload falcon-7b-custom-dpo-lora-lablebox - LoRA fine-tuned Falcon-7B about 2 months ago
special_tokens_map.json

427 Bytes

Upload falcon-7b-custom-dpo-lora-lablebox - LoRA fine-tuned Falcon-7B about 2 months ago
tokenizer.json

4.61 MB

Upload falcon-7b-custom-dpo-lora-lablebox - LoRA fine-tuned Falcon-7B about 2 months ago
tokenizer_config.json

2.67 kB

Upload falcon-7b-custom-dpo-lora-lablebox - LoRA fine-tuned Falcon-7B about 2 months ago
training_metrics.json

30.3 kB

Upload falcon-7b-custom-dpo-lora-lablebox - LoRA fine-tuned Falcon-7B about 2 months ago