readme updates for full DPO distributed recipe #2363
Merged
+2
−1
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchtune/2363
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit a0b3a51 with merge base fb52557 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
README.md
Outdated
| @@ -72,7 +72,8 @@ torchtune provides the following finetuning recipes for training on one or more | |||
| | DoRA/QDoRA Finetuning | ✅ | ✅ | ❌ | [lora_finetune_single_device](recipes/lora_finetune_single_device.py) <br> [lora_finetune_distributed](recipes/lora_finetune_distributed.py)| [Llama3 8B QDoRA single-device](recipes/configs/llama3/8B_qdora_single_device.yaml) <br> [Llama3 8B DoRA distributed](recipes/configs/llama3/8B_dora.yaml) | |||
| | Quantization-Aware Training | ❌ | ✅ | ❌ | [qat_distributed](recipes/qat_distributed.py)| [Llama3 8B QAT](recipes/configs/llama3/8B_qat_full.yaml) | |||
| | Quantization-Aware Training and LoRA Finetuning | ❌ | ✅ | ❌ | [qat_lora_finetune_distributed](recipes/qat_lora_finetune_distributed.py)| [Llama3 8B QAT](recipes/configs/llama3/8B_qat_lora.yaml) | |||
| | Direct Preference Optimization | ✅ | ✅ | ❌ | [lora_dpo_single_device](recipes/lora_dpo_single_device.py) <br> [lora_dpo_distributed](recipes/lora_dpo_distributed.py) | [Llama2 7B single-device](recipes/configs/llama2/7B_lora_dpo_single_device.yaml) <br> [Llama2 7B distributed](recipes/configs/llama2/7B_lora_dpo.yaml) | |||
| | Direct Preference Optimization: Full Finetuning | ❌ | ✅ | ❌ | [full_dpo_distributed](recipes/full_dpo_distributed.py) | [Llama3.1 8B DPO](recipes/configs/llama3_1/8B_full_dpo.yaml) | |||
| | Direct Preference Optimization with LoRA | ✅ | ✅ | ❌ | [lora_dpo_single_device](recipes/lora_dpo_single_device.py) <br> [lora_dpo_distributed](recipes/lora_dpo_distributed.py) | [Llama2 7B single-device](recipes/configs/llama2/7B_lora_dpo_single_device.yaml) <br> [Llama2 7B distributed](recipes/configs/llama2/7B_lora_dpo.yaml) | |||
There was a problem hiding this comment.
Suggested change
| | Direct Preference Optimization with LoRA | ✅ | ✅ | ❌ | [lora_dpo_single_device](recipes/lora_dpo_single_device.py) <br> [lora_dpo_distributed](recipes/lora_dpo_distributed.py) | [Llama2 7B single-device](recipes/configs/llama2/7B_lora_dpo_single_device.yaml) <br> [Llama2 7B distributed](recipes/configs/llama2/7B_lora_dpo.yaml) | |
| | LoRA Direct Preference Optimization | ✅ | ✅ | ❌ | [lora_dpo_single_device](recipes/lora_dpo_single_device.py) <br> [lora_dpo_distributed](recipes/lora_dpo_distributed.py) | [Llama2 7B single-device](recipes/configs/llama2/7B_lora_dpo_single_device.yaml) <br> [Llama2 7B distributed](recipes/configs/llama2/7B_lora_dpo.yaml) |
There was a problem hiding this comment.
Also we have more up to date 3.1 8B configs we could point to, if you'd like : )
SalmanMohammadi
approved these changes
Feb 8, 2025
felipemello1
approved these changes
Feb 8, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Update our readme to include DPO full finetune distributed recipe now that #2275 has landed