readme updates for full DPO distributed recipe (pytorch#2363)

README.md

@@ -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)
+| LoRA Direct Preference Optimization | ✅ | ✅ | ❌ | [lora_dpo_single_device](recipes/lora_dpo_single_device.py) <br> [lora_dpo_distributed](recipes/lora_dpo_distributed.py) | [Llama3.1 8B single-device](recipes/configs/llama3_1/8B_lora_dpo_single_device.yaml) <br> [Llama3.1 8B distributed](recipes/configs/llama3_1/8B_lora_dpo.yaml)
 | Proximal Policy Optimization | ✅ | ❌ | ❌ |  [ppo_full_finetune_single_device](recipes/ppo_full_finetune_single_device.py) | [Mistral 7B](recipes/configs/mistral/7B_full_ppo_low_memory.yaml)
 | LoRA Knowledge Distillation | ✅ | ✅ | ❌ | [knowledge_distillation_single_device](recipes/knowledge_distillation_single_device.py) <br> [knowledge_distillation_distributed](recipes/knowledge_distillation_distributed.py) | [Qwen2 1.5B -> 0.5B single-device](recipes/configs/qwen2/1.5B_to_0.5B_KD_lora_single_device.yaml) <br> [Qwen2 1.5B -> 0.5B distributed](recipes/configs/qwen2/1.5B_to_0.5B_KD_lora_distributed.yaml)