NanoCode012
NanoCode012
### ⚠️ Please check that this feature request hasn't been suggested before. - [x] I searched previous [Ideas in Discussions](https://github.com/axolotl-ai-cloud/axolotl/discussions/categories/ideas) didn't find any similar feature requests. - [x] I searched...
### Please check that this issue hasn't been reported before. - [X] I searched previous [Bug Reports](https://github.com/axolotl-ai-cloud/axolotl/labels/bug) didn't find any similar reports. ### Expected Behavior Loads the dataset, goes to...
Hey! Thank you for the nice tool and integrations. I've been trying this out with English JSON parsing using vllm, and it works great! However, when I tried with a...
# Description See https://github.com/huggingface/peft/issues/2864 There can be a desync for adapters on tied embed_tok and lm_head weights. This config forces a sync if tied. ## Motivation and Context ## How...
# Description Adds SageAttention https://github.com/thu-ml/SageAttention/ Since it has similar interface as sdpa_attention, I used that implementation and flash attention in transformers to cross check. ## Motivation and Context ## How...
# Description This PR is just a working branch at the moment. The upstream code for Kimi is inference optimized. The code in this PR is LLM-gen and not verified....
# Description Some training notes on 4xH100: - offload would require patching modeling code to remove `e_score_correction_bias` else device mismatch during calculation. - fft offload, checkpointing error - fft without...
# Description Fixes https://github.com/axolotl-ai-cloud/axolotl/discussions/2803 ## Motivation and Context ## How has this been tested? ## Screenshots (if appropriate) ## Types of changes ## Social Handles (Optional)
### ⚠️ Please check that this feature request hasn't been suggested before. - [x] I searched previous [Ideas in Discussions](https://github.com/axolotl-ai-cloud/axolotl/discussions/categories/ideas) didn't find any similar feature requests. - [x] I searched...
### ⚠️ Please check that this feature request hasn't been suggested before. - [x] I searched previous [Ideas in Discussions](https://github.com/axolotl-ai-cloud/axolotl/discussions/categories/ideas) didn't find any similar feature requests. - [x] I searched...