adding the modelnames in the LORA.md file and removing unused functions from mamba2.py

This commit is contained in:
Goekdeniz-Guelmez
2024-12-12 22:52:00 +01:00
parent a883e39f41
commit dff4e52910
2 changed files with 29 additions and 30 deletions

View File

@@ -7,12 +7,37 @@ LoRA (QLoRA).[^qlora] LoRA fine-tuning works with the following model families:
- Mistral
- Llama
- Phi2
- Phi3
- Phi3 Small
- PhiMOE
- Phixtral
- Plamo
- Mixtral
- Qwen
- Qwen2
- Qwen2 MOE
- Gemma
- Gemma2
- OLMo
- OLMo2
- MiniCPM
- InternLM2
- Mamba
- Mamba2
- EXAONE
- Hunyuan
- GPT 2
- GPT Neo
- GPT BigCode
- Deepseek
- Deepseek2
- OpenLM
- StableLM
- Cohere
- DBRX
- Nemotron
- Recurrent Gemma
- Starcoder
## Contents