PrototypeCommon
jackaduma/ChatGLM-LoRA-RLHF-PyTorch
A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the ChatGLM architecture. Basically ChatGPT but with ChatGLM
- Owner
- jackaduma (personal account)
- Stars
- Stars: 138
- Forks
- Forks: 9
- Language
- Python
- License
- MIT
- Created
- 2023
- Topics
- lorachatglmchatglm-6bchatgptfinetunegptllmpytorchrlhfllama
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by jackaduma
All 8 repos by jackaduma- jackaduma/awesome_LLMs_interview_notesStars: 1,320Beta
- jackaduma/CycleGAN-VC2Stars: 572PythonAlpha
- jackaduma/Vicuna-LoRA-RLHF-PyTorchStars: 219PythonPrototype
- jackaduma/SecBERTStars: 213PythonPrototype
- jackaduma/Recurrent-LLMStars: 207PythonPrototype
- jackaduma/CycleGAN-VC3Stars: 157PythonPrototype
Nearby in Python
All Python repos- zai-org/zcode-pluginsStars: 138PythonPrototype
- UniWAM/UniWAMStars: 138PythonPrototype
- jerryhan1201-debug/maimen-intelStars: 138PythonPrototype
- dustin/bindirStars: 138PythonPrototype
- dozercodes/DecisionTreeStars: 138PythonPrototype
- brentp/cruzdbStars: 138PythonPrototype