mshumer / gpt-llm-trainer

mshumer/gpt-llm-trainer Issues

GPT-2 torch argmax issues
Closed 3 months ago3
How to mine fine-tuning samples from specified corpora
Updated 4 months ago
hello, would you have time for a chat?
Updated 4 months ago2
getting an error after running generate_example().
Updated 4 months ago
Question
Updated 4 months ago
Running into CUDA out of memory on Colab
Updated 6 months ago8
error :You tried to access openai.ChatCompletion, but this is no longer supported in openai>=1.0.0
Updated 7 months ago1
Token generation limit
Updated 8 months ago5
Merge the model and store in Google Drive (Section)
Updated 10 months ago3
Problem with workflow
Updated 10 months ago
API not working even after upgrading to gpt 4
Updated a year ago1
llm
Updated a year ago
the model before lora load and after lora load is diff
Updated a year ago1
NousResearch/llama-2-7b-chat-hf NOT AVAILABLE
Updated a year ago1
Cost estimate?
Updated a year ago3
Logging into wandb.ai
Updated a year ago1
without openai !!!
Updated a year ago1
ㅂㅂ
Updated a year ago
Can we use GPT3.5?
Closed a year ago6
which GPU?
Updated a year ago1
The model `gpt-4` does not exist or you do not have access to it
Closed a year ago
Add 'LLM Knowledge Distillation' to Readme or Topic Tags
Updated a year ago