issues
search
KhoomeiK
/
LlamaGym
Fine-tune LLM agents with online reinforcement learning
MIT License
994
stars
44
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Unable to install due to error: metadata-generation-failed
#12
Aragath
opened
1 month ago
0
Why are all the past messages for any given question -> answer pair included?
#11
mainrs
opened
4 months ago
0
How to load fine-tuned model after training?
#10
mainrs
opened
5 months ago
0
ImportError: cannot import name 'top_k_top_p_filtering' from 'transformers' (/home/eito/AIExperiments/LlamaGym/myenv/lib/python3.10/site-packages/transformers/__init__.py)
#9
Miyamura80
closed
5 months ago
4
what models support？ and only cpu enough？
#8
wzg-zhuo
closed
5 months ago
0
OOM when run the example
#7
haosdent
closed
7 months ago
1
[WIP] Adding support for Q&A Agents and environments
#6
danikhan632
opened
8 months ago
1
Fix the unexpected action of llm
#5
yuxiaooye
opened
8 months ago
1
Is there a comparison of training speed with the implementation in TWOSOME?
#4
elggurts22
closed
8 months ago
1
LangChain Integration
#3
slavakurilyak
opened
8 months ago
0
crewAI Integration
#2
slavakurilyak
closed
5 months ago
0
Fix batching, data formatting, action extraction, prompts; add wandb logging
#1
KhoomeiK
closed
8 months ago
0