Thomas Wood PRO
odellus
AI & ML interests
Long document summarization, neural program synthesis, automated theorem proving, open ended question answering, and embodied intelligence.
Recent Activity
new activity about 19 hours ago
unsloth/Qwen3.8-27B-GGUF:Subtle chat template issue when building from latest llama.cpp master branch liked a model 4 days ago
openvla/openvla-7b updated a model 18 days ago
odellus/colqwen2-v1.0-ggufOrganizations
Subtle chat template issue when building from latest llama.cpp master branch
4
#67 opened 2 days ago
by odellus
zai-org/GLM-4.5-Air
👍❤️ 11
1
#3706 opened about 1 year ago
by 
eshine-downtown
How to run huggingface model?
3
#2 opened over 1 year ago
by odellus
Which one should I use?
4
#1 opened over 1 year ago
by odellus
App doesn't seem to work
1
#1 opened over 2 years ago
by odellus
apply_chat_template(add_generation_prompt=True) not working
1
#9 opened over 2 years ago
by odellus
Why is this 7B model only showing 5GB of gpu ram allocation?
🤝 1
3
#96 opened over 2 years ago
by 
shayak
Wow! What a model. Didn't know it could be trained with Axolotl
7
#5 opened almost 3 years ago
by 
Acrious
Merging technique
👍 3
1
#8 opened almost 3 years ago
by 
khoantap
How to load saved model after fine tuning
1
#1 opened about 3 years ago
by odellus
"LayerNormKernelImpl" not implemented for 'Half'
5
#40 opened almost 4 years ago
by 
Ringerill
delete this
2
#8 opened about 4 years ago
by odellus