Brandon
bhenrym14
AI & ML interests
CV by day, NLP by night.
Organizations
None yet
bhenrym14's activity
Fine-tuning framework?
1
#1 opened about 1 year ago
by
Yhyu13
Can't submit model - migtissera/SynthIA-7B-v1.3
16
#304 opened over 1 year ago
by
migtissera
![](https://cdn-avatars.huggingface.co/v1/production/uploads/647a6317555b5e199cffd5a2/PZJmfzzuM_Vo-8jFGkN_H.jpeg)
VRAM used
1
#1 opened over 1 year ago
by
shossain
How did you calcualte the perplexities for 2048 and 3072 contexts?
2
#3 opened over 1 year ago
by
Shouyi987
QLoRa model?
1
#2 opened over 1 year ago
by
totally-not-an-llm
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6464317c38083255f676ff38/N25A6tTplkgQ7hmhC8vXq.png)
Curious to know how 8k context llama2 got trained on 24gb GPU
3
#1 opened over 1 year ago
by
Praveen92y
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1677584785919-639a01816945e9ab07f80841.jpeg)
Request: A GGML edition of extended Airophin v2+.
2
#2 opened over 1 year ago
by
SabinStargem
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/TKk0SYTJxvCYG3tZPpTQt.jpeg)
Any chance for a ggml version to have a better perplexity?
2
#1 opened over 1 year ago
by
Nexesenex
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6451b24dc5d273f95482bfa4/YFUHCkSsz8vkYb9buv9GT.jpeg)
65B
12
#2 opened over 1 year ago
by
nxnhjrjtbjfzhrovwl
Line 13 in config.json is missing a comma
2
#1 opened over 1 year ago
by
Tibbnak
Uploading
1
#1 opened over 1 year ago
by
Peeepy
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63d4a400640bb0f77180091b/vegaepayjkuTcdXmB6qb_.png)