Brandon's picture

12 6

Brandon

bhenrym14

·

AI & ML interests

CV by day, NLP by night.

Organizations

None yet

bhenrym14's activity

New activity in bhenrym14/platypus-yi-34b 12 months ago

Fine-tuning framework?

#1 opened about 1 year ago by

New activity in open-llm-leaderboard/open_llm_leaderboard about 1 year ago

Can't submit model - migtissera/SynthIA-7B-v1.3

#304 opened about 1 year ago by

New activity in bhenrym14/airoboros-l2-13b-2.1-YaRN-64k about 1 year ago

VRAM used

#1 opened about 1 year ago by

New activity in bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ about 1 year ago

How did you calcualte the perplexities for 2048 and 3072 contexts?

#3 opened over 1 year ago by

New activity in bhenrym14/airophin-13b-pntk-16k-fp16 about 1 year ago

QLoRa model?

#2 opened over 1 year ago by

totally-not-an-llm

New activity in bhenrym14/airophin-v2-13b-PI-8k-fp16 about 1 year ago

Curious to know how 8k context llama2 got trained on 24gb GPU

#1 opened over 1 year ago by

New activity in bhenrym14/airophin-v2-13b-PI-8k-fp16 over 1 year ago

Request: A GGML edition of extended Airophin v2+.

#2 opened over 1 year ago by

New activity in bhenrym14/airophin-13b-pntk-16k-fp16 over 1 year ago

Any chance for a ggml version to have a better perplexity?

#1 opened over 1 year ago by

New activity in bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ over 1 year ago

65B

#2 opened over 1 year ago by

nxnhjrjtbjfzhrovwl

New activity in bhenrym14/airoboros-7b-gpt4-1.4.1-lxctx-PI-16384-GPTQ over 1 year ago

Line 13 in config.json is missing a comma

#1 opened over 1 year ago by

New activity in bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-fp16 over 1 year ago

Uploading

#1 opened over 1 year ago by

New activity in bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ over 1 year ago

4bit

#1 opened over 1 year ago by