Koes Nandar's picture

Koes Nandar

koesn

·

AI & ML interests

LLM Quantizing, Fine-Tuning, Law AI, Automation

Organizations

None yet

koesn's activity

New activity in OpenPipe/Hermes-2-Theta-Llama-3-8B-32k 8 months ago

exl2 quants?

#1 opened 8 months ago by

New activity in NousResearch/Hermes-2-Theta-Llama-3-70B 8 months ago

Exl2 quants

#1 opened 9 months ago by

New activity in sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0 9 months ago

Nice job!

#4 opened 9 months ago by

New activity in gradientai/Llama-3-8B-Instruct-262k 9 months ago

ITS NOT REAL

#15 opened 11 months ago by

New activity in turboderp/command-r-v01-35B-exl2 11 months ago

What's the VRAM usage?

#2 opened 11 months ago by

New activity in LoneStriker/Meta-Llama-3-70B-Instruct-3.0bpw-h6-exl2 11 months ago

Lines end with "assistant"

#1 opened 11 months ago by

New activity in Dracones/Midnight-Miqu-70B-v1.5_exl2_3.0bpw 11 months ago

2.75 bpw high EQ bench

#1 opened 11 months ago by

New activity in abacusai/Smaug-Mixtral-v0.1 11 months ago

Great combo

#7 opened 11 months ago by

New activity in bartowski/Smaug-Mixtral-v0.1-exl2 11 months ago

Would love 5.0bpw

#2 opened 11 months ago by

New activity in LoneStriker/34b-beta-5.0bpw-h6-exl2 11 months ago

Very good on complex prompt

#1 opened 11 months ago by

New activity in alchemonaut/BoreanGale-70B 12 months ago

exl2 please

#3 opened 12 months ago by

New activity in LoneStriker/miqu-1-70b-sf-3.0bpw-h6-exl2 12 months ago

This model run on 3x3060 at 32k contexts

#1 opened 12 months ago by

New activity in koesn/ZySec-7B-v1-GGUF 12 months ago

Updated version

#1 opened 12 months ago by

New activity in bardsai/jaskier-7b-dpo-v6.1 about 1 year ago

GGUF?

#1 opened about 1 year ago by

New activity in senseable/garten2-7b about 1 year ago

Smart and Cohesive

#1 opened about 1 year ago by

New activity in CalderaAI/Naberius-7B about 1 year ago

Best for summarizing long context.

#2 opened about 1 year ago by

New activity in TheBloke/Yi-34B-GGUF over 1 year ago

Can the yi-34b.Q3_K_S.gguf model be set up on Mac M1 with 16GB of memory?

#7 opened over 1 year ago by

New activity in Ichsan2895/Merak-7B-v4-GGUF over 1 year ago

Rikues Basis Mistral

#1 opened over 1 year ago by

New activity in asyafiqe/Merak-7B-v3-Mini-Orca-Indo-GGUF over 1 year ago

Model Q8 File Corrupt

#1 opened over 1 year ago by

New activity in Undi95/Mistral-11B-CC-Air-GGUF over 1 year ago

Coherence in Exhaustive Tests on 8k Context

#1 opened over 1 year ago by