Sam Vance's picture

19 1 3

Sam Vance

Samvanity

AI & ML interests

None yet

Organizations

None yet

Samvanity's activity

New activity in ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1 3 months ago

what is the expected effective context length for this model?

#1 opened 3 months ago by

New activity in bartowski/L3-70B-Euryale-v2.1-GGUF 7 months ago

IQ2_XS

#1 opened 7 months ago by

New activity in mradermacher/L3-MS-Astoria-70b-i1-GGUF 7 months ago

even smaller quants

#1 opened 7 months ago by

New activity in bartowski/openchat-3.6-8b-20240522-GGUF 7 months ago

exl2 vs GGUF at 8bit

#2 opened 7 months ago by

New activity in PrunaAI/Meta-Llama-3-70B-Instruct-GGUF-smashed 8 months ago

what does smashed mean?

#1 opened 8 months ago by

New activity in mgoin/Meta-Llama-3-70B-Instruct-Marlin 8 months ago

What is Marlin?

#1 opened 8 months ago by

New activity in Kooten/DaringMaid-20B-V1.1 9 months ago

Incredible - the best 20b model I've used

#2 opened 9 months ago by

New activity in Kquant03/NurseButtercup-4x7B-bf16 9 months ago

Unable to create exl2 quant for this model

#1 opened 9 months ago by

New activity in bartowski/airoboros-34b-3.2-exl2 10 months ago

Can you make a 4.65 bpw?

#1 opened 10 months ago by

New activity in Bakanayatsu/NeuralHermes-2.5-Mistral-7B-laser-imatrix-GGUF 10 months ago

what does imatrix do to the model?

#1 opened 10 months ago by

New activity in ibivibiv/alpaca-dragon-72b-v1 11 months ago

what is the minimum Hardware requirement?

#3 opened 11 months ago by

New activity in LoneStriker/dolphin-2.7-mixtral-8x7b-3.75bpw-h6-exl2 11 months ago

What calibration dataset did you use to convert it?

#1 opened 11 months ago by

New activity in second-state/Dolphin-2.7-mixtral-8x7b-GGUF 11 months ago

How is this different from TheBloke's quants?

#1 opened 11 months ago by

New activity in Kooten/FlatDolphinMaid-8x7B-4bpw-exl2 11 months ago

using context above 4096 - need to set compress_pos_emb above 1?

#1 opened 12 months ago by

New activity in NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss 11 months ago

Recommended settings?

#1 opened 12 months ago by

New activity in LoneStriker/Noromaid-v0.1-mixtral-8x7b-Instruct-v3-4.0bpw-h6-exl2 12 months ago

Noromaid updated to v0.4

#1 opened 12 months ago by

New activity in LoneStriker/openchat-3.5-0106-6.0bpw-h6-exl2 12 months ago

Wrong eos_token_id set in config.json

#1 opened 12 months ago by

New activity in Undi95/Llamix2-MLewd-4x13B about 1 year ago

What is the context length of this model?

#4 opened about 1 year ago by

New activity in Gryphe/MythoMax-L2-13b about 1 year ago

Whats the maximum context length for this model?

#19 opened about 1 year ago by