Brett S's picture

26 2

Brett S

cleverest

·

AI & ML interests

None yet

Organizations

None yet

cleverest's activity

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 8 months ago

Is there a working/quantized/exl2 (etc) version that will fit on a single 24GB video card (4090)

#170 opened 8 months ago by

New activity in TheBloke/WizardCoder-Python-34B-V1.0-GGUF about 1 year ago

Single 4090 system

#3 opened about 1 year ago by

New activity in LaconicAI/falcon-40b-instruct-gptq over 1 year ago

Will this model work in OobaBooga (text-generation-webui) on a single 4090 card system with any settings?

#1 opened over 1 year ago by

New activity in TheBloke/galpaca-30B-GPTQ over 1 year ago

which one do I choose? Thanks...

#4 opened over 1 year ago by

New activity in twilightBOO/pov-skin-textures-dreamlike-r34-v2 over 1 year ago

MODEL FILE

#2 opened over 1 year ago by

New activity in TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ over 1 year ago

Tips on running on 3090 24gb VRAM?

#1 opened over 1 year ago by

New activity in TheBloke/samantha-1.1-llama-33B-GPTQ over 1 year ago

Using Oogabooga and a 4090 (windows install) - which model of the two available do I use?

#1 opened over 1 year ago by

New activity in TheBloke/chronos-33b-GPTQ over 1 year ago

Is there any chance of getting this into a 4bit quantized (GPTQ as well?) version?

#1 opened over 1 year ago by

New activity in Aeala/Alpaca-elina-65b-ggml over 1 year ago

Oobagooda error, changed from a working 5.1 model to 4.0 and now I can no longer load the model at all

#1 opened over 1 year ago by

New activity in zombihed/ZombiMix-v6 over 1 year ago

Any description of this model anywhere? Changes from V7 to V9?

#1 opened over 1 year ago by

New activity in TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ over 1 year ago

In text-generation-webui I don't see where to set the LOADER to ExLlama

#1 opened over 1 year ago by

New activity in allenai/tulu-30b over 1 year ago

Any feedback on what this model is particularly good at? Not good at?

#1 opened over 1 year ago by

New activity in Zicara/OPT-30B-Erebus-4bit-128g over 1 year ago

Did anyone manage to run it with oobabooga? It's very slow

#7 opened over 1 year ago by

New activity in CalderaAI/30B-Lazarus-GPTQ4bit over 1 year ago

Can you please provide the quantize_config.json file?

#1 opened over 1 year ago by

New activity in Zicara/OPT-30B-Erebus-4bit-128g over 1 year ago

Why is this model so sloooooooow in text-generation-webui?

#6 opened over 1 year ago by

New activity in benjicolby/WizardLM-30B-Guanaco-SuperCOT-GPTQ-4bit over 1 year ago

RTX 4090 Windows system with 96GB of RAM - I cannot get this model to load in OobaBooga - ERROR

#1 opened over 1 year ago by

New activity in Monero/WizardLM-SuperCOT-StoryTelling-30b-4bit over 1 year ago

4090 test with OobaBooga (In Windows) fails to load the model

#2 opened over 1 year ago by

New activity in askmyteapot/GPT4-x-AlpacaDente2-30b-4bit over 1 year ago

What are the best 4090 settings to use for this in OobaBooga / Text-Generation-WebUI?

#3 opened over 1 year ago by

Great speed, great answers, great work. But only runs limited on rtx 4090...?

#2 opened over 1 year ago by

New activity in Aeala/VicUnlocked-alpaca-65b-GGML over 1 year ago

4090 system, i9-13900k, 96GB RAM - I could not launch this model (trying the 4.0 GGML one)

#1 opened over 1 year ago by