Victor Major

vmajor

vmajor

AI & ML interests

Application of ML and AI to classification of physical world inputs, in particular the ability of models to generalize to unseen real world data and independently categorise new observations.

Organizations

None yet

New activity in unsloth/Qwen3-235B-A22B-128K-GGUF 6 months ago

Qwen3-235B-A22B-128K-Q8_0 does not run with vllm, or llama.cpp

#9 opened 6 months ago by

vmajor

New activity in unsloth/gemma-3-27b-it-bnb-4bit 8 months ago

I am so confused

#1 opened 8 months ago by

vmajor

New activity in unsloth/DeepSeek-R1-GGUF 9 months ago

Are the Q4 and Q5 models R1 or R1-Zero

#2 opened 10 months ago by

gng2info

New activity in deepseek-ai/DeepSeek-R1 9 months ago

Suggestion for censorship disclosure - odd responses from R1

#25 opened 10 months ago by

vmajor

Hardware requirements?

🚀 8

#19 opened 10 months ago by

JohnnieB

New activity in unsloth/DeepSeek-V3-GGUF 10 months ago

Advice on running llama-server with Q2_K_L quant

#6 opened 10 months ago by

vmajor

llama.cpp cannot load Q6_K model

#3 opened 10 months ago by

vmajor

New activity in Qwen/Qwen2.5-7B-Instruct 11 months ago

How do I make the model output JSON?

#14 opened 12 months ago by

vmajor

New activity in vmajor/Orca2-13B-selfmerge-39B almost 2 years ago

add merge tag

#1 opened almost 2 years ago by

davanstrien

New activity in vmajor/Orca2-13B-selfmerge-26B almost 2 years ago

add merge tag

#1 opened almost 2 years ago by

davanstrien

New activity in berkeley-nest/Starling-LM-7B-alpha almost 2 years ago

Pytorch format available?

#7 opened almost 2 years ago by

vmajor

New activity in google/switch-c-2048 almost 2 years ago

Thank you

#9 opened almost 2 years ago by

ehartford

New activity in jondurbin/airoboros-l2-70b-3.1.2 about 2 years ago

Ability to generalise

#1 opened about 2 years ago by

vmajor

New activity in TheBloke/guanaco-65B-GGML over 2 years ago

fp16 version

#2 opened over 2 years ago by

vmajor

New activity in google/flan-ul2 over 2 years ago

Is it possible to run this model on the CPU?

#20 opened over 2 years ago by

vmajor

New activity in bavest/fin-llama-33b-merged over 2 years ago

COVID-19?

#1 opened over 2 years ago by

vmajor

New activity in TheBloke/fin-llama-33B-GGML over 2 years ago

Still referring to COVID-19?

#1 opened over 2 years ago by

vmajor

New activity in TheBloke/stable-vicuna-13B-GPTQ over 2 years ago

stable-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors not compatible with "standard" settings

#1 opened over 2 years ago by

vmajor

Loading and interacting with Stable-vicuna-13B-GPTQ through python without webui

#6 opened over 2 years ago by

AbdouS

stable-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors not compatible with "standard" settings

#1 opened over 2 years ago by

vmajor

Victor Major

AI & ML interests

Organizations

vmajor's activity

Qwen3-235B-A22B-128K-Q8_0 does not run with vllm, or llama.cpp

I am so confused

Are the Q4 and Q5 models R1 or R1-Zero

Suggestion for censorship disclosure - odd responses from R1

Hardware requirements?

Advice on running llama-server with Q2_K_L quant

llama.cpp cannot load Q6_K model

How do I make the model output JSON?

add merge tag

add merge tag

Pytorch format available?

Thank you

Ability to generalise

fp16 version

Is it possible to run this model on the CPU?

COVID-19?

Still referring to COVID-19?

stable-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors not compatible with "standard" settings

Loading and interacting with Stable-vicuna-13B-GPTQ through python without webui

stable-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors not compatible with "standard" settings