Wolfram Ravenwolf's picture

Wolfram Ravenwolf

wolfram

·

https://ko-fi.com/wolframravenwolf

AI & ML interests

Local LLMs

Recent Activity

upvoted an article about 1 month ago

Welcome to Inference Providers on the Hub 🔥

liked a model about 2 months ago

deepseek-ai/DeepSeek-R1

liked a model about 2 months ago

openbmb/MiniCPM-o-2_6

View all activity

Organizations

wolfram's activity

New activity in blog-explorers/README 2 months ago

[Support] Community Articles

#5 opened 12 months ago by

New activity in turboderp/Llama-3.1-70B-Instruct-exl2 7 months ago

The tokenizer has changed just fyi

#2 opened 8 months ago by

New activity in mistralai/Mistral-7B-Instruct-v0.3 10 months ago

no system message?

#14 opened 10 months ago by

tokenizer.model and tokenizer.model.v3 are identical

#15 opened 10 months ago by

New activity in nvidia/Llama3-ChatQA-1.5-70B 10 months ago

Concerns regarding Prompt Format

#1 opened 10 months ago by

New activity in wolfram/miquliz-120b-v2.0 12 months ago

Strange observation: model becomes super horny in ST's MinP mode

#7 opened 12 months ago by deleted

New activity in wolfram/miquliz-120b-v2.0-GGUF 12 months ago

Upload folder using huggingface_hub

#3 opened 12 months ago by

New activity in wolfram/miquliz-120b-v2.0 12 months ago

VRAM Estimates

#3 opened about 1 year ago by

Merge method

#4 opened about 1 year ago by

New activity in wolfram/miqu-1-103b about 1 year ago

Can't wait to test

#4 opened about 1 year ago by

Kindly asking for quants

#2 opened about 1 year ago by

New activity in LoneStriker/miqu-1-103b-3.5bpw-h6-exl2 about 1 year ago

Update README.md

#1 opened about 1 year ago by

New activity in LoneStriker/miqu-1-103b-3.0bpw-h6-exl2 about 1 year ago

Update README.md

#1 opened about 1 year ago by

New activity in LoneStriker/miqu-1-103b-2.4bpw-h6-exl2 about 1 year ago

Update README.md

#1 opened about 1 year ago by

New activity in wolfram/miquliz-120b-v2.0 about 1 year ago

GPTQ / AWQ

#2 opened about 1 year ago by

New activity in wolfram/miqu-1-120b about 1 year ago

Guidance on GPU VRAM Split?

#3 opened about 1 year ago by

New activity in wolfram/miqu-1-103b about 1 year ago

Upload folder using huggingface_hub

#1 opened about 1 year ago by

New activity in wolfram/miquliz-120b-v2.0-3.0bpw-h6-exl2 about 1 year ago

Very interesting that miqu will give 16k context work even only first layer and last layer

#2 opened about 1 year ago by

New activity in wolfram/miquliz-120b-v2.0-GGUF about 1 year ago

iMatrix, IQ2_XS & IQ2_XXS

#2 opened about 1 year ago by

New activity in wolfram/miqu-1-120b about 1 year ago

Performance

#2 opened about 1 year ago by

KnutJaegersberg