Timon Käch's picture

Timon Käch

CyberTimon

·

cybertimon

AI & ML interests

ai text generation

Organizations

New activity in Qwen/Qwen3-32B 7 months ago

Feedback: It's a good model, however it hallucinates very badly at local facts (Germany)

#12 opened 7 months ago by

New activity in unsloth/Qwen3-30B-A3B-GGUF 7 months ago

`UD-Q4_K_XL` or `Q4_K_M`?

#6 opened 7 months ago by

New activity in DavidAU/Command-R-01-Ultra-NEO-V1-35B-IMATRIX-GGUF over 1 year ago

Amazing, thank you so much. Small question :)

#2 opened over 1 year ago by

New activity in TIGER-Lab/Mantis-8B-siglip-llama3 over 1 year ago

GGUF Quants?

#1 opened over 1 year ago by

New activity in dphn/dolphin-2.9-llama3-8b-256k over 1 year ago

What is 256k?

#1 opened over 1 year ago by

New activity in Vezora/Mistral-22B-v0.1 over 1 year ago

Brain issues

#4 opened over 1 year ago by

New activity in QQGYLab/ELLA over 1 year ago

I Guess I'll Be "That Guy"... SDXL?

#2 opened over 1 year ago by

New activity in mistral-community/Mixtral-8x22B-v0.1 over 1 year ago

We are working on creating a single 22b from this model

#5 opened over 1 year ago by

New activity in databricks/dbrx-base over 1 year ago

Release weights of smaller Experimental MoE

#12 opened over 1 year ago by

New activity in Lykon/dreamshaper-xl-lightning over 1 year ago

Pattern

#3 opened over 1 year ago by

New activity in TheBloke/CapybaraHermes-2.5-Mistral-7B-GPTQ over 1 year ago

Whats up with TheBloke ?

#2 opened over 1 year ago by

New activity in wangfuyun/AnimateLCM almost 2 years ago

Not working

#2 opened almost 2 years ago by

New activity in vikhyatk/moondream1 almost 2 years ago

Quants

#1 opened almost 2 years ago by

New activity in openchat/openchat_3.5 almost 2 years ago

Hallucinations

#2 opened about 2 years ago by

New activity in DiscoResearch/DiscoLM-70b almost 2 years ago

Fix Stop Tokens

#2 opened almost 2 years ago by

New activity in CausalLM/72B-preview-llamafied-qwen-llamafy almost 2 years ago

Exciting, how can you do that so quickly?

#1 opened almost 2 years ago by

KnutJaegersberg

New activity in Qwen/Qwen-14B almost 2 years ago

It would be useful if someone spent the time to convert the tokenizer to gpt2 HF format

#9 opened almost 2 years ago by

KnutJaegersberg

New activity in VAGOsolutions/SauerkrautLM-7b-HerO almost 2 years ago

Training dataset + Hyperparamters

#1 opened almost 2 years ago by

New activity in coqui/XTTS-v2 almost 2 years ago

Support for swiss german - please!

#15 opened almost 2 years ago by

New activity in deepseek-ai/deepseek-coder-33b-instruct almost 2 years ago

tokenizer.model

#6 opened about 2 years ago by