DataSoul's picture

DataSoul

DataSoul

·

AI & ML interests

AI User

Recent Activity

reacted to MonsterMMORPG's post with 🔥 3 days ago

I just pushed another amazing update to our Wan 2.1 APP. LoRA loading for 14B Wan 2.1 models were taking over 15 minutes. Optimized to take only few seconds now. Fully supports RTX 5000 series and fully optimized for both VRAM and RAM. Our APP here : https://www.patreon.com/posts/wan-2-1-ultra-as-123105403 Tutorial 1 : https://youtu.be/hnAhveNy-8s Tutorial 2 : https://youtu.be/ueMrzmbdWBg It is also pushed to the original repo you can see pull request here : https://github.com/modelscope/DiffSynth-Studio/pull/442

liked a model 4 days ago

sesame/csm-1b

updated a model 4 days ago

DataSoul/QAQ-32B-merge4-SEC

View all activity

Organizations

None yet

DataSoul's activity

New activity in DataSoul/QwQ-32B-uncensored-Q5_K_S-GGUF 4 days ago

Seeking the non-GGUF version (full)

#2 opened 4 days ago by

New activity in DataSoul/Rombo-LLM-V3.1-QWQ-32b-abliterated-Q5_K_S-GGUF 4 days ago

Well done

#1 opened 4 days ago by

New activity in DataSoul/QwQ-32B-uncensored-Q5_K_S-GGUF 5 days ago

QwQ-32B Model’s Resistance

#1 opened 5 days ago by

New activity in DataSoul/QAQ-32B-merge1 5 days ago

A failed half-finished merge.

#1 opened 5 days ago by

New activity in DataSoul/Sky-T1-32B-Flash-abliterated-merge1-Q4_K_M-GGUF 6 days ago

Test results on the q4km of this model: abliterated appears to be effective, but it is unstable.

#1 opened 6 days ago by

New activity in DataSoul/Sky-T1-32B-Flash-abliterated-merge1 6 days ago

Test results on the q4km of this model: abliterated appears to be effective, but it is unstable.

#1 opened 6 days ago by

New activity in DataSoul/MwM-7B-CoT-Merge1 about 1 month ago

Model test results

#1 opened about 1 month ago by

New activity in mradermacher/Mistral-Small-24B-Instruct-2501-i1-GGUF about 1 month ago

Try to Fixing Template Rendering Issues in LM Studio for GGUF Models

#1 opened about 1 month ago by

New activity in DataSoul/DwQ-R1-32B-v0.1 about 2 months ago

Still Failing Merge Attempts

#1 opened about 2 months ago by

New activity in zetasepic/Qwen2.5-32B-Instruct-abliterated-v2 about 2 months ago

question

#1 opened about 2 months ago by

New activity in Steelskull/L3.3-MS-Nevoria-70b about 2 months ago

Produces Garbige

#3 opened about 2 months ago by

New activity in deepseek-ai/DeepSeek-R1-Distill-Llama-70B about 2 months ago

SFT (Non-RL) distillation is this good on a sub-100B model?

#2 opened about 2 months ago by

New activity in Qwen/QwQ-32B-Preview 3 months ago

🖐️🖐️ Can we please get a 7B reasoning model? 😎🤗🤗😍

#50 opened 3 months ago by

New activity in DataSoul/Ministral-3b-instruct-Q5_K_M-GGUF 5 months ago

Oh, this isn't the new model; I just realized its original model is an old one from 7 months ago.

#1 opened 5 months ago by

New activity in arcee-ai/SuperNova-Medius 5 months ago

llama.cpp convert problem report(about `tokenizer.json`)

#2 opened 5 months ago by

New activity in dnhkng/RYS-Phi-3-medium-4k-instruct 7 months ago

There is an error in the README.

#1 opened 7 months ago by

New activity in dranger003/c4ai-command-r-plus-iMat.GGUF 11 months ago

Can we get a Q4 without the IMat?

#14 opened 11 months ago by

New activity in DataSoul/chinese-imatrix-data-and.dat 11 months ago

[bot] Conversion to Parquet

#1 opened 11 months ago by

parquet-converter

New activity in CohereForAI/c4ai-command-r-v01 11 months ago

VRAM

#53 opened 11 months ago by

New activity in CausalLM/34b-beta 11 months ago

Feel great！

#3 opened about 1 year ago by