Hugging Face's logo
Yuri's picture
46 32

Yuri

TheYuriLover
Gargaz's profile picture NikolayKozloff's profile picture flashvenom's profile picture
·

AI & ML interests

None yet

Organizations

None yet

TheYuriLover's activity

New activity in leapfusion-image2vid-test/image2vid-960x544 4 months ago

Great Work

❤️ 1
6
#1 opened 4 months ago by
DrakenZA
New activity in TheYuriLover/HunyuanVideo_nfsw_lora 6 months ago

Will this work with the GGUF version of the model?

3
#1 opened 6 months ago by
Debich
New activity in city96/HunyuanVideo-gguf 6 months ago

Can you make your GGUF node compatible with torch.compile?

10
#5 opened 6 months ago by
TheYuriLover
New activity in Kijai/HunyuanVideo_comfy 6 months ago

Your node doesn't produce the same output as the official script one.

2
#1 opened 6 months ago by
TheYuriLover
New activity in TheYuriLover/flux-dev-de-distill-GGUF 8 months ago

When to expect new updated models?

1
#2 opened 8 months ago by
ryg81

Forge support and updated convert script.

3
#1 opened 8 months ago by
city96
New activity in Kijai/OpenFLUX-comfy 8 months ago

Can we expect the "fp16" version?

5
#1 opened 8 months ago by
bigcat88
New activity in Envoid/SensualNousInstructDARETIES-CATA-LimaRP-ZlossDT-SLERP-8x7B over 1 year ago

Issue with the tokenizer

2
#1 opened over 1 year ago by
intervitens
New activity in brucethemoose/Yi-34B-200K-DARE-megamerge-v8-31bpw-exl2-fiction over 1 year ago

Tokenizer of Yi Dare v5

👍 1
8
#4 opened over 1 year ago by
Nexesenex
New activity in NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF over 1 year ago

Using the new gguf quant method may result in a worse overall performance than that of the old gguf quants.

1
#2 opened over 1 year ago by
TheYuriLover
New activity in TheBloke/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF over 1 year ago

Using the new gguf quant method may result in a worse overall performance than that of the old gguf quants.
#2 opened over 1 year ago by
TheYuriLover
New activity in ikawrakow/various-2bit-sota-gguf over 1 year ago

Please 3b model rocket 2bit?

17
#1 opened over 1 year ago by
Shqmil
New activity in LoneStriker/deepseek-coder-33b-instruct-4.65bpw-h6-exl2 over 1 year ago

Charmap issue

7
#1 opened over 1 year ago by
VertexMachine
New activity in Eigeen/Xwin-LM-13B-V0.2-exl2 over 1 year ago

Can you make a 5.5 bpw?

4
#2 opened over 1 year ago by
TheYuriLover
New activity in Undi95/Xwin-LM-13B-V0.2-GGUF over 1 year ago

Can you make a Q4_K_M?

3
#1 opened over 1 year ago by
TheYuriLover
New activity in TheBloke/CodeLlama-13B-Instruct-GPTQ almost 2 years ago

thanks for all the nice models. unfortunately all CodeLlamas throw "KeyError: ‘pad_token_id’"

6
#2 opened almost 2 years ago by
DQ83
New activity in jondurbin/airoboros-l2-13b-gpt4-m2.0 almost 2 years ago

The 2.0 and m2.0 versions still feel like a QLora

7
#1 opened almost 2 years ago by
TheYuriLover
New activity in jondurbin/airoboros-l2-13b-gpt4-1.4.1 almost 2 years ago

Can't you make a finetune instead?

2
#1 opened almost 2 years ago by
TheYuriLover
New activity in jondurbin/airoboros-13b-gpt4-1.4 almost 2 years ago

Big gpt4 dataset you could use

1
#3 opened almost 2 years ago by
TheYuriLover
New activity in flashvenom/Airoboros-13B-SuperHOT-8K-4bit-GPTQ almost 2 years ago

Download corrupted/Not working

16
#1 opened almost 2 years ago by
Sergei6000