kk

kk3dmax's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in tencent/HunyuanImage-2.1 5 months ago

3.0 会出 Instruct 模型, 那么 2.1还会出 Edit 模型吗?

#9 opened 5 months ago by

kk3dmax

New activity in Qwen/Qwen3-VL-235B-A22B-Thinking 5 months ago

Output messy code with demo code.

#11 opened 5 months ago by

kk3dmax

New activity in Qwen/Qwen3-VL-235B-A22B-Instruct 5 months ago

Output messy code with demo code.

2

#10 opened 5 months ago by

kk3dmax

New activity in deepseek-ai/DeepSeek-R1-0528-Qwen3-8B 9 months ago

Tried it, but not good as expected.

5

#11 opened 9 months ago by

kk3dmax

Any plans for a Qwen3-32B model?

👍 13

7

#9 opened 9 months ago by

wanghf

New activity in deepseek-ai/DeepSeek-V3-0324 10 months ago

Feature Request: Can we have a QAT version?

👍 2

#68 opened 10 months ago by

kk3dmax

New activity in ByteDance/Hyper-SD about 1 year ago

The hyper-FLUX.1-dev-8steps-lora can not used in diffusers

👍 3

1

#74 opened about 1 year ago by

LHJ0

New activity in zer0int/LongCLIP-GmP-ViT-L-14 over 1 year ago

"Finally working: Redundant TEXT model for HF inference". Could you do the same thing for this LongClip?

7

#3 opened over 1 year ago by

kk3dmax

New activity in zer0int/CLIP-GmP-ViT-L-14 over 1 year ago

Diffusors missing config.json file

13

#3 opened over 1 year ago by

jspaun

New activity in zai-org/LongCite-llama3.1-8b over 1 year ago

Crash while loading tokenizer

5

#1 opened over 1 year ago by

legraphista

New activity in WhereIsAI/UAE-Large-V1 about 2 years ago

Will there be a 2048 token length version?

4

#7 opened about 2 years ago by

kk3dmax

New activity in Qwen/Qwen-72B-Chat-Int4 about 2 years ago

有时候会吐出 训练集文本.

10

#2 opened about 2 years ago by

kk3dmax

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 about 2 years ago

What is the ETA for Mistral-embed? And what is the max token length of this emb model?

3

#8 opened about 2 years ago by

kk3dmax

New activity in jinaai/jina-embeddings-v2-base-en about 2 years ago

Is there a ETA for large version?

👍 1

6

#31 opened about 2 years ago by

kk3dmax

New activity in BAAI/bge-reranker-large about 2 years ago

Is there a way to support > 512 token length?

8

#5 opened about 2 years ago by

kk3dmax

New activity in Muennighoff/SGPT-5.8B-weightedmean-msmarco-specb-bitfit over 2 years ago

TypeError: Pooling.__init__() got an unexpected keyword argument 'pooling_mode_weightedmean_tokens'

2

#4 opened over 2 years ago by

kk3dmax

New activity in BAAI/bge-large-en over 2 years ago

How to set the max length from 512 to 2048?

3

#11 opened over 2 years ago by

kk3dmax

New activity in TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ over 2 years ago

ModuleNotFoundError: No module named 'transformers_modules.TheBloke.WizardLM-33B-V1'

4

#2 opened over 2 years ago by

kk3dmax

ModuleNotFoundError: No module named 'transformers_modules.TheBloke.WizardLM-33B-V1'

4

#2 opened over 2 years ago by

kk3dmax

ModuleNotFoundError: No module named 'transformers_modules.TheBloke.WizardLM-33B-V1'

4

#2 opened over 2 years ago by

kk3dmax