陳能弘

Gavin-chen's activity

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

New activity in RikiyaT/Qwen3.5-0.8B-weight-space-programming about 5 hours ago

9B 、35B A3B or 27B please

#3 opened about 5 hours ago by

Gavin-chen

New activity in burner22/numbat 6 days ago

If You Fix It Like This, It Actually Looks Plausible — A Proposal on LatentMoE Projection and Depth Scaling for the 14T Numbat Architecture.

🔥 8

7

#39 opened 6 days ago by

Gavin-chen

I want to research involving pre-training. do not delete

2

#27 opened 6 days ago by

testamentaddress01

New activity in Nanbeige/Nanbeige4.3-33B 14 days ago

Can we find out about the plans related to the release of the 3B student model?

#15 opened 14 days ago by

Gavin-chen

New activity in unsloth/Ornith-1.5-122B-GGUF 16 days ago

Is mtp support?

1

#7 opened 18 days ago by

tarjintor

New activity in openbmb/MiniCPM5-1B-GGUF about 2 months ago

Context is 4096, not the 131k advertised...

2

#9 opened about 2 months ago by

liar666

New activity in deepgrove/maple-preview-GGUF about 2 months ago

where are the benchmarks?

1

#9 opened about 2 months ago by

JNK333

New activity in deepseek-ai/DeepSeek-V4.1-Flash about 2 months ago

Bro....500多B的Flash，8卡H200已经上不了桌了吗[cry]

9

#16 opened about 2 months ago by

Saito-Karuha

New activity in openbmb/MiniCPM5-2B 2 months ago

Can you make a 3:1 SWA version or linear attention version?

🔥 2

2

#6 opened 2 months ago by

Gavin-chen

New activity in Akahsizrr/Fuse-2-MoE-BF16 2 months ago

May I as

3

#1 opened 2 months ago by

wh-wh-wh

New activity in zai-org/GLM-5.3-Flash 2 months ago

GLM 5.3 Flash Lite idea

15

#13 opened 2 months ago by

ChessVania

New activity in unsloth/Qwen3.8-27B-GGUF 3 months ago

Will any other model get UD3 update?

➕👀 3

1

#108 opened 3 months ago by

Gavin-chen

New activity in redashes/Qwen3.8-27B-BF16-SSMFIX 3 months ago

can you make gguf?

6

#1 opened 3 months ago by

Gavin-chen

New activity in Qwen/Qwen3.8-27B 3 months ago

Why Qwen3.8-27B overthinks? Here the reason and partial fix confirmed by benchmarks.

❤️👀 25

29

#76 opened 3 months ago by

LuffyTheFox

New activity in unsloth/Qwen3.8-27B-GGUF 3 months ago

Why UD-Q2_K_XL has IQ1_M SSM alpha/beta and only token_embd use 2bit quant? It's a Q2 GGUF!

➕ 2

#36 opened 3 months ago by

Gavin-chen

New activity in Qwen/Qwen3.8-2.4T-A95B 3 months ago

I just checked Qwen3.8-2.4T-A95B for singular matrices and exploded condition numbers

👍 2

6

#29 opened 3 months ago by

LuffyTheFox

can you do 99999999999999B-A0.00000000000001B

🚀 2

5

#31 opened 3 months ago by

inikishev

New activity in Nanbeige/Nanbeige4.2-3B 3 months ago

Can't use bnb 4bit to load your model.

#11 opened 4 months ago by

Gavin-chen

New activity in prism-ml/Bonsai-27B-gguf 4 months ago

Why so many empty response?

1

#15 opened 4 months ago by

Gavin-chen

New activity in zai-org/GLM-5.2 4 months ago

Nice Model, can beat Gemini3.1pro,sonnet5 , and GPT-5.5 instant

👍 2

1

#32 opened 4 months ago by

Gavin-chen