Joe

JoeSmith245's activity

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

New activity in ubergarm/Step-3.5-Flash-GGUF 2 days ago

IQ2_KS model merging failed

2

#4 opened 2 days ago by

lan0004

New activity in Qwen/Qwen3-Coder-Next 4 days ago

Very specific json formatting issue in tool calls

➕ 1

2

#14 opened 4 days ago by

JoeSmith245

model with thinking?

➕ 2

5

#5 opened 6 days ago by

pypry

AWQ quantization

👀 1

8

#1 opened 6 days ago by

dr-e

New activity in unsloth/Qwen3-Coder-Next-GGUF 5 days ago

Feb 4: Qwen3-Coder-Next GGUFs reuploaded - much better outputs!

🤗 👍 14

23

#5 opened 5 days ago by

danielhanchen

just curious, why the lack of <thinking> response?

3

#4 opened 5 days ago by

YellowjacketGames

New activity in mistralai/Devstral-Small-2-24B-Instruct-2512 11 days ago

Question about Mistral Vibe being recommended

3

#8 opened 2 months ago by

electroglyph

Devstral for non-agentic tasks?

3

#3 opened 2 months ago by

ooooh-nooooo

New activity in unsloth/Devstral-2-123B-Instruct-2512-GGUF 13 days ago

mmproj?

10

#1 opened 2 months ago by

aaron-newsome

User/assistant message pairing broken

👍 1

1

#3 opened about 2 months ago by

tyler94

New activity in nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 about 2 months ago

Beware: doesn't work on compute capability 8.6, only on 8.9 and newer

2

#1 opened about 2 months ago by

DrRos

New activity in nisten/deepseek-r1-bitnet-gguf-experiment1 3 months ago

Does it work? Model card? Benchmarks?

#3 opened 3 months ago by

JoeSmith245

New activity in TheDrummer/Valkyrie-49B-v2 3 months ago

Which template?

3

#1 opened 4 months ago by

Topsy1

New activity in microsoft/MAI-DS-R1 10 months ago

Great work! How about the distils?

#2 opened 10 months ago by

JoeSmith245

upvoted a collection 10 months ago

MAI-DS-R1

Collection

MAI-DS-R1 is a DeepSeek-R1 reasoning model that has been post-trained by the Microsoft AI team. • 2 items • Updated May 1, 2025 • 14

New activity in meta-llama/Llama-3.1-8B-Instruct over 1 year ago

Update chat template

👍 1

5

#53 opened over 1 year ago by

Rocketknight1

liked a model almost 2 years ago

xai-org/grok-1

Text Generation • Updated Mar 28, 2024 • 236 • 2.39k

New activity in vicuna4all/vicuna4all over 2 years ago

What exactly is this?

2

#1 opened almost 3 years ago by

underlines

New activity in bigscience/bloom about 3 years ago

Bloom-176B on Google Colab

5

#63 opened over 3 years ago by

thisisanshgupta