Ben Shankles PRO

warshanks's activity

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

New activity in Tongyi-MAI/Z-Image 3 months ago

README Typo?

2

#8 opened 3 months ago by

warshanks

New activity in unsloth/GLM-4.6V-Flash-GGUF 5 months ago

Update with vision support

👍 2

4

#3 opened 5 months ago by

warshanks

New activity in inclusionAI/Ring-mini-2.0-GGUF 7 months ago

Official llama.cpp support merged

1

#1 opened 7 months ago by

warshanks

New activity in LiquidAI/LFM2-350M-ENJP-MT-GGUF 8 months ago

Sensitive to Quantization

2

#1 opened 8 months ago by

warshanks

New activity in warshanks/Hermes-4-14B-AWQ 8 months ago

Improve model card: Add pipeline tag, correct base model, and add code/project links

2

#1 opened 8 months ago by

nielsr

New activity in OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview 8 months ago

Issue with llama.cpp

18

#3 opened 8 months ago by

wsbagnsv1

New activity in warshanks/medgemma-4b-it 8 months ago

Avoid demo to be embedded in other sites

#8 opened 8 months ago by

osanseviero

New activity in unsloth/gpt-oss-20b-GGUF 9 months ago

Feature Request: Disable reasoning

👀 1

3

#22 opened 9 months ago by

SomAnon

New activity in warshanks/Qwen3-4B-Thinking-2507-AWQ 9 months ago

Quantization Script

2

#1 opened 9 months ago by

kawchar85

New activity in unsloth/gpt-oss-20b-bnb-4bit 9 months ago

Model size?

2

#1 opened 9 months ago by

warshanks

New activity in mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit 9 months ago

Convert in bf16 or fp16?

2

#2 opened 9 months ago by

remember2015

New activity in lingshu-medical-mllm/Lingshu-32B 11 months ago

Missing preprocessor_config.json

5

#2 opened 11 months ago by

warshanks

New activity in mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit 11 months ago

tokenizer_config.json is not correct

12

#1 opened 11 months ago by

depasquale

New activity in mlx-community/DeepSeek-R1-0528-Qwen3-8B-8bit 11 months ago

chat_template in tokenizer_config.json?

1

#1 opened 11 months ago by

nff

New activity in mlx-community/medgemma-27b-text-it-bf16 11 months ago

mlx-community/medgemma-27b-text-it-bf16 is entirely broken on mlx-lm

👍 1

8

#1 opened 12 months ago by

sjug

New activity in mlx-community/medgemma-4b-it-4bit 12 months ago

Convert model with mlx-vlm instead of mlx-lm to enable vision capabilities

3

#1 opened 12 months ago by

ljoana

Convert model with mlx-vlm instead of mlx-lm to enable vision capabilities

3

#1 opened 12 months ago by

ljoana

New activity in mlx-community/medgemma-27b-text-it-bf16 12 months ago

mlx-community/medgemma-27b-text-it-bf16 is entirely broken on mlx-lm

👍 1

8

#1 opened 12 months ago by

sjug