Jeonghyun Lee

sigjhl's activity

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

New activity in google/gemma-4-31B-it 4 months ago

Update chat_template.jinja to address JSON Schema shapes that do not expose their meaning through a direct top-level type

👍 7

#91 opened 4 months ago by

sigjhl

Update chat_template.jinja

#90 opened 4 months ago by

sigjhl

Preserve anyOf/$ref/$defs in Gemma tool declarations

#89 opened 4 months ago by

sigjhl

Possible chat_template.jinja issue: nullable $ref tool schemas are rendered as empty types

1

#87 opened 4 months ago by

sigjhl

Template fix: Preserve anyOf/$ref/$defs in Gemma tool declarations

#88 opened 4 months ago by

sigjhl

New activity in openai/gpt-oss-20b about 1 year ago

What is the metal/model.bin for?

3

#95 opened about 1 year ago by

sigjhl

New activity in lmstudio-community/gpt-oss-20b-MLX-8bit about 1 year ago

The base model is 4bit (“native MXFP4 quantization”), is it useful to upscale to 8bit?

👍🔥 4

4

#1 opened about 1 year ago by

datatap

New activity in mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit-DWQ about 1 year ago

Update README.md

#1 opened about 1 year ago by

sigjhl

New activity in sigjhl/gemma-2-9b-it-WPO-HB-8bit almost 2 years ago

Upload folder using huggingface_hub

2

#1 opened almost 2 years ago by

sigjhl

New activity in sigjhl/gemma-2-9b-it-WPO-HB-4bit almost 2 years ago

[WIP] Upload folder using huggingface_hub (multi-commit 86cb151215396b32b35aa03146c447a3e2d2c31f48247c523e3fe26cbe846c43)

#1 opened almost 2 years ago by

sigjhl

New activity in sigjhl/Llama-3.1-Minitron-4B-Width-Base_mlx_q8 almost 2 years ago

Upload folder using huggingface_hub

2

#1 opened almost 2 years ago by

sigjhl

Upload folder using huggingface_hub

2

#1 opened almost 2 years ago by

sigjhl