null's picture

30 1 8

null

mzbac

·

mzbac

AI & ML interests

None yet

Recent Activity

liked a model about 22 hours ago

mlx-community/Qwen3-235B-A22B-4bit-DWQ

updated a model 5 days ago

mlx-community/Qwen3-4B-4bit-DWQ-calibration-1332

published a model 5 days ago

mlx-community/Qwen3-4B-4bit-DWQ-calibration-1332

View all activity

Organizations

mzbac's activity

New activity in mlx-community/Qwen3-30B-A3B-4bit-DWQ-0508 7 days ago

What distinguishes this model from another MLX-Community/Qwen3-30B-A3B-4bit-DWQ?

#1 opened 7 days ago by

New activity in mlx-community/DeepSeek-V2-Lite-Chat-4bit-mlx 9 months ago

Fine tuning with Lora does not support this model

#4 opened 9 months ago by

New activity in mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx 9 months ago

The repository for mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx contains custom code which must be executed to correctly load the model

#2 opened 9 months ago by

New activity in mlx-community/DeepSeek-V2-Lite-Chat-4bit-mlx 10 months ago

mlx-lm 0.16 not found

#2 opened 10 months ago by

Upload folder using huggingface_hub

#1 opened 10 months ago by

New activity in mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx 10 months ago

Upload folder using huggingface_hub

#1 opened 10 months ago by

New activity in mlx-community/Yi-34B-Chat-hf-4bit-mlx 11 months ago

update license in readme.md

#1 opened 11 months ago by

New activity in mzbac/function-calling-phi-3-format-v1.1 about 1 year ago

[bot] Conversion to Parquet

#1 opened about 1 year ago by

parquet-converter

New activity in mzbac/function-calling-llama-3-format-v1.1 about 1 year ago

[bot] Conversion to Parquet

#1 opened about 1 year ago by

parquet-converter

New activity in mzbac/glaive-function-calling-v2-llama-3-format about 1 year ago

[bot] Conversion to Parquet

#1 opened about 1 year ago by

parquet-converter

New activity in mlx-community/Mixtral-8x7B-Instruct-v0.1-hf-4bit-mlx about 1 year ago

can you plesse share how to make this version?

#3 opened about 1 year ago by

Parameters

#1 opened about 1 year ago by

New activity in mlx-community/Mixtral-8x7B-v0.1-hf-4bit-mlx about 1 year ago

Why this model is extremely slow on M1 Max with 32GB RAM

#3 opened about 1 year ago by

New activity in mlx-community/OLMo-7B-hf-4bit-mlx over 1 year ago

where is OLMo-7B-hf-4bit-mlx stored?

#1 opened over 1 year ago by

New activity in miqudev/miqu-1-70b over 1 year ago

Add miku.mp4 to the readme

#7 opened over 1 year ago by

New activity in mlabonne/phixtral-4x2_8 over 1 year ago

Update the model type to make it compatible with mlx-lm's model mapping.

#14 opened over 1 year ago by

New activity in mlx-community/Mixtral-8x7B-v0.1-hf-4bit-mlx over 1 year ago

Token generation limit?

#1 opened over 1 year ago by

New activity in mzbac/yayi2-30b-guanaco-gguf over 1 year ago

Have you gotten this to work somehow?

#1 opened over 1 year ago by

New activity in wenge-research/yayi2-30b over 1 year ago

Fix the configuration for num_key_value_heads so that current tools will be supported.

#6 opened over 1 year ago by

fix AttributeError: 'YayiTokenizer' object has no attribute 'sp_model'

#5 opened over 1 year ago by