Hugging Face's logo
null's picture
29 1 7

null

mzbac
FallaxAura's profile picture saken-tukenov's profile picture Nexesenex's profile picture
·

AI & ML interests

None yet

Organizations

MLX Community's profile picture

mzbac's activity

New activity in mlx-community/DeepSeek-V2-Lite-Chat-4bit-mlx 3 months ago

Fine tuning with Lora does not support this model

2
#4 opened 3 months ago by fromjon
New activity in mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx 3 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

1
#2 opened 3 months ago by AlexCheema
New activity in mlx-community/DeepSeek-V2-Lite-Chat-4bit-mlx 4 months ago

mlx-lm 0.16 not found

2
#2 opened 4 months ago by tristanwe

Upload folder using huggingface_hub

2
#1 opened 4 months ago by mzbac
New activity in mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx 4 months ago

Upload folder using huggingface_hub

2
#1 opened 4 months ago by mzbac
New activity in mlx-community/Yi-34B-Chat-hf-4bit-mlx 5 months ago

update license in readme.md
#1 opened 5 months ago by Chen-01AI
New activity in mzbac/function-calling-phi-3-format-v1.1 6 months ago

[bot] Conversion to Parquet
#1 opened 6 months ago by parquet-converter
New activity in mzbac/function-calling-llama-3-format-v1.1 7 months ago

[bot] Conversion to Parquet
#1 opened 7 months ago by parquet-converter
New activity in mzbac/glaive-function-calling-v2-llama-3-format 7 months ago

[bot] Conversion to Parquet
#1 opened 7 months ago by parquet-converter
New activity in mlx-community/Mixtral-8x7B-Instruct-v0.1-hf-4bit-mlx 7 months ago

can you plesse share how to make this version?

3
#3 opened 7 months ago by cloudyu
New activity in mlx-community/dbrx-instruct-4bit 7 months ago

fix the incorrect config.json
#5 opened 7 months ago by mzbac
New activity in mlx-community/Mixtral-8x7B-Instruct-v0.1-hf-4bit-mlx 8 months ago

Parameters

2
#1 opened 8 months ago by l0d0v1c
New activity in mlx-community/Mixtral-8x7B-v0.1-hf-4bit-mlx 8 months ago

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

6
#3 opened 9 months ago by bltfqx
New activity in mlx-community/OLMo-7B-hf-4bit-mlx 9 months ago

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

2
#1 opened 9 months ago by gue22
New activity in allenai/OLMo-7B 9 months ago

Adding `safetensors` variant of this model

1
#11 opened 9 months ago by mzbac
New activity in miqudev/miqu-1-70b 9 months ago

Add miku.mp4 to the readme

6
#7 opened 9 months ago by modster
New activity in mlabonne/phixtral-4x2_8 10 months ago

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

4
#14 opened 10 months ago by mzbac
New activity in mlx-community/Mixtral-8x7B-v0.1-hf-4bit-mlx 10 months ago

Token generation limit?

2
#1 opened 10 months ago by fab4ml
New activity in mzbac/yayi2-30b-guanaco-gguf 10 months ago

Have you gotten this to work somehow?

4
#1 opened 10 months ago by AiCreatornator
New activity in wenge-research/yayi2-30b 10 months ago

The model is using Llama Arch. Would we update the config to be compatible with Llama?

1
#8 opened 10 months ago by mzbac