null
mzbac
AI & ML interests
None yet
Organizations
mzbac's activity
mlx-lm 0.16 not found
2
#2 opened 10 days ago
by
tristanwe
Upload folder using huggingface_hub
2
#1 opened 10 days ago
by
mzbac
Upload folder using huggingface_hub
2
#1 opened 11 days ago
by
mzbac
update license in readme.md
#1 opened 30 days ago
by
Chen-01AI
[bot] Conversion to Parquet
#1 opened 3 months ago
by
parquet-converter
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1658495802629-61f02cf649ea1fb7363729dc.png)
[bot] Conversion to Parquet
#1 opened 3 months ago
by
parquet-converter
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1658495802629-61f02cf649ea1fb7363729dc.png)
[bot] Conversion to Parquet
#1 opened 3 months ago
by
parquet-converter
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1658495802629-61f02cf649ea1fb7363729dc.png)
can you plesse share how to make this version?
3
#3 opened 4 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
fix the incorrect config.json
#5 opened 4 months ago
by
mzbac
Parameters
2
#1 opened 4 months ago
by
l0d0v1c
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63332aea518c0f78a6dfd50f/Zc6s3RkapWycF9sGKXsT2.png)
Why this model is extremely slow on M1 Max with 32GB RAM
6
#3 opened 5 months ago
by
bltfqx
where is OLMo-7B-hf-4bit-mlx stored?
2
#1 opened 6 months ago
by
gue22
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1672345606582-63adf6e542fd3b8dbaeb3df0.jpeg)
Adding `safetensors` variant of this model
1
#11 opened 6 months ago
by
mzbac
Add miku.mp4 to the readme
6
#7 opened 6 months ago
by
modster
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65ab93082bf3e0cbbf717850/iaiYac1w-1a18PeDOfzCp.png)
Update the model type to make it compatible with mlx-lm's model mapping.
4
#14 opened 6 months ago
by
mzbac
Token generation limit?
2
#1 opened 6 months ago
by
fab4ml
Have you gotten this to work somehow?
4
#1 opened 7 months ago
by
AiCreatornator
The model is using Llama Arch. Would we update the config to be compatible with Llama?
1
#8 opened 7 months ago
by
mzbac
Fix the configuration for num_key_value_heads so that current tools will be supported.
2
#6 opened 7 months ago
by
mzbac
fix AttributeError: 'YayiTokenizer' object has no attribute 'sp_model'
2
#5 opened 7 months ago
by
mzbac
fix the bos and eos token
3
#1 opened 7 months ago
by
mzbac
Can you release a chat version soon ?
11
#8 opened 9 months ago
by
dong0213
Upload Mistral-7B-Grammar-Checker-v1.1.2.Q5_K_M.gguf
#2 opened 9 months ago
by
mzbac
Error when trying to start server
1
#1 opened 9 months ago
by
antderosa
Is the 34B llama2 actually GPTQ working?
4
#3 opened 11 months ago
by
mzbac
fix load tokenizer error
1
#1 opened about 1 year ago
by
mzbac
Fix the special token mapping
4
#20 opened about 1 year ago
by
mzbac