Alfonso² Peterssen

mukel's activity

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

New activity in mistralai/Codestral-22B-v0.1 5 months ago

New tokenizer.json doesn't match tokenizer.model.v3, there's no [SUFFIX], [MIDDLE] and [PREFIX] tokens.

1

#24 opened 5 months ago by mukel

New activity in TheBloke/CodeLlama-7B-Instruct-GGUF about 1 year ago

The Q4_0 file has "output.weight" quantized with Q6_K.

#2 opened about 1 year ago by mukel

New activity in TheBloke/CodeLlama-7B-Python-GGUF about 1 year ago

The Q8_0 have mixed tensor types e.g. 'output.norm' is of type Q6_K.

4

#2 opened about 1 year ago by mukel

The Q8_0 have mixed tensor types e.g. 'output.norm' is of type Q6_K.

4

#2 opened about 1 year ago by mukel

The Q8_0 have mixed tensor types e.g. 'output.norm' is of type Q6_K.

4

#2 opened about 1 year ago by mukel