Alfonso² Peterssen's picture

3 3

Alfonso² Peterssen

mukel

·

AI & ML interests

Java in Java by day, LLMs in Java by night.

Recent Activity

updated a model about 1 month ago

mukel/Qwen2.5-Coder-3B-Instruct-GGUF

updated a model about 1 month ago

mukel/Qwen2.5-Coder-0.5B-Instruct-GGUF

View all activity

Organizations

None yet

mukel's activity

New activity in mistralai/Codestral-22B-v0.1 7 months ago

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

#24 opened 7 months ago by

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

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

#2 opened over 1 year ago by

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

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

#2 opened over 1 year ago by

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

#2 opened over 1 year ago by

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

#2 opened over 1 year ago by