Michael Shatskiy

YearZero's activity

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

New activity in bartowski/Meta-Llama-3-8B-Instruct-GGUF 2 months ago

You think you could re-quant with the regex fix?

4

#3 opened 2 months ago by YearZero

New activity in cybrtooth/TheBloke-Mistral-7B-Instruct-v0.2-GGUF 3 months ago

🚩 Report: Ethical issue(s)

1

#2 opened 3 months ago by YearZero

New activity in abacusai/Smaug-34B-v0.1 5 months ago

prompt template?

1

#4 opened 5 months ago by YearZero

New activity in argilla/notux-8x7b-v1 6 months ago

Prompt template?

2

#3 opened 6 months ago by YearZero

New activity in TheBloke/Magicoder-S-DS-6.7B-GGUF 7 months ago

failed to load the model

16

#1 opened 7 months ago by rinoa

New activity in TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF 7 months ago

This model uses <0x0A> instead of a carriage return

8

#1 opened 7 months ago by YearZero

New activity in defog/sqlcoder-34b-alpha 8 months ago

Error during converting to gguf

3

#3 opened 8 months ago by apepkuss79

New activity in TheBloke/neural-chat-7B-v3-1-GGUF 8 months ago

Do we know if this is a base model or instruction tuned?

8

#1 opened 8 months ago by YearZero

New activity in TheBloke/Nous-Capybara-34B-GGUF 8 months ago

Q4_0 works great in Koboldcpp, Q4_K_M gives absolute gibberish.

3

#3 opened 8 months ago by YearZero

BOS token as 1 seriously hurts these GGUF Yi models

11

#1 opened 8 months ago by KerfuffleV2

New activity in TheBloke/robin-7B-v2-GGML about 1 year ago

Confirm prompt template

2

#1 opened about 1 year ago by YearZero

New activity in mindrage/Manticore-13B-Chat-Pyg-Guanaco-GGML about 1 year ago

Any chance for q8_0?

6

#1 opened about 1 year ago by YearZero