Rayen

Lissanro's activity

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

New activity in Qwen/QwQ-32B 2 days ago

Is this model native 128K context length, or YaRN extended?

4

#28 opened 4 days ago by

danielhanchen

New activity in Qwen/QwQ-32B 3 days ago

Doesn't Generate `<think>` tags

2

#25 opened 4 days ago by

bingw5

liked a model about 1 month ago

turboderp/Qwen2.5-VL-7B-Instruct-exl2

Updated Feb 2 • 111 • 5

liked a model 5 months ago

softwareweaver/Twilight-Large-123B-EXL2-5bpw

Text Generation • Updated Oct 17, 2024 • 9 • 1

New activity in bigstorm/Llama-3.1-Nemotron-70B-Instruct-HF-7.0bpw-8hb-exl2 5 months ago

6bpw quant request

1

#2 opened 5 months ago by

Lissanro

liked a model 8 months ago

LoneStriker/Meta-Llama-3.1-70B-Instruct-6.0bpw-h6-exl2

Text Generation • Updated Jul 24, 2024 • 20 • 6

upvoted a collection 9 months ago

SSMs

Collection

A collection of Mamba-2-based research models with 8B parameters trained on 3.5T tokens for comparison with Transformers. • 5 items • Updated Jan 17 • 27

New activity in turboderp/Llama-3-70B-Instruct-exl2 11 months ago

tokenizer_config.json and config.json specify wrong EOS token, causing the model to not function correctly in backends which do not read EOS tokens from generation_config.json

6

#1 opened 11 months ago by

Lissanro

New activity in LoneStriker/Meta-Llama-3-8B-Instruct-8.0bpw-h8-exl2 11 months ago

Works great on oobabooga, but always ends with assistant

1

#3 opened 11 months ago by

Noodlz

liked a model 11 months ago

turboderp/Llama-3-70B-Instruct-exl2

Updated Apr 19, 2024 • 44 • 51

New activity in alpindale/WizardLM-2-8x22B 11 months ago

This could likely be dewokefied and possible even improved using mergekit's new 'Model Stock' method!

31

#5 opened 11 months ago by

jukofyork