Cognitive Tech

cognitivetech's activity

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

New activity in mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF over 1 year ago

what template are we using?

3

#8 opened over 1 year ago by

cognitivetech

New activity in liuhaotian/llava-v1.6-mistral-7b over 1 year ago

chat template

👍 4

2

#3 opened about 2 years ago by

cognitivetech

New activity in meta-llama/Meta-Llama-3-8B-Instruct almost 2 years ago

Tokenizer mismatch all the time

2

#47 opened almost 2 years ago by

tian9

New activity in blog-explorers/README almost 2 years ago

[Support] Community Articles

🤝🚀 1

103

#5 opened almost 2 years ago by

victor

commented 3 papers about 2 years ago

Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models

Paper • 2402.14848 • Published Feb 19, 2024 • 19 •

6

Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models

Paper • 2402.14848 • Published Feb 19, 2024 • 19 •

6

Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models

Paper • 2402.14848 • Published Feb 19, 2024 • 19 •

6

New activity in QuixiAI/samantha-mistral-7b about 2 years ago

mistral 7b instruct v0.2

4

#4 opened about 2 years ago by

cognitivetech

New activity in mlabonne/NeuralBeagle14-7B about 2 years ago

Model follows ChatML format, but does not have the special tokens for ChatML

24

#3 opened about 2 years ago by

andysalerno

New activity in mistralai/Mistral-7B-Instruct-v0.2 about 2 years ago

What is the max. content length of Mistral-7B-Instruct-v0.2?

17

#43 opened about 2 years ago by

hanshupe

What are the context window (input) and output token limits ?

4

#24 opened about 2 years ago by

sniffski

New activity in jartine/mistral-7b.llamafile about 2 years ago

can we get this in v0.2?

3

#3 opened about 2 years ago by

cognitivetech

New activity in migtissera/Synthia-7B-v3.0 about 2 years ago

this version has too much personality compared to v2.0

7

#1 opened over 2 years ago by

cognitivetech

this version has too much personality compared to v2.0

7

#1 opened over 2 years ago by

cognitivetech

New activity in migtissera/Synthia-7B-v3.0 over 2 years ago

this version has too much personality compared to v2.0

7

#1 opened over 2 years ago by

cognitivetech