22 4 16

Cognitive Tech

cognitivetech

AI & ML interests

local first: research assistance starting with psychology book summaries

Recent Activity

liked a model about 2 months ago

bartowski/Yi-Coder-9B-Chat-GGUF

liked a model 2 months ago

pandalla/MBTIGPT_en_ENTJ

liked a model 2 months ago

pandalla/MBTIGPT_en_ISFP

View all activity

Articles

Bulleted Notes eBook Summary: A Different Way to Chat with PDF

Aug 10, 2024

• 2

Samantha Mistral Instruct 7b - Comprehensive Bulleted Notes

Mar 28, 2024

• 7

Organizations

cognitivetech's activity

New activity in mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF 5 months ago

what template are we using?

#8 opened 5 months ago by

cognitivetech

New activity in liuhaotian/llava-v1.6-mistral-7b 6 months ago

chat template

#3 opened 11 months ago by

cognitivetech

New activity in meta-llama/Meta-Llama-3-8B-Instruct 9 months ago

Tokenizer mismatch all the time

#47 opened 9 months ago by

tian9

New activity in imone/Llama-3-8B-fixed-special-embedding 9 months ago

instruct?

#1 opened 9 months ago by

cognitivetech

New activity in lmstudio-community/WizardLM-2-7B-GGUF 9 months ago

do as you say, not as you do?

#1 opened 9 months ago by

cognitivetech

New activity in bartowski/stable-code-instruct-3b-GGUF 9 months ago

did you require any special flags to convert \ quant this?

#1 opened 9 months ago by

cognitivetech

New activity in blog-explorers/README 10 months ago

[Support] Community Articles

#5 opened 10 months ago by

victor

commented 3 papers 10 months 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 • 18 •

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

Paper • 2402.14848 • Published Feb 19, 2024 • 18 •

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

Paper • 2402.14848 • Published Feb 19, 2024 • 18 •

New activity in cognitivecomputations/samantha-mistral-7b 11 months ago

mistral 7b instruct v0.2

#4 opened 11 months ago by

cognitivetech

New activity in MaziyarPanahi/samantha-1.2-mistral-7b-Mistral-7B-Instruct-v0.2-slerp-GGUF 11 months ago

mistral prompt style

#1 opened 11 months ago by

cognitivetech

New activity in KnutJaegersberg/2-bit-LLMs 11 months ago

Error: invalid file magic

#5 opened 11 months ago by

cognitivetech

New activity in mlabonne/NeuralBeagle14-7B 11 months ago

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

#3 opened 12 months ago by

andysalerno

New activity in mistralai/Mistral-7B-Instruct-v0.2 11 months ago

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

#43 opened 11 months ago by

hanshupe

New activity in flemmingmiguel/MBX-7B-v3 11 months ago

model template and context?

#2 opened 11 months ago by

cognitivetech

New activity in paulml/OmniBeagleMBX-v3-7B 11 months ago

chat template and context?

#1 opened 11 months ago by

cognitivetech

New activity in senseable/WestLake-7B-v2 11 months ago

context?

#10 opened 11 months ago by

cognitivetech

New activity in mlabonne/OmniBeagle-7B 11 months ago

preferred chat template? context size?

#2 opened 11 months ago by

cognitivetech

New activity in mistralai/Mistral-7B-Instruct-v0.2 11 months ago

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

#24 opened about 1 year ago by

sniffski