33 1 36

Jonathan McKinney

pseudotensor

https://github.com/pseudotensor/

pseudotensor

AI & ML interests

AI and LLMs

Recent Activity

liked a model 10 days ago

deepseek-ai/DeepSeek-R1-0528

new activity 30 days ago

mistral-community/pixtral-12b:Cannot apply chat template from tokenizer

new activity about 2 months ago

gaia-benchmark/leaderboard:This model has already been submitted but is not showing up.

View all activity

Organizations

pseudotensor's activity

New activity in mistral-community/pixtral-12b 30 days ago

Cannot apply chat template from tokenizer

#31 opened 3 months ago by

DarkLight1337

New activity in gaia-benchmark/leaderboard about 2 months ago

This model has already been submitted but is not showing up.

#47 opened 2 months ago by

Whliuyu

New activity in gaia-benchmark/leaderboard 3 months ago

How to eliminate SPAM that devalues the benchmark? Perhaps each login should only be allowed one entry per day at least? Other ways?

#40 opened 3 months ago by

pseudotensor

missing top post

#41 opened 3 months ago by

pseudotensor

New activity in reasoning-machines/gsm-hard 9 months ago

wrong entries

#2 opened 9 months ago by

pseudotensor

New activity in meta-llama/Llama-3.1-405B-Instruct-FP8 10 months ago

8-kv-heads

🔥 🚀 5

#14 opened 10 months ago by

ArthurZ

New activity in nvidia/Llama3-ChatQA-1.5-70B 11 months ago

Why do various companies keep using hard-coded system prompt in the chat template?

#17 opened 11 months ago by

pseudotensor

New activity in HuggingFaceM4/idefics2-8b about 1 year ago

Add chat template to processor_config.json

#36 opened about 1 year ago by

Rocketknight1

New activity in CohereLabs/c4ai-command-r-v01 about 1 year ago

Context length is not 128k

👍 1

#41 opened about 1 year ago by

pseudotensor

Remove AutoConfig, AutoModel and AutoModelForCausalLM register

🔥 2

#37 opened about 1 year ago by

jmprcp

ValueError: Cannot instantiate this tokenizer from a slow version. If it's based on sentencepiece, make sure you have sentencepiece installed.

#18 opened about 1 year ago by

pseudotensor

New activity in abacusai/Smaug-72B-v0.1 over 1 year ago

which chat template should we use?

#6 opened over 1 year ago by

wyxwangmed

bad output of model

#19 opened over 1 year ago by

coldanimal

New activity in 01-ai/Yi-34B-200K over 1 year ago

Weight updates?

👍 7

#13 opened over 1 year ago by

brucethemoose

New activity in NousResearch/Nous-Hermes-2-Yi-34B over 1 year ago

Difference between Hermes and Capybara?

👍 2

#4 opened over 1 year ago by

Yhyu13

New activity in h2oai/h2ogpt-4096-llama2-70b-chat over 1 year ago

Take very long time to get the answers and answers never comes

#2 opened over 1 year ago by

UDJA

New activity in distil-whisper/distil-large-v2 over 1 year ago

When will disl_large_v3 comes out?

👍 3

#16 opened over 1 year ago by

lucasjin

New activity in h2oai/h2ogpt-chatbot over 1 year ago

Run on local machine

#3 opened over 1 year ago by

TAMYS

New activity in TheBloke/Nous-Hermes-13B-GPTQ almost 2 years ago

latest update broke use

#16 opened almost 2 years ago by

pseudotensor

New activity in h2oai/h2ogpt-chatbot2 almost 2 years ago

Is there any API endpoint to this model?

#4 opened almost 2 years ago by

tiduzzo