Jonathan McKinney PRO

pseudotensor's activity

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

New activity in h2oai/h2o-lightning-4b 5 days ago

MLX builds by NetProjects are now v1.3.1 (card says v1.2.x one-way)

8

#4 opened 14 days ago by

Paris99

Shim: do not answer a client that already hung up

2

#5 opened 6 days ago by

mjvk

New activity in h2oai/h2o-lightning-4b 21 days ago

Add decision-model tag

1

#3 opened 21 days ago by

mishig

New activity in h2oai/h2o-lightning-4b 22 days ago

Demo for this model on Spaces

3

#1 opened 26 days ago by

multimodalart

Community MLX builds (8-bit and 4-bit) for Apple Silicon

1

#2 opened 22 days ago by

Paris99

New activity in meta-agents-research-environments/leaderboard about 1 year ago

GAIA2 only applicable to LLM evaluation not agent scaffold evaluation?

2

#1 opened about 1 year ago by

pseudotensor

New activity in mistral-experimental/pixtral-12b over 1 year ago

Cannot apply chat template from tokenizer

2

#31 opened over 1 year ago by

DarkLight1337

New activity in gaia-benchmark/leaderboard over 1 year ago

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

10

#47 opened over 1 year ago by

Whliuyu

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

9

#40 opened over 1 year ago by

pseudotensor

missing top post

3

#41 opened over 1 year ago by

pseudotensor

New activity in reasoning-machines/gsm-hard about 2 years ago

wrong entries

2

#2 opened about 2 years ago by

pseudotensor

New activity in meta-llama/Llama-3.1-405B-Instruct-FP8 about 2 years ago

8-kv-heads

🔥🚀 5

8

#14 opened about 2 years ago by

ArthurZ

New activity in nvidia/Llama3-ChatQA-1.5-70B over 2 years ago

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

2

#17 opened over 2 years ago by

pseudotensor

New activity in HuggingFaceM4/idefics2-8b over 2 years ago

Add chat template to processor_config.json

4

#36 opened over 2 years ago by

Rocketknight1

New activity in CohereLabs/c4ai-command-r-v01 over 2 years ago

Context length is not 128k

👍 1

4

#41 opened over 2 years ago by

pseudotensor

Remove AutoConfig, AutoModel and AutoModelForCausalLM register

🔥 2

3

#37 opened over 2 years ago by

jmprcp

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

3

#18 opened over 2 years ago by

pseudotensor

New activity in abacusai/Smaug-72B-v0.1 over 2 years ago

which chat template should we use?

4

#6 opened over 2 years ago by

wyxwangmed

bad output of model

4

#19 opened over 2 years ago by

coldanimal

New activity in 01-ai/Yi-34B-200K over 2 years ago

Weight updates?

👍 7

8

#13 opened over 2 years ago by

brucethemoose