Perry Link

perrylink's activity

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

New activity in LocalLLaMA/typed-decisions 2 days ago

Leaderboard question: the current #1 was trained on test-split rows (Phocinae-Largha-150M-v1)

4

#25 opened 2 days ago by

masterset-ai

New activity in evaleval/EEE_datastore 4 days ago

[Submission] Add typed-decisions: Phocinae-Largha-150M-v1 (en + zh, 2 records) with per-decision instances

5

#238 opened 4 days ago by

perrylink

New activity in hotchpotch/s1mb-result 4 days ago

Add Phocinae-Largha-150M-v1 results

1

#16 opened 4 days ago by

perrylink

New activity in multimodalart/jev-decision-index 4 days ago

news: add Phocinae-Largha-150M-v1 (trained)

#66 opened 4 days ago by

perrylink

New activity in LocalLLaMA/typed-decisions 4 days ago

Add Phocinae-Largha-150M-v1 (specialist, fitted on train) to Table 2

#21 opened 4 days ago by

perrylink

New activity in hugging-apps/phocinae-largha-150m 4 days ago

Update card numbers to v1.1 (README + app subtitle; text-only)

#2 opened 4 days ago by

perrylink

New activity in LocalLLaMA/typed-decisions 4 days ago

Submission: Phocinae/Phocinae-Largha-150M-v1 — specialist (fitted on the train split); accuracy 0.906 (en) / 0.848 (zh)

🔥 1

3

#18 opened 6 days ago by

perrylink

Phocinae-Largha-150M-v1 — test scores (specialist: fitted on train split) + reproduction

🔥 1

2

#15 opened 6 days ago by

perrylink

New activity in Phocinae/Phocinae-Largha-150M-v1 5 days ago

Demo for this model on Spaces

1

#2 opened 6 days ago by

multimodalart

New activity in hugging-apps/phocinae-largha-150m 5 days ago

v1.1 numbers refresh: README + app.py (flip 0.0300 -> 2.17%/2.83%; acc 0.797/0.789 -> 0.906/0.848; ECE 0.1313 -> 0.0168/0.0152; 54% -> -55.0%; 144M -> 144.3M)

#1 opened 5 days ago by

perrylink

New activity in Phocinae/Phocinae-Largha-150M-v1 6 days ago

What decisions are you routing locally? (use cases + what breaks first)

#1 opened 6 days ago by

perrylink

New activity in convaiinnovations/laya 10 days ago

CPU latency numbers for laya-multilingual — the model card only has T4

4

#12 opened 21 days ago by

htqmike

New activity in convaiinnovations/laya 18 days ago

choice:11+ temperature (0.1006) saturates confidence: answers return at 1.00, wrong ones included

👍 3

1

#2 opened 25 days ago by

DrowsyJungle

Laya-multilingual: a 100-scenario decision-making evaluation

🔥 19

1

#3 opened 24 days ago by

mghafiri

New activity in convaiinnovations/laya 19 days ago

Zero-shot Laya as an agent step guard: agrees when agents say "done", never escalates destructive commands, blind past 320–768 tokens

👀 2

5

#15 opened 21 days ago by

sinhal