Unverified50% confidenceFactExact time
Manacá-1B-Instruct-2 is the second-generation post-training aligned version of Manacá-1B, with an SFT corpus of 291,223 entries.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAccording to the Chinchilla scaling law, the optimal training data volume for a 30B model is approximately 600B–1T tokens.56% similarUnverifiedGPT-3 has 175B parameters and was trained on 300B tokens; Gopher has 280B parameters and was trained on 300B tokens — both are in an over-parameterized and under-trained state.56% similarUnverifiedThe LLaMA series adopts an over-training strategy, training a 7B-parameter model on 1T tokens, far exceeding the Chinchilla-optimal ratio of 140B tokens55% similarUnverifiedThe fine-tuned 406M model achieved 36.33 ROUGE-1 on the test set, while the authors' own 1.2B system achieved 35.41 ROUGE-1, and the two cannot be statistically distinguished.52% similarUnverifiedOn the Rule Induction task, TwIL-LM3 scored 96.4 while gpt-oss-120b scored 65.2.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032785API
curl https://kongchang.com/api/v1/knowledge/claims/1032785MCP
get_claim(id=1032785)