6 commits

Author	SHA1	Message	Date
Alex Jones	ac5b115988	fix: correct Llama 4 Maverick metadata (expert count, context length) (#446) ... Fixes #445 - Maverick num_experts was 16 (from generic llama4 fallback), now 128 matching the model name (17B-128E) - Maverick context_length was 4096 (bare max_position_embeddings), now 1048576 after applying RoPE scaling factor - MODELS.md listed both Scout/Maverick as 128k; corrected to 10M/1M - Scraper detect_moe() now checks text_config for nested MoE fields (Llama 4 multimodal models store num_local_experts there) - Scraper infer_context_length() now applies rope_scaling factor when present, so models using RoPE extension get correct context values Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-15 20:25:09 +01:00
Alexander Silva	226c5c2d80	feat: add Qwen3.5 small model series (0.8B, 2B, 4B, 9B)	2026-03-02 21:21:22 -05:00
Laurence S.	fac36872ee	Add new Qwen3.5 models to database ... All Multimodal vision and text models: - Qwen3.5-27B (27.8B params, 256k context) - Qwen3.5-35B-A3B (36.0B MoE, 256k context) - Qwen3.5-122B-A10B (125.1B MoE, 256k context) - Qwen3.5-397B-A17B (403.4B MoE, 256k context)	2026-03-01 10:30:30 -08:00
Alex	c68d7aad0c	feat: supporting 94 models ... Signed-off-by: Alex <alexsimonjones@gmail.com>	2026-02-16 13:50:36 +00:00
Alex	c18bb647c5	chore: scripts and models ... Signed-off-by: Alex <alexsimonjones@gmail.com>	2026-02-15 21:21:51 +00:00
AlexsJones	75a9530483	chore: improved readme and updated models ... Signed-off-by: AlexsJones <alexsimonjones@gmail.com>	2026-02-15 17:14:29 +00:00