Three Foxes (in a Trenchcoat) 8214b1f19b fix: add AutoRound format detection to prevent misclassification as GGUF (#532) ... * fix: add AutoRound format detection to prevent misclassification as GGUF - Add ModelFormat::Autoround enum variant in models.rs - Update is_prequantized() to include AutoRound - Fix bit-per-parameter calculation for AutoRound-4bit - Update scrape_hf_models.py to detect auto-round quant_method - Correct 3 misclassified AutoRound models in hf_models.json - Add AutoRound-4bit to SUPPORTED_QUANTS and parse_quant() in plan.rs - Update pre-quantization comments in fit.rs - Update test_model_format_prequantized() assertion Fixes #526 * style: apply cargo fmt formatting * ci: use npx for web build/test steps to fix Windows PATH issue * fix: add AutoRound-8bit to quant metrics in models.rs Add explicit entries for AutoRound-8bit in quant_speed_multiplier, quant_bytes_per_param, and quant_quality_penalty. Without these, an 8-bit AutoRound model would incorrectly fall through to the 4-bit defaults (0.5 bpp, quality penalty -5.0).		2026-05-05 10:00:56 +01:00
..
install-openclaw-skill.sh	docs: brew official formula	2026-03-02 11:58:15 +07:00
scrape_benchmarks.py	feat: add benchmark cache with offline fallback	2026-04-27 15:51:57 +01:00
scrape_docker_models.py	feat: add Docker Model Runner as a runtime provider	2026-03-14 17:42:58 +00:00
scrape_hf_models.py	fix: add AutoRound format detection to prevent misclassification as GGUF (#532)	2026-05-05 10:00:56 +01:00
test_api.py	feat: adding serve capabilities	2026-03-03 14:16:31 +00:00
update_models.sh	Add Qwen3.5B Claude Opus 4.6 reasoning models, fix cursor navigate, add support for parallel models update and enriching with --threads, marquee effect for model name column (#275)	2026-04-30 08:15:49 +01:00
verify_models.py	feat: caught some unavailable models on ollama	2026-02-19 10:40:18 +00:00