kallewoof 23ec550835 PoC: add chat template heuristics (#1283) ... * PoC: add chat template heuristics The fallback chat template adapter of Vicuna is not ideal in some cases (e.g. a test against a sub-portion of the BBC news classification task on Kaggle gave an 82% accuracy with Vicuna and 88% with the official ChatML format for a q4_k_m Qwen 2.5 3B-Instruct gguf). This PR adds a proof of concept simple heuristic which looks at the chat template and upgrades the adapter when it is able to. * gemma 2 heuristic * Phi 4, Llama 3.x heuristics * better qwen vs generic heuristic * cleanup * mistral (generic) heuristic * fix sys msg for mistral * phi 3.5 * mistral v3 * cohere (aya expanse 32b based) * only derive from chat template if AutoGuess * add notes about alpaca fallbacks * added AutoGuess.json dummy * add mistral v7 * switch to using a json list with search strings		2024-12-28 12:15:23 +08:00
..
Alpaca.json	Update kcpp_adapters (#985)	2024-07-13 19:06:15 +08:00
AutoGuess.json	PoC: add chat template heuristics (#1283)	2024-12-28 12:15:23 +08:00
ChatML.json	Update kcpp_adapters (#985)	2024-07-13 19:06:15 +08:00
Command-R.json	Update kcpp_adapters (#985)	2024-07-13 19:06:15 +08:00
Gemma-2.json	Update kcpp_adapters (#985)	2024-07-13 19:06:15 +08:00
Llama-2-Chat.json	Update kcpp_adapters (#985)	2024-07-13 19:06:15 +08:00
Llama-3.json	Update kcpp_adapters (#985)	2024-07-13 19:06:15 +08:00
Metharme.json	Update kcpp_adapters (#985)	2024-07-13 19:06:15 +08:00
Mistral-V1.json	update templates, fix rwkv	2024-09-22 01:32:12 +08:00
Mistral-V2-V3.json	update templates, fix rwkv	2024-09-22 01:32:12 +08:00
Mistral-V3-Tekken-V7.json	consolidate mistral templates (too many)	2024-12-15 00:03:34 +08:00
Phi-3.json	Update kcpp_adapters (#985)	2024-07-13 19:06:15 +08:00
Vicuna.json	Update kcpp_adapters (#985)	2024-07-13 19:06:15 +08:00