fix: update model

fix: remove exAI

fix: still error

fix: still error

fix: check_model_input issue

fix: update req

fix: update req

fix: update req and docker

fix: update base model

fix: exAI ropeparam

fix: update dependency

fix: update backend lib with log

fix: update model lists

feat: select model from admin panel

fix: update model to 360m

feat: update base free model

perf: switch default LLM to SmolLM2-1.7B - 40-50% faster tok/s, better instruction following

perf: greedy decoding + dtype fix - 2-3x faster inference on CPU

fix: rewrite loader.py as clean UTF-8 - remove Windows-1252 em-dashes causing SyntaxError

feat: self-hosted Qwen2.5-1.5B-Instruct via transformers — no external API, no compilation

feat: replace llama-cpp-python/Groq with free HF InferenceClient (zero compilation)

fix: double .gguf extension — skip symlink when path already ends in .gguf; add verbose step logging

feat: LLM readiness tracking — 503 while loading, llm_ready in /health

fix: symlink blob to .gguf extension so llama.cpp C loader accepts it

fix: use hf_hub_download + realpath to avoid snapshot ./path crash

fix: correct GGUF filename case — Qwen3-4B-Q4_K_M.gguf

Initial backend