add smollm2 135m multilingual

app.py

@@ -28,6 +28,7 @@ cancel_event = threading.Event()
 MODELS = {
     # … your existing entries …
     "Qwen2.5-Taiwan-1.5B-Instruct": {"repo_id": "benchang1110/Qwen2.5-Taiwan-1.5B-Instruct", "description": "Qwen2.5-Taiwan-1.5B-Instruct"},
+    "SmolLM2-135M-multilingual-base": {"repo_id": "agentlans/SmolLM2-135M-multilingual-base", "description": "SmolLM2-135M-multilingual-base"},
     "parser_model_ner_gemma_v0.1": {
         "repo_id": "myfi/parser_model_ner_gemma_v0.1",
         "description": "A lightweight named‑entity‑like (NER) parser fine‑tuned from Google’s **Gemma‑3‑270M** model. The base Gemma‑3‑270M is a 270 M‑parameter, hyper‑efficient LLM designed for on‑device inference, supporting >140 languages, a 128 k‑token context window, and instruction‑following capabilities [2][7]. This variant is further trained on standard NER corpora (e.g., CoNLL‑2003, OntoNotes) to extract PERSON, ORG, LOC, and MISC entities with high precision while keeping the memory footprint low (≈240 MB VRAM in BF16 quantized form) [1]. It is released under the Apache‑2.0 license and can be used for fast, cost‑effective entity extraction in low‑resource environments."