Agaram 2.5B：首个从零训练、支持工具调用的泰米尔语优先模型
Agaram 2.5B: The First Tamil-First Language Model Trained from Scratch with Tool Calling. A Playbook for Under-Represented Languages
AI 导读
Agaram 2.5B 是一个从零训练的泰米尔语优先语言模型，支持泰米尔文、Tanglish 和英文对话并调用工具，权重以 Apache-2.0 开源。该模型基于 50B token（58% 为泰米尔语）预训练 2.53B 参数，tokenizer 每 1.55 token 处理一个泰米尔语词，远优于 Qwen2.5 的 9.44。
正文 · 原文
Abstract:We present Agaram 2.5B, a Tamil-first language model trained from scratch that converses in Tamil script, romanized Tanglish and English, and calls tools. Our first model, Agaram 1.5B, guided the new base, tokenizer and fine-tuning recipe: we pretrained a new 2.53B-parameter base on 50 billion tokens, 58% of them Tamil, with a tokenizer that needs 1.55 tokens per Tamil word where Qwen2.5's needs 9.44. A four-day public preview of our first 2.5B chat model showed where it fell short with real users, and we rebuilt supervised fine-tuning around what we saw, on 222,662 records. The released model scores above Sarvam-1 in all six translation directions we measured (FLORES chrF 56.9 into Tamil and 55.4 into English), chooses the expected tool on all 25 prompts of a tool set that was used during checkpoint selection and whose schemas appear in training, with exact arguments on 16, and was preferred over the preview model by an LLM judge on 100 sealed human-written prompts (net preference +30 points, 95% interval +14.5 to +45.0). On FLORES it also scores above Google's Gemma 4 E4B-it and our fine-tuned variant of it in both directions, with 2.53B parameters against E4B's 4.5B effective parameters. Factual knowledge and reliable refusal of harmful requests remain open problems, which we set out as future work. The base and chat weights and GGUF files are released under Apache-2.0, and this report gives a full account of the data, training and evaluation as a playbook for building language models for under-represented languages.
| Comments: | v2: restructured report on the released model (SFT v2 step 700), public preview analysis, sealed comparison, comparison with a fine-tuned Gemma 4 E4B, representation analysis; 34 pages main text, 76 total. Weights: this https URL ; demo: this https URL |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.18420 [cs.CL] |
| (or arXiv:2610.18420v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18420 arXiv-issued DOI via DataCite |
Submission history
From: Ramchand Kumaresan [view email]
[v1]
Tue, 13 Oct 2026 14:00:05 UTC (298 KB)
[v2]
Tue, 27 Oct 2026 04:52:52 UTC (453 KB)
来源：arXiv cs.AI · arxiv.org