Lythri

Hugging Face | ModelScope | Technical Report

## Introduction **Lythri-Tada-4B** is part of the **Lythri 2.0** family. It answers directly without a thinking phase, while reinforce model's emotional understanding. Compared with the previous-generation Lythri-4B-A2B, Tada brings three main upgrades: - **Stronger instruction following.** Tada scores 39.19 on IFEval (prompt-level strict), **surpassing even the Lythri-7B-A4B (31.05)**. - **Better multi-turn conversations.** Tada keeps track of earlier context and user requests more consistently over long chats, and carries the emotional thread from turn to turn. - **System prompt support.** Unlike Lythri-4B-A2B, Tada follows system prompts, so you can set a persona, tone or rules for your app directly in the system message. Long-tail knowledge, such as graduate-level science questions, is slightly weaker than Lythri-4B-A2B, while overall performance improves **substantially**. ## Writing Naturalness

EQ-Bench Slop Score

On the [EQ-Bench Slop Score](https://eqbench.com/slop-score.html), which measures how much a model relies on typical AI phrasing (lower is better), **Lythri-Tada-4B scores 39.0 and writes more naturally than GPT-4o (47.7) and DeepSeek-R1 (67.9)**, far ahead of Qwen3-4B (62.2) and Gemma-3-4B (85.2). ## General Benchmarks

Benchmark	Lythri-4B-A2B	Lythri-Tada-4B
Knowledge
MMLU	55.23	55.41
ARC-C	52.99	56.57
Reasoning
HellaSwag	72.80	74.23
General
SocialIQA	49.80	51.43
Science
GPQA Diamond	28.79	21.21
Math
GSM8K	28.81	27.45
Code / Instruction
HumanEval	28.66	24.39
IFEval	26.43	39.19

All benchmarks are evaluated with their official standard settings and the chat template applied, reflecting real-world inference conditions. Lythri-4B-A2B is evaluated with thinking; Lythri-Tada-4B answers directly without thinking. ## Quickstart ```python from transformers import AutoModelForCausalLM, AutoTokenizer import torch model_path = "Lythri/Lythri-Tada-4B" tok = AutoTokenizer.from_pretrained(model_path) model = AutoModelForCausalLM.from_pretrained( model_path, dtype=torch.bfloat16, device_map="auto" ) messages = [{"role": "user", "content": "My friend just lost their job and seems really down. What should I say to them?"}] chat = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) inputs = tok(chat, return_tensors="pt", add_special_tokens=False).to(model.device) with torch.inference_mode(): out = model.generate( **inputs, max_new_tokens=1024, do_sample=True, temperature=0.8, top_p=0.95, eos_token_id=[1, 106], ) print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)) ``` ### Recommended Generation Config ```python generation_config = { "temperature": 0.8, "top_p": 0.95, "top_k": 64, "max_new_tokens": 1024, "repetition_penalty": 1.05, "do_sample": True, "eos_token_id": [1, 106], } out = model.generate(**inputs, **generation_config) ``` ### System Prompt (Optional) Lythri-Tada-4B supports system prompts, which Lythri-4B-A2B does not. It works well without one; to set a persona or rules for your app, add a system message: ```python messages = [ {"role": "system", "content": "You are Lythri, a warm and caring companion. Reply in the same language as the user."}, {"role": "user", "content": "I had a really rough day at work."}, ] ``` ## Compute Lythri-Tada-4B starts from the Gemma4-E2B PT and training on SFT with CoT, followed by instant-reply SFT with multi-turn companion conversations, and online preference optimization on only writing with responses judged by Gemma2-27B. ## Limitations - Lythri is optimized for conversation and emotional understanding, not for math, coding or complex reasoning. - Lythri is not a substitute for professional mental health support. If you or someone you know is in crisis, please contact local emergency services or a crisis helpline. - Like all language models, it can produce inaccurate or inappropriate content. ## License Lythri is built on Gemma 4 and is released under the Apache License 2.0. ## Citation ```bibtex @techreport{li2026lythri, title = {Lythri Technical Report}, author = {Li, Jiawen}, year = {2026}, institution = {Zenodo}, doi = {10.5281/zenodo.23179311}, url = {https://doi.org/10.5281/zenodo.23179311} } ``` ## Support **The whole training process is self-funded. If you like our model, please click a free like — that means a lot to me as a student!**

Full Model Card (README)