GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
EumenesXIII
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
EumenesXIII
Model Tree
HuggingFaceTB/SmolLM2-360M-Instruct
Input Modalities
Output Modalities
Supported Functionality
Asistente que explica conceptos de inteligencia artificial generativa a ejecutivos, con ejemplos aplicados a distintas industrias (banca, retail, AFP, logística, universidades, clínicas). Cubre 5 temas: Agentes de IA, Ajuste fino, Fundamentos de LLM, Ingeniería de prompts, RAG.
datos/entrenamiento.jsonl).
| Antes (base) | Después (destilado) | |
|---|---|---|
| Nota media (1–10) | 1.33 | 8.58 |
| Aprobación (≥ 7) | 0% | 75% |
| Tema | Antes | Después |
|---|---|---|
| Agentes de IA | 1.50 | 10.00 |
| Ajuste fino | 1.00 | 10.00 |
| Fundamentos de LLM | 1.33 | 8.67 |
| Ingeniería de prompts | 1.00 | 10.00 |
| RAG | 1.33 | 5.67 |
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base = "HuggingFaceTB/SmolLM2-360M-Instruct"tok = AutoTokenizer.from_pretrained(base)m = PeftModel.from_pretrained(AutoModelForCausalLM.from_pretrained(base), "EumenesXIII/finbot-slm")msgs = [{"role": "user", "content": "Explica qué es RAG para un banco."}]ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True)out = m.generate(**ids, max_new_tokens=80)print(tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True))from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base = "HuggingFaceTB/SmolLM2-360M-Instruct"tok = AutoTokenizer.from_pretrained(base)m = PeftModel.from_pretrained(AutoModelForCausalLM.from_pretrained(base), "EumenesXIII/finbot-slm")msgs = [{"role": "user", "content": "Explica qué es RAG para un banco."}]ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True)out = m.generate(**ids, max_new_tokens=80)print(tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True))