Downloads · 30 days
5
5% of all-time downloads
jsantillana/qwen2.5-3b-f1-commentary-lora
qwen2.5-3b-f1-commentary-lora is a machine learning model from jsantillana. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as other.
LoRA adapter for Qwen/Qwen2.5-3B-Instruct, fine-tuned to generate short (2-3 sentence), grounded live F1 race commentary from a structured live-state snapshot (positions, gaps, tyre compounds/age, on-track battles, pa…
Downloads · 30 days
5
5% of all-time downloads
All-time downloads
93
Public
Repo size
278 MB
Likes
0
Public
Click a slice to open those files.
.pt178 MB · 52%
From the Hugging Face model README
LoRA adapter for Qwen/Qwen2.5-3B-Instruct, fine-tuned to generate short (2-3 sentence), grounded live F1 race commentary from a structured live-state snapshot (positions, gaps, tyre compounds/age, on-track battles, pace deltas, safety-car flag). Powers the live commentary feature of Pitwall.
Companion adapter to jsantillana/qwen2.5-3b-f1-strategy-lora (the paper's post-race
strategy-explanation model, fine-tuned on a different prompt/format). This adapter is
fine-tuned specifically on the prompt/context format used by
services/api/commentary.py::build_context and SYSTEM_PROMPT/PROMPTS, so it learns to
terminate cleanly after 2-3 sentences instead of degenerating into repetition.
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = "Qwen/Qwen2.5-3B-Instruct"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(model, "jsantillana/qwen2.5-3b-f1-commentary-lora")
strategy_sim/track_store.state_at_lap) paired
with the exact commentary.py prompt and a deterministic grounded template
(commentary._template_text) as the target. 2025/2026 seasons held out for eval.