chore: update commit counter 68 → 101

fix: pre-translate non-English chunks to English before LLM inference

fix: enable sampling — temperature=0.8 for MCQ, 0.4 for evaluator

fix: stronger MCQ/evaluator prompts — no duplicates, no self-reference, English-only, section 2 always present

fix: restore MiniCPM4-8B in hackathon narrative, fix fine-tune duration claim

feat: 6/6 badges — unlock Sharing is Caring, add Chapter 06 on MiniCPM4.1-8B upgrade

chore: update blog to MiniCPM4.1-8B fine-tune + Sharing is Caring badge earned

feat: add share_trace.py — run session + push agent trace to HF Hub dataset

feat: retarget fine-tune pipeline to MiniCPM4.1-8B

feat: upgrade to MiniCPM4.1-8B + official GGUF, disable thinking mode

revert: restore original demo.launch(), blog served from separate static Space

fix: inject /blog into Gradio's internal FastAPI router at position 0

fix: mount /blog before Gradio so static files aren't swallowed by catch-all route

feat: serve blog at /blog from main Space + badge showcase

feat: full-height libraries, pre-generated reward image, English upload text

fix: make the llama.cpp CPU runtime actually usable on the Space

feat: grounded, varied training explanations for MCQ and evaluation

fix: custom collator so EOS is learned (pad==eos masked stop tokens in v2)

fix: truncate runaway question generation to the first question

fix: multi-task fine-tuning — single-task training broke MCQ format

fix: prebuilt CPU wheel for llama-cpp-python, skip 15min source compile on Spaces

feat: llama.cpp runtime ready for the Space (Llama Champion)

fix: verify Hub write access before training, fallback to user namespace

feat: switch to our fine-tuned MiniCPM4-8B-PaperProf model (Well-Tuned)

feat: Well-Tuned + Llama Champion groundwork

move: team section to Chapter 01, right after the intro

feat: team section on the blog with Ryad Gazenay and Mehdi Azouz, GitHub and LinkedIn links, optimized photos

fix: library panels full width, hidden rows off-screen

redesign: blog as a crafted dev site, no emoji, heavier animations

feat: full-height library side panels with animated robots

feat: Field Notes blog as a standalone designed website (blog/index.html)

feat: animated library side panels with mini robots

docs: Field Notes blog post — what we built and what we learned

feat: amphitheater hero with mouse-tracking robot professor, fixed particles

fix: MCQ clicks broken — restore onclick in showMCQ, remove duplicate addEventListener

fix: MCQ double-count — remove duplicate onclick handler in showMCQ

fix: force English output in all LLM prompts regardless of PDF language

feat: FLUX image generation moved to End Session modal as session visual summary

fix: server error

fix: increase GPU duration to 120s, prefetch FLUX weights on startup

fix: increase GPU duration to 120s, prefetch FLUX weights on startup

fix: FLUX.2-klein reajust

fix: FLUX.2-klein prompt keyword arg, image for all verdicts

feat: switch to FLUX.2-klein-4B for image generation

feat: FLUX.1-schnell image generation after correct answers

ui: replace mode pills with large cards (icon, title, desc, check indicator)

remove: source passage section and Open Q/MCQ mode toggle from UI

fix: English only, remove language toggle

fix: MCQ onclick via closure, add FR/EN language pills wired to hidden textbox

feat: add MCQ mode with 4 options, client-side evaluation and per-choice explanations