Ready to Rumble

.dockerignore

@@ -0,0 +1,9 @@
+
+frontend/node_modules
+frontend/dist
+__pycache__/
+*.pyc
+*.pyo
+.git
+.gitignore
+.DS_Store

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,39 @@
+
+# --- Stage 1: Build React frontend ---
+FROM node:20-alpine AS frontend
+WORKDIR /app/frontend
+COPY frontend/package*.json ./
+RUN npm ci
+COPY frontend/ ./
+RUN npm run build
+
+# --- Stage 2: GPU-enabled Python backend ---
+# Requires NVIDIA Container Toolkit on host and runtime flag: --gpus all
+FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04 AS backend
+
+ENV DEBIAN_FRONTEND=noninteractive             PYTHONDONTWRITEBYTECODE=1             PYTHONUNBUFFERED=1             PIP_NO_CACHE_DIR=1
+
+# Install Python and system deps
+RUN apt-get update && apt-get install -y --no-install-recommends             python3 python3-pip python3-venv git &&             rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Install CUDA-enabled PyTorch (cu121)
+RUN python3 -m pip install --upgrade pip &&             python3 -m pip install --index-url https://download.pytorch.org/whl/cu121 torch==2.4.1+cu121
+
+# Install remaining Python deps
+COPY backend/requirements.txt /app/backend/requirements.txt
+RUN python3 -m pip install -r /app/backend/requirements.txt
+
+# Copy backend code
+COPY backend/ /app/backend/
+
+# Copy frontend build to a static dir served by FastAPI
+RUN mkdir -p /app/static
+COPY --from=frontend /app/frontend/dist/ /app/static/
+
+ENV STATIC_DIR=/app/static             MODEL_ID=FractalAIResearch/Fathom-R1-14B             PIPELINE_TASK=text-generation             QUANTIZE=auto
+
+EXPOSE 8000
+
+CMD ["uvicorn", "app.main:app", "--app-dir", "/app/backend", "--host", "0.0.0.0", "--port", "8000"]

README.md

@@ -1,12 +1,43 @@
----
-title: Fathom R1 Chat
-emoji: 🚀
-colorFrom: pink
-colorTo: pink
-sdk: docker
-pinned: false
-license: mit
-short_description: Solve Math; Don't Cheat
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+# Fathom R1 Chat — Full‑stack (React + FastAPI)
+
+ChatGPT‑style UI on React + a FastAPI backend that calls **FractalAIResearch/Fathom-R1-14B** via `transformers`.
+
+## Run with Docker (GPU)
+
+> Requires an NVIDIA GPU + NVIDIA Container Toolkit.
+
+```bash
+docker build -t fathom-r1-chat .
+docker run --gpus all -p 8000:8000           -e MODEL_ID=FractalAIResearch/Fathom-R1-14B           -e QUANTIZE=auto           fathom-r1-chat
+# Open http://localhost:8000
+```
+
+### Notes
+- Model is derived from **DeepSeek-R1-Distill-Qwen-14B** and targets **16K context** usage. Use the tokenizer chat template.
+- For long answers, bump `max_new_tokens` in the request.
+- If you need private HF access, pass `-e HUGGING_FACE_HUB_TOKEN=...`.
+
+## Dev mode (run separately)
+```bash
+# backend
+cd backend
+python3 -m venv .venv && source .venv/bin/activate
+pip install --index-url https://download.pytorch.org/whl/cu121 torch==2.4.1+cu121
+pip install -r requirements.txt
+uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload
+
+# frontend (new terminal)
+cd frontend
+npm ci
+npm run dev
+```
+
+## API
+- `POST /api/chat` with `{ messages: [{role, content}, ...], max_new_tokens, temperature, top_p }` → `{ reply, model }`
+
+## Hardware
+- 14B parameter model; for comfortable generation use **>=24–40 GB VRAM** or 4/8‑bit quantization on 16–24 GB GPUs.
+
+## License
+- MIT (model card states MIT) and this template is MIT.