Skip to content

A ~9M parameter LLM that talks like a small fish.

Python

Split into train + use notebooks, add interactive chat

Arman Hossain96830cbfa7dc
diff --git a/README.md b/README.md
index 3a989f2..18511c6 100644
--- a/README.md
+++ b/README.md
@@ -8,7 +8,8 @@
<p align="center">
<a href="https://huggingface.co/datasets/arman-bd/guppylm-60k-generic"><img src="https://img.shields.io/badge/πŸ€—_Dataset-guppylm--60k-blue" alt="Dataset"/></a>&nbsp;
<a href="https://huggingface.co/arman-bd/guppylm-9M"><img src="https://img.shields.io/badge/πŸ€—_Model-guppylm--9M-orange" alt="Model"/></a>&nbsp;
- <a href="https://colab.research.google.com/github/arman-bd/guppylm/blob/main/guppy_colab.ipynb"><img src="https://img.shields.io/badge/Open_in-Colab-F9AB00?logo=googlecolab" alt="Colab"/></a>&nbsp;
+ <a href="https://colab.research.google.com/github/arman-bd/guppylm/blob/main/train_guppylm.ipynb"><img src="https://img.shields.io/badge/Train_in-Colab-F9AB00?logo=googlecolab" alt="Train"/></a>&nbsp;
+ <a href="https://colab.research.google.com/github/arman-bd/guppylm/blob/main/use_guppylm.ipynb"><img src="https://img.shields.io/badge/Chat_in-Colab-F9AB00?logo=googlecolab" alt="Chat"/></a>&nbsp;
<a href="https://github.com/arman-bd/guppylm/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MIT-green" alt="License"/></a>
</p>
@@ -88,12 +89,19 @@ Guppy:
## Quick Start
-### Train on Colab
+### Chat with Guppy (no training needed)
-1. Upload [`guppy_colab.ipynb`](guppy_colab.ipynb) to [Google Colab](https://colab.research.google.com)
-2. Set runtime to **T4 GPU**
-3. **Run all cells** β€” downloads dataset, trains tokenizer, trains model, tests it
-4. Download the trained model (~35 MB)
+[![Open in Colab](https://img.shields.io/badge/Chat_in-Colab-F9AB00?logo=googlecolab)](https://colab.research.google.com/github/arman-bd/guppylm/blob/main/use_guppylm.ipynb)
+
+Downloads the pre-trained model from HuggingFace and lets you chat. Just run all cells.
+
+### Train your own
+
+[![Open in Colab](https://img.shields.io/badge/Train_in-Colab-F9AB00?logo=googlecolab)](https://colab.research.google.com/github/arman-bd/guppylm/blob/main/train_guppylm.ipynb)
+
+1. Set runtime to **T4 GPU**
+2. **Run all cells** β€” downloads dataset, trains tokenizer, trains model, tests it
+3. Upload to HuggingFace or download locally
### Chat locally
diff --git a/tools/dataset_card.md b/tools/dataset_card.md
index 5317219..a5f6fa4 100644
--- a/tools/dataset_card.md
+++ b/tools/dataset_card.md
@@ -21,7 +21,7 @@ pretty_name: GuppyLM Chat
<p align="center">
<a href="https://github.com/arman-bd/guppylm"><img src="https://img.shields.io/badge/GitHub-guppylm-181717?logo=github" alt="GitHub"/></a>&nbsp;
<a href="https://huggingface.co/arman-bd/guppylm-9M"><img src="https://img.shields.io/badge/πŸ€—_Model-guppylm--9M-orange" alt="Model"/></a>&nbsp;
- <a href="https://colab.research.google.com/github/arman-bd/guppylm/blob/main/guppy_colab.ipynb"><img src="https://img.shields.io/badge/Open_in-Colab-F9AB00?logo=googlecolab" alt="Colab"/></a>
+ <a href="https://colab.research.google.com/github/arman-bd/guppylm/blob/main/train_guppylm.ipynb"><img src="https://img.shields.io/badge/Open_in-Colab-F9AB00?logo=googlecolab" alt="Colab"/></a>
</p>
# GuppyLM Chat Dataset
diff --git a/tools/make_colab.py b/tools/make_colab.py
index fe3cdc6..e2a99e4 100644
--- a/tools/make_colab.py
+++ b/tools/make_colab.py
@@ -83,7 +83,7 @@ def build():
))
cells.append(code(
- "!pip install -q torch tokenizers tqdm numpy datasets\n"
+ "!pip install -q torch tokenizers tqdm numpy datasets huggingface_hub\n"
"\n"
"import torch\n"
"print(f'PyTorch {torch.__version__}')\n"
@@ -287,21 +287,52 @@ def build():
))
# ══════════════════════════════════════════════════════════════════
- # 7. DOWNLOAD
+ # 7. UPLOAD TO HUGGINGFACE
# ══════════════════════════════════════════════════════════════════
cells.append(md(
- "## 7. Download\n"
+ "## 7. Upload to HuggingFace\n"
"\n"
- "Package the trained model for local use.\n"
+ "Push the trained model to HuggingFace Hub.\n"
+ "Set your token and repo below."
+ ))
+
+ cells.append(code(
+ "from huggingface_hub import HfApi, login\n"
+ "import os\n"
"\n"
- "```python\n"
- "# Run locally after downloading:\n"
- "from inference import GuppyInference\n"
- "engine = GuppyInference('checkpoints/best_model.pt', 'data/tokenizer.json')\n"
- "r = engine.chat_completion([{'role': 'user', 'content': 'hi guppy'}])\n"
- "print(r['choices'][0]['message']['content'])\n"
- "```"
+ "HF_TOKEN = '' # Paste your HF token here\n"
+ "HF_REPO = 'arman-bd/guppylm-9M' # Change to your repo\n"
+ "\n"
+ "if not HF_TOKEN:\n"
+ " print('Set HF_TOKEN above to upload. Skipping.')\n"
+ "else:\n"
+ " login(token=HF_TOKEN)\n"
+ " api = HfApi()\n"
+ " api.create_repo(HF_REPO, exist_ok=True)\n"
+ "\n"
+ " # Upload model checkpoint, tokenizer, and source files\n"
+ " for path in ['checkpoints/best_model.pt', 'checkpoints/config.json',\n"
+ " 'data/tokenizer.json', 'model.py', 'config.py', 'inference.py']:\n"
+ " if os.path.exists(path):\n"
+ " api.upload_file(\n"
+ " path_or_fileobj=path,\n"
+ " path_in_repo=path,\n"
+ " repo_id=HF_REPO,\n"
+ " )\n"
+ " print(f' Uploaded {path}')\n"
+ "\n"
+ " print(f'\\nDone! https://huggingface.co/{HF_REPO}')"
+ ))
+
+ # ══════════════════════════════════════════════════════════════════
+ # 8. DOWNLOAD
+ # ══════════════════════════════════════════════════════════════════
+
+ cells.append(md(
+ "## 8. Download\n"
+ "\n"
+ "Or download the model locally as a tar.gz."
))
cells.append(code(
@@ -330,7 +361,7 @@ def build():
return {
"nbformat": 4, "nbformat_minor": 0,
"metadata": {
- "colab": {"provenance": [], "gpuType": "T4", "name": "GuppyLM β€” Train a Fish"},
+ "colab": {"provenance": [], "gpuType": "T4", "name": "GuppyLM β€” Train"},
"kernelspec": {"name": "python3", "display_name": "Python 3"},
"language_info": {"name": "python"},
"accelerator": "GPU",
@@ -339,11 +370,161 @@ def build():
}
-if __name__ == "__main__":
- nb = build()
- out = os.path.join(PROJECT_ROOT, "guppy_colab.ipynb")
+def build_use():
+ """Build the use_guppylm notebook β€” download model from HF and chat."""
+ cells = []
+
+ cells.append(md(
+ "# GuppyLM β€” Chat with a Fish\n"
+ "\n"
+ "Download the pre-trained GuppyLM model from HuggingFace and chat with it.\n"
+ "No training needed β€” just run all cells.\n"
+ "\n"
+ "**Model:** [arman-bd/guppylm-9M](https://huggingface.co/arman-bd/guppylm-9M) (8.7M params)"
+ ))
+
+ # ── Setup ──────────────────────────────────────────────────────
+
+ cells.append(md("## 1. Setup"))
+
+ cells.append(code(
+ "!pip install -q torch tokenizers huggingface_hub\n"
+ "\n"
+ "import torch\n"
+ "print(f'PyTorch {torch.__version__}')\n"
+ "print(f'CUDA: {torch.cuda.is_available()}')"
+ ))
+
+ cells.append(code(
+ "import os, shutil\n"
+ "if os.path.exists('/content/guppy'):\n"
+ " shutil.rmtree('/content/guppy')\n"
+ "os.makedirs('/content/guppy')\n"
+ "os.chdir('/content/guppy')\n"
+ "print(f'Working dir: {os.getcwd()}')"
+ ))
+
+ # ── Download model ─────────────────────────────────────────────
+
+ cells.append(md(
+ "## 2. Download Model\n"
+ "\n"
+ "Download the pre-trained model, tokenizer, and inference code from HuggingFace."
+ ))
+
+ cells.append(code(
+ "from huggingface_hub import hf_hub_download\n"
+ "import os\n"
+ "\n"
+ "HF_REPO = 'arman-bd/guppylm-9M'\n"
+ "\n"
+ "files = [\n"
+ " ('checkpoints/best_model.pt', 'checkpoints'),\n"
+ " ('checkpoints/config.json', 'checkpoints'),\n"
+ " ('data/tokenizer.json', 'data'),\n"
+ " ('model.py', '.'),\n"
+ " ('config.py', '.'),\n"
+ " ('inference.py', '.'),\n"
+ "]\n"
+ "\n"
+ "for filename, subdir in files:\n"
+ " os.makedirs(subdir, exist_ok=True)\n"
+ " hf_hub_download(\n"
+ " repo_id=HF_REPO,\n"
+ " filename=filename,\n"
+ " local_dir='.',\n"
+ " )\n"
+ " print(f' Downloaded {filename}')\n"
+ "\n"
+ "print(f'\\nModel ready from {HF_REPO}')"
+ ))
+
+ # ── Chat ───────────────────────────────────────────────────────
+
+ cells.append(md(
+ "## 3. Chat\n"
+ "\n"
+ "Talk to Guppy. Each message is independent (single-turn)."
+ ))
+
+ cells.append(code(
+ "from inference import GuppyInference\n"
+ "import torch\n"
+ "\n"
+ "engine = GuppyInference(\n"
+ " 'checkpoints/best_model.pt', 'data/tokenizer.json',\n"
+ " device='cuda' if torch.cuda.is_available() else 'cpu'\n"
+ ")\n"
+ "\n"
+ "def chat(prompt):\n"
+ " r = engine.chat_completion([{'role': 'user', 'content': prompt}], max_tokens=64)\n"
+ " return r['choices'][0]['message'].get('content', '').strip()"
+ ))
+
+ cells.append(code(
+ "# Try different topics\n"
+ "tests = [\n"
+ " 'hi guppy',\n"
+ " 'are you hungry',\n"
+ " 'it is really hot today',\n"
+ " 'do you like bubbles',\n"
+ " 'what is the meaning of life',\n"
+ " 'tell me a joke',\n"
+ " 'the cat is looking at you',\n"
+ " 'do you love me',\n"
+ " 'what is the internet',\n"
+ " 'goodnight guppy',\n"
+ "]\n"
+ "\n"
+ "for prompt in tests:\n"
+ " reply = chat(prompt)\n"
+ " print(f'You> {prompt}')\n"
+ " print(f'Guppy> {reply}')\n"
+ " print()"
+ ))
+
+ cells.append(md(
+ "## 4. Interactive Chat\n"
+ "\n"
+ "Type your own messages. Type `quit` to stop."
+ ))
+
+ cells.append(code(
+ "print('Chat with Guppy (type quit to stop)')\n"
+ "print('=' * 40)\n"
+ "while True:\n"
+ " try:\n"
+ " prompt = input('You> ').strip()\n"
+ " except (KeyboardInterrupt, EOFError):\n"
+ " break\n"
+ " if not prompt or prompt.lower() in ('quit', 'exit', 'q'):\n"
+ " print('Guppy> bye. i will continue being a fish.')\n"
+ " break\n"
+ " reply = chat(prompt)\n"
+ " print(f'Guppy> {reply}')\n"
+ " print()"
+ ))
+
+ return {
+ "nbformat": 4, "nbformat_minor": 0,
+ "metadata": {
+ "colab": {"provenance": [], "name": "GuppyLM β€” Chat"},
+ "kernelspec": {"name": "python3", "display_name": "Python 3"},
+ "language_info": {"name": "python"},
+ },
+ "cells": cells,
+ }
+
+
+def write_notebook(nb, filename):
+ out = os.path.join(PROJECT_ROOT, filename)
with open(out, "w") as f:
json.dump(nb, f, indent=1)
n = len(nb["cells"])
sz = os.path.getsize(out) / 1024
print(f"Generated {out}: {n} cells, {sz:.1f} KB")
+
+
+if __name__ == "__main__":
+ write_notebook(build(), "train_guppylm.ipynb")
+ write_notebook(build_use(), "use_guppylm.ipynb")
diff --git a/tools/model_card.md b/tools/model_card.md
index 22693ad..56e623e 100644
--- a/tools/model_card.md
+++ b/tools/model_card.md
@@ -18,7 +18,7 @@ pipeline_tag: text-generation
<p align="center">
<a href="https://github.com/arman-bd/guppylm"><img src="https://img.shields.io/badge/GitHub-guppylm-181717?logo=github" alt="GitHub"/></a>&nbsp;
<a href="https://huggingface.co/datasets/arman-bd/guppylm-60k-generic"><img src="https://img.shields.io/badge/πŸ€—_Dataset-guppylm--60k-blue" alt="Dataset"/></a>&nbsp;
- <a href="https://colab.research.google.com/github/arman-bd/guppylm/blob/main/guppy_colab.ipynb"><img src="https://img.shields.io/badge/Open_in-Colab-F9AB00?logo=googlecolab" alt="Colab"/></a>
+ <a href="https://colab.research.google.com/github/arman-bd/guppylm/blob/main/use_guppylm.ipynb"><img src="https://img.shields.io/badge/Open_in-Colab-F9AB00?logo=googlecolab" alt="Colab"/></a>
</p>
# GuppyLM β€” 9M Parameter Fish Chat Model
diff --git a/guppy_colab.ipynb b/train_guppylm.ipynb
similarity index 54%
rename from guppy_colab.ipynb
rename to train_guppylm.ipynb
index 17dc9c4..b3d7600 100644
--- a/guppy_colab.ipynb
+++ b/train_guppylm.ipynb
@@ -1,10 +1,27 @@
{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "provenance": [],
+ "gpuType": "T4",
+ "name": "GuppyLM \u2014 Train"
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ },
+ "accelerator": "GPU"
+ },
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
- "# GuppyLM β€” Your Friendly Fish\n",
+ "# GuppyLM \u2014 Your Friendly Fish\n",
"\n",
"Train a ~9M parameter LLM that talks like a small fish.\n",
"\n",
@@ -32,52 +49,34 @@
},
{
"cell_type": "code",
- "execution_count": 1,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "PyTorch 2.10.0+cu128\n",
- "CUDA: True\n",
- "GPU: Tesla T4\n"
- ]
- }
- ],
"source": [
- "!pip install -q torch tokenizers tqdm numpy datasets\n",
+ "!pip install -q torch tokenizers tqdm numpy datasets huggingface_hub\n",
"\n",
"import torch\n",
"print(f'PyTorch {torch.__version__}')\n",
"print(f'CUDA: {torch.cuda.is_available()}')\n",
"if torch.cuda.is_available():\n",
" print(f'GPU: {torch.cuda.get_device_name(0)}')"
- ]
+ ],
+ "outputs": [],
+ "execution_count": null
},
{
"cell_type": "code",
- "execution_count": 2,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Working dir: /content/guppy\n"
- ]
- }
- ],
"source": [
"import os, shutil\n",
"\n",
- "# Start fresh β€” removes stale files from previous runs\n",
+ "# Start fresh \u2014 removes stale files from previous runs\n",
"if os.path.exists('/content/guppy'):\n",
" shutil.rmtree('/content/guppy')\n",
"os.makedirs('/content/guppy')\n",
"os.chdir('/content/guppy')\n",
"print(f'Working dir: {os.getcwd()}')"
- ]
+ ],
+ "outputs": [],
+ "execution_count": null
},
{
"cell_type": "markdown",
@@ -86,26 +85,16 @@
"## 2. Source Files\n",
"\n",
"Write the model code to disk. These are the only files needed:\n",
- "- `config.py` β€” model and training hyperparameters\n",
- "- `model.py` β€” transformer architecture\n",
- "- `dataset.py` β€” data loading and batching\n",
- "- `train.py` β€” training loop\n",
- "- `inference.py` β€” chat interface"
+ "- `config.py` \u2014 model and training hyperparameters\n",
+ "- `model.py` \u2014 transformer architecture\n",
+ "- `dataset.py` \u2014 data loading and batching\n",
+ "- `train.py` \u2014 training loop\n",
+ "- `inference.py` \u2014 chat interface"
]
},
{
"cell_type": "code",
- "execution_count": 3,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Writing config.py\n"
- ]
- }
- ],
"source": [
"%%writefile config.py\n",
"\"\"\"GuppyLM configuration.\"\"\"\n",
@@ -143,26 +132,19 @@
" device: str = \"auto\"\n",
" seed: int = 42\n",
" data_dir: str = \"data\"\n",
- " output_dir: str = \"checkpoints\"\n"
- ]
+ " output_dir: str = \"checkpoints\"\n",
+ ""
+ ],
+ "outputs": [],
+ "execution_count": null
},
{
"cell_type": "code",
- "execution_count": 4,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Writing model.py\n"
- ]
- }
- ],
"source": [
"%%writefile model.py\n",
"\"\"\"\n",
- "GuppyLM β€” a tiny fish brain.\n",
+ "GuppyLM \u2014 a tiny fish brain.\n",
"\n",
"Vanilla transformer: multi-head attention, ReLU FFN, LayerNorm, learned positional embeddings.\n",
"No GQA, no SwiGLU, no parallel residual, no RoPE. As simple as it gets.\n",
@@ -289,22 +271,15 @@
"\n",
" def param_summary(self):\n",
" total, _ = self.param_count()\n",
- " return f\"GuppyLM: {total:,} params ({total/1e6:.1f}M)\"\n"
- ]
+ " return f\"GuppyLM: {total:,} params ({total/1e6:.1f}M)\"\n",
+ ""
+ ],
+ "outputs": [],
+ "execution_count": null
},
{
"cell_type": "code",
- "execution_count": 5,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Writing dataset.py\n"
- ]
- }
- ],
"source": [
"%%writefile dataset.py\n",
"\"\"\"GuppyLM dataset loading.\"\"\"\n",
@@ -357,22 +332,15 @@
" return DataLoader(\n",
" dataset, batch_size=batch_size, shuffle=shuffle,\n",
" collate_fn=collate_fn, num_workers=0, pin_memory=True,\n",
- " )\n"
- ]
+ " )\n",
+ ""
+ ],
+ "outputs": [],
+ "execution_count": null
},
{
"cell_type": "code",
- "execution_count": 6,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Writing train.py\n"
- ]
- }
- ],
"source": [
"%%writefile train.py\n",
"\"\"\"GuppyLM training loop.\"\"\"\n",
@@ -535,25 +503,18 @@
"\n",
"\n",
"if __name__ == \"__main__\":\n",
- " train()\n"
- ]
+ " train()\n",
+ ""
+ ],
+ "outputs": [],
+ "execution_count": null
},
{
"cell_type": "code",
- "execution_count": 7,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Writing inference.py\n"
- ]
- }
- ],
"source": [
"%%writefile inference.py\n",
- "\"\"\"GuppyLM inference β€” simple chat.\"\"\"\n",
+ "\"\"\"GuppyLM inference \u2014 simple chat.\"\"\"\n",
"\n",
"import json\n",
"import time\n",
@@ -584,7 +545,7 @@
"\n",
" def chat_completion(self, messages, temperature=0.7, max_tokens=64,\n",
" top_k=50, **kwargs):\n",
- " \"\"\"Chat completion β€” takes messages, returns response.\"\"\"\n",
+ " \"\"\"Chat completion \u2014 takes messages, returns response.\"\"\"\n",
" prompt = self._format_prompt(messages)\n",
" input_ids = self.tokenizer.encode(prompt).ids\n",
" prompt_tokens = len(input_ids)\n",
@@ -592,7 +553,7 @@
"\n",
" output_t, _ = self.model.generate(input_t, max_tokens, temperature, top_k)\n",
" output_text = self.tokenizer.decode(output_t[0].tolist()[prompt_tokens:])\n",
- " # Truncate at first <|im_end|> β€” don't let the model leak into the next turn\n",
+ " # Truncate at first <|im_end|> \u2014 don't let the model leak into the next turn\n",
" if \"<|im_end|>\" in output_text:\n",
" output_text = output_text.split(\"<|im_end|>\")[0]\n",
" # Also strip any <|im_start|> fragments\n",
@@ -642,8 +603,11 @@
"\n",
"\n",
"if __name__ == \"__main__\":\n",
- " main()\n"
- ]
+ " main()\n",
+ ""
+ ],
+ "outputs": [],
+ "execution_count": null
},
{
"cell_type": "markdown",
@@ -667,126 +631,18 @@
},
{
"cell_type": "code",
- "execution_count": 8,
"metadata": {},
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "/usr/local/lib/python3.12/dist-packages/huggingface_hub/utils/_auth.py:104: UserWarning: \n",
- "Error while fetching `HF_TOKEN` secret value from your vault: 'Requesting secret HF_TOKEN timed out. Secrets can only be fetched when running from the Colab UI.'.\n",
- "You are not authenticated with the Hugging Face Hub in this notebook.\n",
- "If the error persists, please let us know by opening an issue on GitHub (https://github.com/huggingface/huggingface_hub/issues/new).\n",
- " warnings.warn(\n"
- ]
- },
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "e9ab300612fd4b9b8cef97a653463677",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "README.md: 0.00B [00:00, ?B/s]"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.\n",
- "WARNING:huggingface_hub.utils._http:Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.\n"
- ]
- },
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "00f09b71d216412089184ac027fec981",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "data/train-00000-of-00001.parquet: 0%| | 0.00/557k [00:00<?, ?B/s]"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "063737a546b9414da8c2bac2e7621692",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "data/test-00000-of-00001.parquet: 0%| | 0.00/57.9k [00:00<?, ?B/s]"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "aa23e29731c949d2b819fa1967ef15e6",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "Generating train split: 0%| | 0/57000 [00:00<?, ? examples/s]"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "ad886029d1084ca7b60f234e96a77d9d",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "Generating test split: 0%| | 0/3000 [00:00<?, ? examples/s]"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Downloaded: 57,000 train, 3,000 test samples\n",
- " data/train.jsonl: 57,000 samples\n",
- " data/eval.jsonl: 3,000 samples\n",
- " Tokenizer: 2418 tokens\n",
- "\n",
- "Sample (temp_cold):\n",
- "<|im_start|>user\n",
- "i need a heater<|im_end|>\n",
- "<|im_start|>assistant\n",
- "the water feels cool today. i just hide and wait.<|im_end|>\n"
- ]
- }
- ],
"source": [
"import json, os\n",
"from datasets import load_dataset\n",
"from tokenizers import Tokenizer, models, trainers, pre_tokenizers, decoders, processors\n",
"\n",
- "# ── Download from HuggingFace ──\n",
+ "# \u2500\u2500 Download from HuggingFace \u2500\u2500\n",
"HF_DATASET = 'arman-bd/guppylm-60k-generic'\n",
"ds = load_dataset(HF_DATASET)\n",
"print(f'Downloaded: {len(ds[\"train\"]):,} train, {len(ds[\"test\"]):,} test samples')\n",
"\n",
- "# ── Format into ChatML and save as JSONL ──\n",
+ "# \u2500\u2500 Format into ChatML and save as JSONL \u2500\u2500\n",
"os.makedirs('data', exist_ok=True)\n",
"texts = []\n",
"\n",
@@ -801,7 +657,7 @@
" texts.append(text)\n",
" print(f' {path}: {len(ds[split]):,} samples')\n",
"\n",
- "# ── Train BPE tokenizer on the data ──\n",
+ "# \u2500\u2500 Train BPE tokenizer on the data \u2500\u2500\n",
"tokenizer = Tokenizer(models.BPE())\n",
"tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel(add_prefix_space=False)\n",
"tokenizer.decoder = decoders.ByteLevel()\n",
@@ -817,11 +673,13 @@
"tokenizer.save('data/tokenizer.json')\n",
"print(f' Tokenizer: {tokenizer.get_vocab_size()} tokens')\n",
"\n",
- "# ── Preview ──\n",
+ "# \u2500\u2500 Preview \u2500\u2500\n",
"with open('data/train.jsonl') as f:\n",
" sample = json.loads(f.readline())\n",
"print(f'\\nSample ({sample[\"category\"]}):\\n{sample[\"text\"]}')"
- ]
+ ],
+ "outputs": [],
+ "execution_count": null
},
{
"cell_type": "markdown",
@@ -829,25 +687,12 @@
"source": [
"## 4. Verify Architecture\n",
"\n",
- "Quick sanity check β€” build the model, print param count, run a dummy forward pass."
+ "Quick sanity check \u2014 build the model, print param count, run a dummy forward pass."
]
},
{
"cell_type": "code",
- "execution_count": 9,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "GuppyLM: 8,726,016 params (8.7M)\n",
- " Layers: 6, Heads: 6, FFN: 768\n",
- " Vocab: 4096, Max seq: 128\n",
- " Forward pass: torch.Size([2, 32]) -> torch.Size([2, 32, 4096]) OK\n"
- ]
- }
- ],
"source": [
"from config import GuppyConfig\n",
"from model import GuppyLM\n",
@@ -864,7 +709,9 @@
"logits, _ = model(x)\n",
"print(f' Forward pass: {x.shape} -> {logits.shape} OK')\n",
"del model"
- ]
+ ],
+ "outputs": [],
+ "execution_count": null
},
{
"cell_type": "markdown",
@@ -883,220 +730,13 @@
},
{
"cell_type": "code",
- "execution_count": 10,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Device: cuda\n",
- "GuppyLM: 8,726,016 params (8.7M)\n",
- "Train: 57,000, Eval: 3,000\n",
- "\n",
- "Training for 10000 steps...\n",
- " Step | LR | Train | Eval | Time\n",
- "--------------------------------------------------------\n",
- " 0 | 0.000000 | 8.4972 | -- | 1.0s\n",
- " 100 | 0.000150 | 5.7581 | -- | 3.5s\n",
- " 200 | 0.000300 | 3.2231 | -- | 5.9s\n",
- " 200 | 0.000300 | 4.4906 | 2.7493 | 6.3s\n",
- " -> Best model (eval=2.7493)\n",
- " 300 | 0.000300 | 2.4972 | -- | 8.8s\n",
- " 400 | 0.000300 | 2.0159 | -- | 11.8s\n",
- " 400 | 0.000300 | 2.2566 | 1.7105 | 12.3s\n",
- " -> Best model (eval=1.7105)\n",
- " 500 | 0.000299 | 1.6539 | -- | 14.8s\n",
- " 600 | 0.000299 | 1.3577 | -- | 17.3s\n",
- " 600 | 0.000299 | 1.5058 | 1.1083 | 17.8s\n",
- " -> Best model (eval=1.1083)\n",
- " 700 | 0.000298 | 1.1433 | -- | 20.2s\n",
- " 800 | 0.000298 | 0.9510 | -- | 23.0s\n",
- " 800 | 0.000298 | 1.0472 | 0.7740 | 23.5s\n",
- " -> Best model (eval=0.7740)\n",
- " 900 | 0.000297 | 0.8354 | -- | 26.2s\n",
- " 1000 | 0.000296 | 0.7302 | -- | 28.6s\n",
- " 1000 | 0.000296 | 0.7828 | 0.6078 | 29.1s\n",
- " -> Best model (eval=0.6078)\n",
- " 1100 | 0.000294 | 0.6600 | -- | 31.7s\n",
- " 1200 | 0.000293 | 0.6254 | -- | 34.3s\n",
- " 1200 | 0.000293 | 0.6427 | 0.5268 | 34.8s\n",
- " -> Best model (eval=0.5268)\n",
- " 1300 | 0.000292 | 0.5897 | -- | 37.8s\n",
- " 1400 | 0.000290 | 0.5569 | -- | 40.3s\n",
- " 1400 | 0.000290 | 0.5733 | 0.4896 | 40.8s\n",
- " -> Best model (eval=0.4896)\n",
- " 1500 | 0.000288 | 0.5441 | -- | 43.3s\n",
- " 1600 | 0.000287 | 0.5200 | -- | 45.7s\n",
- " 1600 | 0.000287 | 0.5320 | 0.4802 | 46.2s\n",
- " -> Best model (eval=0.4802)\n",
- " 1700 | 0.000285 | 0.5175 | -- | 49.4s\n",
- " 1800 | 0.000283 | 0.4995 | -- | 51.9s\n",
- " 1800 | 0.000283 | 0.5085 | 0.4589 | 52.3s\n",
- " -> Best model (eval=0.4589)\n",
- " 1900 | 0.000280 | 0.4888 | -- | 54.9s\n",
- " 2000 | 0.000278 | 0.4814 | -- | 57.3s\n",
- " 2000 | 0.000278 | 0.4851 | 0.4499 | 57.8s\n",
- " -> Best model (eval=0.4499)\n",
- " 2100 | 0.000276 | 0.4791 | -- | 61.0s\n",
- " 2200 | 0.000273 | 0.4718 | -- | 63.4s\n",
- " 2200 | 0.000273 | 0.4755 | 0.4438 | 63.9s\n",
- " -> Best model (eval=0.4438)\n",
- " 2300 | 0.000271 | 0.4645 | -- | 66.5s\n",
- " 2400 | 0.000268 | 0.4665 | -- | 69.1s\n",
- " 2400 | 0.000268 | 0.4655 | 0.4378 | 69.6s\n",
- " -> Best model (eval=0.4378)\n",
- " 2500 | 0.000265 | 0.4660 | -- | 72.7s\n",
- " 2600 | 0.000262 | 0.4555 | -- | 75.2s\n",
- " 2600 | 0.000262 | 0.4607 | 0.4372 | 75.7s\n",
- " -> Best model (eval=0.4372)\n",
- " 2700 | 0.000259 | 0.4556 | -- | 78.2s\n",
- " 2800 | 0.000256 | 0.4497 | -- | 80.6s\n",
- " 2800 | 0.000256 | 0.4526 | 0.4305 | 81.1s\n",
- " -> Best model (eval=0.4305)\n",
- " 2900 | 0.000253 | 0.4472 | -- | 83.8s\n",
- " 3000 | 0.000249 | 0.4479 | -- | 86.5s\n",
- " 3000 | 0.000249 | 0.4476 | 0.4276 | 87.0s\n",
- " -> Best model (eval=0.4276)\n",
- " 3100 | 0.000246 | 0.4459 | -- | 89.6s\n",
- " 3200 | 0.000242 | 0.4427 | -- | 92.0s\n",
- " 3200 | 0.000242 | 0.4443 | 0.4226 | 92.5s\n",
- " -> Best model (eval=0.4226)\n",
- " 3300 | 0.000239 | 0.4441 | -- | 95.2s\n",
- " 3400 | 0.000235 | 0.4389 | -- | 98.1s\n",
- " 3400 | 0.000235 | 0.4415 | 0.4226 | 98.6s\n",
- " -> Best model (eval=0.4226)\n",
- " 3500 | 0.000231 | 0.4349 | -- | 101.1s\n",
- " 3600 | 0.000227 | 0.4331 | -- | 103.5s\n",
- " 3600 | 0.000227 | 0.4340 | 0.4203 | 104.0s\n",
- " -> Best model (eval=0.4203)\n",
- " 3700 | 0.000224 | 0.4359 | -- | 106.5s\n",
- " 3800 | 0.000220 | 0.4273 | -- | 109.6s\n",
- " 3800 | 0.000220 | 0.4316 | 0.4188 | 110.1s\n",
- " -> Best model (eval=0.4188)\n",
- " 3900 | 0.000216 | 0.4258 | -- | 112.6s\n",
- " 4000 | 0.000212 | 0.4291 | -- | 115.1s\n",
- " 4000 | 0.000212 | 0.4274 | 0.4149 | 115.5s\n",
- " -> Best model (eval=0.4149)\n",
- " 4100 | 0.000208 | 0.4254 | -- | 118.2s\n",
- " 4200 | 0.000203 | 0.4248 | -- | 121.0s\n",
- " 4200 | 0.000203 | 0.4251 | 0.4150 | 121.5s\n",
- " 4300 | 0.000199 | 0.4205 | -- | 124.0s\n",
- " 4400 | 0.000195 | 0.4175 | -- | 126.3s\n",
- " 4400 | 0.000195 | 0.4190 | 0.4093 | 126.8s\n",
- " -> Best model (eval=0.4093)\n",
- " 4500 | 0.000191 | 0.4170 | -- | 129.4s\n",
- " 4600 | 0.000187 | 0.4173 | -- | 132.0s\n",
- " 4600 | 0.000187 | 0.4171 | 0.4087 | 132.6s\n",
- " -> Best model (eval=0.4087)\n",
- " 4700 | 0.000182 | 0.4183 | -- | 135.3s\n",
- " 4800 | 0.000178 | 0.4173 | -- | 137.8s\n",
- " 4800 | 0.000178 | 0.4178 | 0.4086 | 138.3s\n",
- " -> Best model (eval=0.4086)\n",
- " 4900 | 0.000174 | 0.4158 | -- | 140.8s\n",
- " 5000 | 0.000169 | 0.4178 | -- | 143.2s\n",
- " 5000 | 0.000169 | 0.4168 | 0.4057 | 143.7s\n",
- " -> Best model (eval=0.4057)\n",
- " 5100 | 0.000165 | 0.4119 | -- | 146.8s\n",
- " 5200 | 0.000161 | 0.4166 | -- | 149.2s\n",
- " 5200 | 0.000161 | 0.4143 | 0.4022 | 149.7s\n",
- " -> Best model (eval=0.4022)\n",
- " 5300 | 0.000156 | 0.4146 | -- | 152.2s\n",
- " 5400 | 0.000152 | 0.4071 | -- | 154.5s\n",
- " 5400 | 0.000152 | 0.4108 | 0.4017 | 155.0s\n",
- " -> Best model (eval=0.4017)\n",
- " 5500 | 0.000148 | 0.4087 | -- | 158.0s\n",
- " 5600 | 0.000143 | 0.4037 | -- | 160.5s\n",
- " 5600 | 0.000143 | 0.4062 | 0.4006 | 161.0s\n",
- " -> Best model (eval=0.4006)\n",
- " 5700 | 0.000139 | 0.4086 | -- | 163.5s\n",
- " 5800 | 0.000135 | 0.4064 | -- | 165.9s\n",
- " 5800 | 0.000135 | 0.4075 | 0.3999 | 166.4s\n",
- " -> Best model (eval=0.3999)\n",
- " 5900 | 0.000131 | 0.4018 | -- | 169.2s\n",
- " 6000 | 0.000127 | 0.4031 | -- | 172.0s\n",
- " 6000 | 0.000127 | 0.4024 | 0.3972 | 172.4s\n",
- " -> Best model (eval=0.3972)\n",
- " 6100 | 0.000122 | 0.4047 | -- | 175.0s\n",
- " 6200 | 0.000118 | 0.4024 | -- | 177.4s\n",
- " 6200 | 0.000118 | 0.4035 | 0.3944 | 177.9s\n",
- " -> Best model (eval=0.3944)\n",
- " 6300 | 0.000114 | 0.4050 | -- | 180.5s\n",
- " 6400 | 0.000110 | 0.4022 | -- | 183.3s\n",
- " 6400 | 0.000110 | 0.4036 | 0.3966 | 183.8s\n",
- " 6500 | 0.000106 | 0.4007 | -- | 186.2s\n",
- " 6600 | 0.000103 | 0.3983 | -- | 188.6s\n",
- " 6600 | 0.000103 | 0.3995 | 0.3933 | 189.1s\n",
- " -> Best model (eval=0.3933)\n",
- " 6700 | 0.000099 | 0.3969 | -- | 191.6s\n",
- " 6800 | 0.000095 | 0.3954 | -- | 194.6s\n",
- " 6800 | 0.000095 | 0.3961 | 0.3947 | 195.0s\n",
- " 6900 | 0.000091 | 0.3981 | -- | 197.5s\n",
- " 7000 | 0.000088 | 0.4002 | -- | 200.0s\n",
- " 7000 | 0.000088 | 0.3991 | 0.3928 | 200.5s\n",
- " -> Best model (eval=0.3928)\n",
- " 7100 | 0.000084 | 0.3980 | -- | 203.1s\n",
- " 7200 | 0.000081 | 0.3916 | -- | 205.9s\n",
- " 7200 | 0.000081 | 0.3948 | 0.3912 | 206.4s\n",
- " -> Best model (eval=0.3912)\n",
- " 7300 | 0.000077 | 0.3913 | -- | 208.9s\n",
- " 7400 | 0.000074 | 0.3922 | -- | 211.4s\n",
- " 7400 | 0.000074 | 0.3917 | 0.3926 | 211.8s\n",
- " 7500 | 0.000071 | 0.3922 | -- | 214.3s\n",
- " 7600 | 0.000068 | 0.3920 | -- | 216.8s\n",
- " 7600 | 0.000068 | 0.3921 | 0.3896 | 217.3s\n",
- " -> Best model (eval=0.3896)\n",
- " 7700 | 0.000065 | 0.3904 | -- | 220.2s\n",
- " 7800 | 0.000062 | 0.3916 | -- | 222.6s\n",
- " 7800 | 0.000062 | 0.3910 | 0.3891 | 223.1s\n",
- " -> Best model (eval=0.3891)\n",
- " 7900 | 0.000059 | 0.3895 | -- | 225.6s\n",
- " 8000 | 0.000057 | 0.3886 | -- | 228.0s\n",
- " 8000 | 0.000057 | 0.3890 | 0.3887 | 228.5s\n",
- " -> Best model (eval=0.3887)\n",
- " 8100 | 0.000054 | 0.3935 | -- | 231.7s\n",
- " 8200 | 0.000052 | 0.3919 | -- | 234.1s\n",
- " 8200 | 0.000052 | 0.3927 | 0.3884 | 234.6s\n",
- " -> Best model (eval=0.3884)\n",
- " 8300 | 0.000050 | 0.3906 | -- | 237.0s\n",
- " 8400 | 0.000047 | 0.3886 | -- | 239.5s\n",
- " 8400 | 0.000047 | 0.3896 | 0.3869 | 240.0s\n",
- " -> Best model (eval=0.3869)\n",
- " 8500 | 0.000045 | 0.3926 | -- | 243.0s\n",
- " 8600 | 0.000043 | 0.3909 | -- | 245.5s\n",
- " 8600 | 0.000043 | 0.3917 | 0.3872 | 246.0s\n",
- " 8700 | 0.000042 | 0.3910 | -- | 248.4s\n",
- " 8800 | 0.000040 | 0.3915 | -- | 250.8s\n",
- " 8800 | 0.000040 | 0.3912 | 0.3859 | 251.3s\n",
- " -> Best model (eval=0.3859)\n",
- " 8900 | 0.000038 | 0.3874 | -- | 254.1s\n",
- " 9000 | 0.000037 | 0.3853 | -- | 256.9s\n",
- " 9000 | 0.000037 | 0.3864 | 0.3866 | 257.4s\n",
- " 9100 | 0.000036 | 0.3843 | -- | 260.0s\n",
- " 9200 | 0.000034 | 0.3882 | -- | 262.5s\n",
- " 9200 | 0.000034 | 0.3863 | 0.3861 | 263.0s\n",
- " 9300 | 0.000033 | 0.3871 | -- | 265.7s\n",
- " 9400 | 0.000032 | 0.3858 | -- | 268.7s\n",
- " 9400 | 0.000032 | 0.3864 | 0.3847 | 269.2s\n",
- " -> Best model (eval=0.3847)\n",
- " 9500 | 0.000032 | 0.3833 | -- | 271.8s\n",
- " 9600 | 0.000031 | 0.3853 | -- | 274.3s\n",
- " 9600 | 0.000031 | 0.3843 | 0.3847 | 274.8s\n",
- " -> Best model (eval=0.3847)\n",
- " 9700 | 0.000031 | 0.3851 | -- | 277.4s\n",
- " 9800 | 0.000030 | 0.3850 | -- | 280.4s\n",
- " 9800 | 0.000030 | 0.3850 | 0.3844 | 280.9s\n",
- " -> Best model (eval=0.3844)\n",
- " 9900 | 0.000030 | 0.3871 | -- | 283.4s\n",
- "\n",
- "Done! 286s, best eval: 0.3844\n"
- ]
- }
- ],
"source": [
"from train import train\n",
"train()"
- ]
+ ],
+ "outputs": [],
+ "execution_count": null
},
{
"cell_type": "markdown",
@@ -1109,34 +749,7 @@
},
{
"cell_type": "code",
- "execution_count": 11,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "GuppyLM loaded: 8.7M params\n",
- "Topic You Guppy\n",
- "====================================================================================================\n",
- "greeting hi guppy oh hello. i'm near the rock. the temperature feels nice.\n",
- "food are you hungry yes. always yes. i've been exploring the cave waiting for this moment. thank you in advance.\n",
- "temperature it is really hot today too warm is not good. i am small and i overheat easy. can you do something about it.\n",
- "water how is the water the water feels a little cloudy right now. i'll swim around behind the plant to feel the new water. the clarity is just right.\n",
- "bubbles do you like bubbles bubbles are great. i swim through them in the corner.\n",
- "confused what is the internet sometimes the temperature changes suddenly. that scares me.\n",
- "lonely do you get lonely i talk to the heater tube sometimes. it doesn't answer. i'm ok alone. fish are used to it. maybe a shrimp. they don't eat the re\n",
- "cat the cat is looking at you tell it i'm not food. please.\n",
- "joke tell me a joke i don't know jokes. but i fell off a rock once. that was funny.\n",
- "dreams what do you dream about maybe fish dream. maybe it's just dark with occasional thoughts.\n",
- "love do you love me if love is wanting someone to stay and bring food then yes.\n",
- "meaning what is the meaning of life i don't think about purpose. i think about food.\n",
- "glass_tap sorry i tapped the glass i know you don't mean it but it scares me.\n",
- "rain it is raining outside tell the rain i said hi.\n",
- "night goodnight guppy goodnight. my little body need a break. goodnight tank. goodnight water.\n"
- ]
- }
- ],
"source": [
"from inference import GuppyInference\n",
"import torch\n",
@@ -1173,59 +786,67 @@
"print('=' * 100)\n",
"for prompt, topic in tests:\n",
" reply = chat(prompt)\n",
- " print(f'{topic:<12s} {prompt:<35s} {reply[:128]}')\n"
- ]
+ " print(f'{topic:<12s} {prompt:<35s} {reply[:128]}')\n",
+ ""
+ ],
+ "outputs": [],
+ "execution_count": null
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
- "## 7. Download\n",
- "\n",
- "Package the trained model for local use.\n",
+ "## 7. Upload to HuggingFace\n",
"\n",
- "```python\n",
- "# Run locally after downloading:\n",
- "from inference import GuppyInference\n",
- "engine = GuppyInference('checkpoints/best_model.pt', 'data/tokenizer.json')\n",
- "r = engine.chat_completion([{'role': 'user', 'content': 'hi guppy'}])\n",
- "print(r['choices'][0]['message']['content'])\n",
- "```"
+ "Push the trained model to HuggingFace Hub.\n",
+ "Set your token and repo below."
]
},
{
"cell_type": "code",
- "execution_count": 12,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Package: /content/guppylm.tar.gz (32.4 MB)\n"
- ]
- },
- {
- "data": {
- "application/javascript": "\n async function download(id, filename, size) {\n if (!google.colab.kernel.accessAllowed) {\n return;\n }\n const div = document.createElement('div');\n const label = document.createElement('label');\n label.textContent = `Downloading \"${filename}\": `;\n div.appendChild(label);\n const progress = document.createElement('progress');\n progress.max = size;\n div.appendChild(progress);\n document.body.appendChild(div);\n\n const buffers = [];\n let downloaded = 0;\n\n const channel = await google.colab.kernel.comms.open(id);\n // Send a message to notify the kernel that we're ready.\n channel.send({})\n\n for await (const message of channel.messages) {\n // Send a message to notify the kernel that we're ready.\n channel.send({})\n if (message.buffers) {\n for (const buffer of message.buffers) {\n buffers.push(buffer);\n downloaded += buffer.byteLength;\n progress.value = downloaded;\n }\n }\n }\n const blob = new Blob(buffers, {type: 'application/binary'});\n const a = document.createElement('a');\n a.href = window.URL.createObjectURL(blob);\n a.download = filename;\n div.appendChild(a);\n a.click();\n div.remove();\n }\n ",
- "text/plain": [
- "<IPython.core.display.Javascript object>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "application/javascript": "download(\"download_9644de2b-5ab7-4a28-a5bf-6741f7ef1cc6\", \"guppylm.tar.gz\", 32436475)",
- "text/plain": [
- "<IPython.core.display.Javascript object>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
+ "source": [
+ "from huggingface_hub import HfApi, login\n",
+ "import os\n",
+ "\n",
+ "HF_TOKEN = '' # Paste your HF token here\n",
+ "HF_REPO = 'arman-bd/guppylm-9M' # Change to your repo\n",
+ "\n",
+ "if not HF_TOKEN:\n",
+ " print('Set HF_TOKEN above to upload. Skipping.')\n",
+ "else:\n",
+ " login(token=HF_TOKEN)\n",
+ " api = HfApi()\n",
+ " api.create_repo(HF_REPO, exist_ok=True)\n",
+ "\n",
+ " # Upload model checkpoint, tokenizer, and source files\n",
+ " for path in ['checkpoints/best_model.pt', 'checkpoints/config.json',\n",
+ " 'data/tokenizer.json', 'model.py', 'config.py', 'inference.py']:\n",
+ " if os.path.exists(path):\n",
+ " api.upload_file(\n",
+ " path_or_fileobj=path,\n",
+ " path_in_repo=path,\n",
+ " repo_id=HF_REPO,\n",
+ " )\n",
+ " print(f' Uploaded {path}')\n",
+ "\n",
+ " print(f'\\nDone! https://huggingface.co/{HF_REPO}')"
],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 8. Download\n",
+ "\n",
+ "Or download the model locally as a tar.gz."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {},
"source": [
"import os\n",
"\n",
@@ -1244,35 +865,10 @@
" from google.colab import files\n",
" files.download('/content/guppylm.tar.gz')\n",
"except ImportError:\n",
- " print('Not in Colab β€” download manually from the file browser.')"
- ]
- }
- ],
- "metadata": {
- "accelerator": "GPU",
- "colab": {
- "gpuType": "T4",
- "name": "GuppyLM β€” Train a Fish",
- "provenance": []
- },
- "kernelspec": {
- "display_name": "Python 3 (ipykernel)",
- "language": "python",
- "name": "python3"
- },
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.12.13"
+ " print('Not in Colab \u2014 download manually from the file browser.')"
+ ],
+ "outputs": [],
+ "execution_count": null
}
- },
- "nbformat": 4,
- "nbformat_minor": 0
-}
+ ]
+}
\ No newline at end of file
diff --git a/use_guppylm.ipynb b/use_guppylm.ipynb
new file mode 100644
index 0000000..01efc68
--- /dev/null
+++ b/use_guppylm.ipynb
@@ -0,0 +1,191 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "provenance": [],
+ "name": "GuppyLM \u2014 Chat"
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# GuppyLM \u2014 Chat with a Fish\n",
+ "\n",
+ "Download the pre-trained GuppyLM model from HuggingFace and chat with it.\n",
+ "No training needed \u2014 just run all cells.\n",
+ "\n",
+ "**Model:** [arman-bd/guppylm-9M](https://huggingface.co/arman-bd/guppylm-9M) (8.7M params)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 1. Setup"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {},
+ "source": [
+ "!pip install -q torch tokenizers huggingface_hub\n",
+ "\n",
+ "import torch\n",
+ "print(f'PyTorch {torch.__version__}')\n",
+ "print(f'CUDA: {torch.cuda.is_available()}')"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "code",
+ "metadata": {},
+ "source": [
+ "import os, shutil\n",
+ "if os.path.exists('/content/guppy'):\n",
+ " shutil.rmtree('/content/guppy')\n",
+ "os.makedirs('/content/guppy')\n",
+ "os.chdir('/content/guppy')\n",
+ "print(f'Working dir: {os.getcwd()}')"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 2. Download Model\n",
+ "\n",
+ "Download the pre-trained model, tokenizer, and inference code from HuggingFace."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {},
+ "source": [
+ "from huggingface_hub import hf_hub_download\n",
+ "import os\n",
+ "\n",
+ "HF_REPO = 'arman-bd/guppylm-9M'\n",
+ "\n",
+ "files = [\n",
+ " ('checkpoints/best_model.pt', 'checkpoints'),\n",
+ " ('checkpoints/config.json', 'checkpoints'),\n",
+ " ('data/tokenizer.json', 'data'),\n",
+ " ('model.py', '.'),\n",
+ " ('config.py', '.'),\n",
+ " ('inference.py', '.'),\n",
+ "]\n",
+ "\n",
+ "for filename, subdir in files:\n",
+ " os.makedirs(subdir, exist_ok=True)\n",
+ " hf_hub_download(\n",
+ " repo_id=HF_REPO,\n",
+ " filename=filename,\n",
+ " local_dir='.',\n",
+ " )\n",
+ " print(f' Downloaded {filename}')\n",
+ "\n",
+ "print(f'\\nModel ready from {HF_REPO}')"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 3. Chat\n",
+ "\n",
+ "Talk to Guppy. Each message is independent (single-turn)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {},
+ "source": [
+ "from inference import GuppyInference\n",
+ "import torch\n",
+ "\n",
+ "engine = GuppyInference(\n",
+ " 'checkpoints/best_model.pt', 'data/tokenizer.json',\n",
+ " device='cuda' if torch.cuda.is_available() else 'cpu'\n",
+ ")\n",
+ "\n",
+ "def chat(prompt):\n",
+ " r = engine.chat_completion([{'role': 'user', 'content': prompt}], max_tokens=64)\n",
+ " return r['choices'][0]['message'].get('content', '').strip()"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "code",
+ "metadata": {},
+ "source": [
+ "# Try different topics\n",
+ "tests = [\n",
+ " 'hi guppy',\n",
+ " 'are you hungry',\n",
+ " 'it is really hot today',\n",
+ " 'do you like bubbles',\n",
+ " 'what is the meaning of life',\n",
+ " 'tell me a joke',\n",
+ " 'the cat is looking at you',\n",
+ " 'do you love me',\n",
+ " 'what is the internet',\n",
+ " 'goodnight guppy',\n",
+ "]\n",
+ "\n",
+ "for prompt in tests:\n",
+ " reply = chat(prompt)\n",
+ " print(f'You> {prompt}')\n",
+ " print(f'Guppy> {reply}')\n",
+ " print()"
+ ],
+ "outputs": [],
+ "execution_count": null
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 4. Interactive Chat\n",
+ "\n",
+ "Type your own messages. Type `quit` to stop."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {},
+ "source": [
+ "print('Chat with Guppy (type quit to stop)')\n",
+ "print('=' * 40)\n",
+ "while True:\n",
+ " try:\n",
+ " prompt = input('You> ').strip()\n",
+ " except (KeyboardInterrupt, EOFError):\n",
+ " break\n",
+ " if not prompt or prompt.lower() in ('quit', 'exit', 'q'):\n",
+ " print('Guppy> bye. i will continue being a fish.')\n",
+ " break\n",
+ " reply = chat(prompt)\n",
+ " print(f'Guppy> {reply}')\n",
+ " print()"
+ ],
+ "outputs": [],
+ "execution_count": null
+ }
+ ]
+}
\ No newline at end of file