Fine-tuning notebooks — Distillio

Free Unsloth Colab notebooks for fine-tuning open models. Run them directly in Colab (free GPU tier works for most).

Filter by task: 2048 Game · Alpaca · Audio · Audio Embeddings · Auto Kernel Creation · CPT · Classification · Conversational · DAPO Math · DAPO Math + vLLM · DPO · Decision Model · Embeddings · Eval · Evaluation

162 notebooks

(A100) GLM Flash(80GB) — Conversational — base model: (A100) GLM Flash(80GB) · task: Conversational
(A100) Gemma3 (27B) — Conversational — base model: (A100) Gemma3 (27B) · task: Conversational
(A100) Llama3.3 (70B) — Conversational — base model: (A100) Llama3.3 (70B) · task: Conversational
(A100) Nemotron 3 Nano 30B A3B — Conversational — base model: (A100) Nemotron 3 Nano 30B A3B · task: Conversational
(A100) Nemotron Nano 3 30B A3B — Conversational — base model: (A100) Nemotron Nano 3 30B A3B · task: Conversational
(A100) Qwen 3 5 27B(80GB) — Conversational — base model: (A100) Qwen 3 5 27B(80GB) · task: Conversational
(A100) Qwen3 (32B) — Reasoning Conversational — base model: (A100) Qwen3 (32B) · task: Reasoning Conversational
(A100) gpt oss (120B) — Fine Tuning — base model: (A100) gpt oss (120B) · task: Fine Tuning
(A100) gpt oss (20B) — Auto Kernel Creation — base model: (A100) gpt oss (20B) · task: Auto Kernel Creation
(DGX Spark) gpt oss (20B) — 2048 Game — base model: (DGX Spark) gpt oss (20B) · task: 2048 Game
(OpenEnv) gpt oss (20B) — 2048 Game — base model: (OpenEnv) gpt oss (20B) · task: 2048 Game
(OpenEnv) gpt oss BF16 (20B) — 2048 Game — base model: (OpenEnv) gpt oss BF16 (20B) · task: 2048 Game
All MiniLM L6 v2 — Embeddings — base model: All MiniLM L6 v2 · task: Embeddings
BGE M3 — Embeddings — base model: BGE M3 · task: Embeddings
CodeForces CoT Reasoning — Reasoning — base model: CodeForces CoT Reasoning · task: Reasoning
CodeGemma (7B) — Conversational — base model: CodeGemma (7B) · task: Conversational
DeepSeek R1 0528 Qwen3 (8B) — DAPO Math + vLLM — base model: DeepSeek R1 0528 Qwen3 (8B) · task: DAPO Math + vLLM
Deepseek OCR (3B) — Eval — base model: Deepseek OCR (3B) · task: Eval
Deepseek OCR (3B) — Evaluation — base model: Deepseek OCR (3B) · task: Evaluation
Deepseek OCR (3B) — Fine Tuning — base model: Deepseek OCR (3B) · task: Fine Tuning
Deepseek OCR 2 (3B) — Fine Tuning — base model: Deepseek OCR 2 (3B) · task: Fine Tuning
DiffusionGemma (26B A4B) — Sudoku — base model: DiffusionGemma (26B A4B) · task: Sudoku
ERNIE 4 5 21B A3B PT — Conversational — base model: ERNIE 4 5 21B A3B PT · task: Conversational
ERNIE 4 5 VL 28B A3B PT — Vision — base model: ERNIE 4 5 VL 28B A3B PT · task: Vision
EmbeddingGemma (300M) — Embeddings — base model: EmbeddingGemma (300M) · task: Embeddings
EmbeddingGemma2 (300M) — Audio Embeddings — base model: EmbeddingGemma2 (300M) · task: Audio Embeddings
EmbeddingGemma2 (300M) — Embeddings — base model: EmbeddingGemma2 (300M) · task: Embeddings
EmbeddingGemma2 (300M) — Image Embeddings — base model: EmbeddingGemma2 (300M) · task: Image Embeddings
EmbeddingGemma2 (300M) — Multimodal Search — base model: EmbeddingGemma2 (300M) · task: Multimodal Search
Falcon H1 — Alpaca — base model: Falcon H1 · task: Alpaca
Falcon H1 (0.5B) — Alpaca — base model: Falcon H1 (0.5B) · task: Alpaca
FunctionGemma (270M) — Conversational — base model: FunctionGemma (270M) · task: Conversational
FunctionGemma (270M) — Inference — base model: FunctionGemma (270M) · task: Inference
FunctionGemma (270M) — Mobile Actions — base model: FunctionGemma (270M) · task: Mobile Actions
FunctionGemma (270M) — Tool Calling — base model: FunctionGemma (270M) · task: Tool Calling
Gemma2 (2B) — Alpaca — base model: Gemma2 (2B) · task: Alpaca
Gemma2 (9B) — Alpaca — base model: Gemma2 (9B) · task: Alpaca
Gemma3 (1B) — GSM8K Math — base model: Gemma3 (1B) · task: GSM8K Math
Gemma3 (270M) — Conversational — base model: Gemma3 (270M) · task: Conversational
Gemma3 (270M) — Phone Deployment — base model: Gemma3 (270M) · task: Phone Deployment
Gemma3 (4B) — Conversational — base model: Gemma3 (4B) · task: Conversational
Gemma3 (4B) — Vision — base model: Gemma3 (4B) · task: Vision
Gemma3 (4B) — Vision Math (GRPO RL) — base model: Gemma3 (4B) · task: Vision Math (GRPO RL)
Gemma3N (2B) — Inference — base model: Gemma3N (2B) · task: Inference
Gemma3N (4B) — Audio — base model: Gemma3N (4B) · task: Audio
Gemma3N (4B) — Multimodal — base model: Gemma3N (4B) · task: Multimodal
Gemma3N (4B) — Vision — base model: Gemma3N (4B) · task: Vision
Gemma4 (26B A4B) — Conversational — base model: Gemma4 (26B A4B) · task: Conversational
Gemma4 (26B A4B) — Vision — base model: Gemma4 (26B A4B) · task: Vision
Gemma4 (31B) — Conversational — base model: Gemma4 (31B) · task: Conversational
Gemma4 (31B) — Vision — base model: Gemma4 (31B) · task: Vision
Gemma4 (E2B) — 2048 Game — base model: Gemma4 (E2B) · task: 2048 Game
Gemma4 (E2B) — Audio — base model: Gemma4 (E2B) · task: Audio
Gemma4 (E2B) — Auto Kernel Creation — base model: Gemma4 (E2B) · task: Auto Kernel Creation
Gemma4 (E2B) — Conversational — base model: Gemma4 (E2B) · task: Conversational
Gemma4 (E2B) — Sudoku — base model: Gemma4 (E2B) · task: Sudoku
Gemma4 (E2B) — Vision — base model: Gemma4 (E2B) · task: Vision
Gemma4 (E4B) — Audio — base model: Gemma4 (E4B) · task: Audio
Gemma4 (E4B) — Conversational — base model: Gemma4 (E4B) · task: Conversational
Gemma4 (E4B) — Vision — base model: Gemma4 (E4B) · task: Vision