shimmyshimmer
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,7 @@ library_name: transformers
|
|
19 |
|
20 |
## ***See [our collection](https://huggingface.co/collections/unsloth/phi-4-all-versions-677eecf93784e61afe762afa) for versions of Phi-4 including GGUF, 4-bit & more formats.***
|
21 |
|
22 |
-
# Finetune Phi-4, Llama 3.3
|
23 |
We have a free Google Colab Tesla T4 notebook for Phi-4 here: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-Alpaca.ipynb
|
24 |
|
25 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth)
|
@@ -30,16 +30,16 @@ We have converted Phi-4 to Llama's architecture for improved ease of use, better
|
|
30 |
|
31 |
## ✨ Finetune for Free
|
32 |
|
33 |
-
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model
|
34 |
|
35 |
| Unsloth supports | Free Notebooks | Performance | Memory use |
|
36 |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
|
|
|
37 |
| **Llama-3.2 (3B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb) | 2.4x faster | 58% less |
|
38 |
| **Llama-3.2 (11B vision)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb) | 2x faster | 60% less |
|
39 |
| **Qwen2 VL (7B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2_VL_(7B)-Vision.ipynb) | 1.8x faster | 60% less |
|
40 |
| **Qwen2.5 (7B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-Alpaca.ipynb) | 2x faster | 60% less |
|
41 |
| **Llama-3.1 (8B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-Alpaca.ipynb) | 2.4x faster | 58% less |
|
42 |
-
| **Phi-3.5 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_3.5_Mini-Conversational.ipynb) | 2x faster | 50% less |
|
43 |
| **Gemma 2 (9B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma2_(9B)-Alpaca.ipynb) | 2.4x faster | 58% less |
|
44 |
| **Mistral (7B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Mistral_v0.3_(7B)-Conversational.ipynb) | 2.2x faster | 62% less |
|
45 |
|
|
|
19 |
|
20 |
## ***See [our collection](https://huggingface.co/collections/unsloth/phi-4-all-versions-677eecf93784e61afe762afa) for versions of Phi-4 including GGUF, 4-bit & more formats.***
|
21 |
|
22 |
+
# Finetune Phi-4, Llama 3.3 2-5x faster with 70% less memory via Unsloth!
|
23 |
We have a free Google Colab Tesla T4 notebook for Phi-4 here: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-Alpaca.ipynb
|
24 |
|
25 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth)
|
|
|
30 |
|
31 |
## ✨ Finetune for Free
|
32 |
|
33 |
+
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model.
|
34 |
|
35 |
| Unsloth supports | Free Notebooks | Performance | Memory use |
|
36 |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
|
37 |
+
| **Phi-4** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_3.5_Mini-Conversational.ipynb) | 2x faster | 50% less |
|
38 |
| **Llama-3.2 (3B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb) | 2.4x faster | 58% less |
|
39 |
| **Llama-3.2 (11B vision)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb) | 2x faster | 60% less |
|
40 |
| **Qwen2 VL (7B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2_VL_(7B)-Vision.ipynb) | 1.8x faster | 60% less |
|
41 |
| **Qwen2.5 (7B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-Alpaca.ipynb) | 2x faster | 60% less |
|
42 |
| **Llama-3.1 (8B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-Alpaca.ipynb) | 2.4x faster | 58% less |
|
|
|
43 |
| **Gemma 2 (9B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma2_(9B)-Alpaca.ipynb) | 2.4x faster | 58% less |
|
44 |
| **Mistral (7B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Mistral_v0.3_(7B)-Conversational.ipynb) | 2.2x faster | 62% less |
|
45 |
|