Phi-3 (#397)
* Fix prompt * Update chat_templates.py * fix_untrained_tokens * Update llama.py * add tokens * Update _utils.py * Update tokenizer_utils.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * pad_token * Update chat_templates.py * Update chat_templates.py * tokenizer * Update save.py * Update chat_templates.py * Update chat_templates.py * patch tokenizer padding * Update tokenizer_utils.py * Update save.py * Fix: loading models with resized vocabulary (#377) * new: vocab resize on load * new: gitignore * GGUF fix * Readme (#390) * Update README.md * Update README.md --------- Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> * Update README.md * Delete .gitignore * Phi-3 * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md --------- Co-authored-by: Igor Kilbas <whitemarsstudios@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com>
This commit is contained in:
Daniel Han
GitHub
parent
ed10172160
commit
6e4ebe4040
2 changed files with 19 additions and 12 deletions
27
README.md
27
README.md
|
|
@ -20,23 +20,25 @@
|
|||
|
||||
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
|
||||
|
||||
| Unsloth supports | Free Notebooks | Performance | Memory use |
|
||||
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
|
||||
| **Llama 3 (8B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing) | 2x faster | 60% less |
|
||||
| **Mistral (7B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 73% less |
|
||||
| **Gemma (7B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing) | 2.4x faster | 71% less |
|
||||
| **Llama 3 (8B)** 1xT4 | [▶️ Start on Kaggle](https://www.kaggle.com/code/danielhanchen/kaggle-llama-3-8b-unsloth-notebook) | 5x faster\* | 73% less |
|
||||
| **ORPO** | [▶️ Start on Colab](https://colab.research.google.com/drive/11t4njE3c4Lxl-07OD8lJSMKkfyJml3Tn?usp=sharing) | 1.9x faster | 43% less |
|
||||
| **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 43% less |
|
||||
| Unsloth supports | Free Notebooks | Performance | Memory use |
|
||||
|-----------|---------|--------|----------|
|
||||
| **Llama 3 (8B)** | [▶️ Start for free](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing) | 2x faster | 60% less |
|
||||
| **Mistral (7B)** | [▶️ Start for free](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 73% less |
|
||||
| **Gemma (7B)** | [▶️ Start for free](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing) | 2.4x faster | 71% less |
|
||||
| **ORPO** | [▶️ Start for free](https://colab.research.google.com/drive/11t4njE3c4Lxl-07OD8lJSMKkfyJml3Tn?usp=sharing) | 1.9x faster | 43% less |
|
||||
| **DPO Zephyr** | [▶️ Start for free](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 43% less |
|
||||
| **Phi-3 (3.8B)** | [▶️ Start for free](https://colab.research.google.com/drive/1NvkBmkHfucGO3Ve9s1NKZvMNlw5p83ym?usp=sharing) | 2x faster | 50% less |
|
||||
| **TinyLlama** | [▶️ Start for free](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less |
|
||||
|
||||
- Benchmarking compared to FA2 + Hugging Face combined.
|
||||
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
|
||||
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
|
||||
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
|
||||
- **Kaggle Notebooks** for [Llama-3 8b](https://www.kaggle.com/code/danielhanchen/kaggle-llama-3-8b-unsloth-notebook), [Gemma 7b](https://www.kaggle.com/code/danielhanchen/kaggle-gemma-7b-unsloth-notebook/), [Mistral 7b](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook)
|
||||
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for Llama-3. And ChatML for [Mistral 7b](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing).
|
||||
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for continued pretraining / raw text.
|
||||
|
||||
## 🦥 Unsloth.ai News
|
||||
- 📣 NEW! [Llama-3 8b](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing) now works! Llama-3 70b also works (change the model name in the notebook).
|
||||
- 📣 NEW! [ORPO support](https://colab.research.google.com/drive/11t4njE3c4Lxl-07OD8lJSMKkfyJml3Tn?usp=sharing) is here!
|
||||
- 📣 NEW! [Phi-3 3.8b support](https://colab.research.google.com/drive/1NvkBmkHfucGO3Ve9s1NKZvMNlw5p83ym?usp=sharing) is here!
|
||||
- 📣 NEW! We cut memory usage by a [further 30%](https://unsloth.ai/blog/long-context) and now support fine-tuning of LLMs with [4x longer context windows](https://unsloth.ai/blog/long-context)! No change required if you're using our notebooks. To enable, simply change 1 line:
|
||||
```python
|
||||
model = FastLanguageModel.get_peft_model(
|
||||
|
|
@ -45,7 +47,7 @@ model = FastLanguageModel.get_peft_model(
|
|||
)
|
||||
```
|
||||
- 📣 [CodeGemma](https://colab.research.google.com/drive/19lwcRk_ZQ_ZtX-qzFP3qZBBHZNcMD1hh?usp=sharing) now works along with [Gemma 7b](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing) and [Gemma 2b](https://colab.research.google.com/drive/15gGm7x_jTm017_Ic8e317tdIpDG53Mtu?usp=sharing)
|
||||
- 📣 [2x faster inference](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) added for all our models
|
||||
- 📣 [2x faster inference](https://colab.research.google.com/drive/1aqlNQi7MMJbynFDyOQteD2t0yVfjb9Zh?usp=sharing) added for all our models
|
||||
|
||||
## 🔗 Links and Resources
|
||||
| Type | Links |
|
||||
|
|
@ -190,6 +192,7 @@ fourbit_models = [
|
|||
"unsloth/gemma-2b-bnb-4bit",
|
||||
"unsloth/gemma-2b-it-bnb-4bit", # Instruct version of Gemma 2b
|
||||
"unsloth/llama-3-8b-bnb-4bit", # [NEW] 15 Trillion token Llama-3
|
||||
"unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
|
||||
] # More models at https://huggingface.co/unsloth
|
||||
|
||||
model, tokenizer = FastLanguageModel.from_pretrained(
|
||||
|
|
|
|||
|
|
@ -140,6 +140,10 @@ __INT_TO_FLOAT_MAPPER = \
|
|||
"unsloth/llama-3-70b-Instruct-bnb-4bit" : (
|
||||
"meta-llama/Meta-Llama-3-70B-Instruct",
|
||||
),
|
||||
"unsloth/Phi-3-mini-4k-instruct-bnb-4bit" : (
|
||||
"unsloth/Phi-3-mini-4k-instruct",
|
||||
"microsoft/Phi-3-mini-4k-instruct",
|
||||
),
|
||||
}
|
||||
|
||||
INT_TO_FLOAT_MAPPER = {}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue