Unsloth Mistral Small (22B) Alpaca

Mistral Small (22B) Alpaca

unsloth-notebooksunslothoriginal_template

alph-notebooks/unsloth-notebooks / Mistral_Small_(22B)-Alpaca.ipynb

Export

Run Notebooks

Contents

No cells yet

Add cells to see them here

News

Placeholder

Installation

[ ]

Unsloth

[ ]

🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.
==((====))==  Unsloth 2024.9: Fast Mistral patching. Transformers = 4.44.2.
   \\   /|    GPU: Tesla T4. Max memory: 14.748 GB. Platform = Linux.
O^O/ \_/ \    Pytorch: 2.4.0+cu121. CUDA = 7.5. CUDA Toolkit = 12.1.
\        /    Bfloat16 = FALSE. FA [Xformers = 0.0.27.post2. FA2 = False]
 "-____-"     Free Apache license: http://github.com/unslothai/unsloth
Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!

model.safetensors.index.json:   0%|          | 0.00/232k [00:00<?, ?B/s]

Downloading shards:   0%|          | 0/3 [00:00<?, ?it/s]

model-00001-of-00003.safetensors:   0%|          | 0.00/4.98G [00:00<?, ?B/s]

model-00002-of-00003.safetensors:   0%|          | 0.00/4.98G [00:00<?, ?B/s]

model-00003-of-00003.safetensors:   0%|          | 0.00/2.12G [00:00<?, ?B/s]

Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]

generation_config.json:   0%|          | 0.00/111 [00:00<?, ?B/s]

tokenizer_config.json:   0%|          | 0.00/141k [00:00<?, ?B/s]

tokenizer.model:   0%|          | 0.00/588k [00:00<?, ?B/s]

special_tokens_map.json:   0%|          | 0.00/560 [00:00<?, ?B/s]

tokenizer.json:   0%|          | 0.00/1.96M [00:00<?, ?B/s]

We now add LoRA adapters so we only need to update 1 to 10% of all parameters!

[ ]

Unsloth 2024.9 patched 56 layers with 56 QKV layers, 56 O layers and 56 MLP layers.

Data Prep

We now use the Alpaca dataset from yahma, which is a filtered version of 52K of the original Alpaca dataset. You can replace this code section with your own data prep.

[NOTE] To train only on completions (ignoring the user's input) read TRL's docs here.

[NOTE] Remember to add the EOS_TOKEN to the tokenized output!! Otherwise you'll get infinite generations!

If you want to use the mistral3 template for ShareGPT datasets, try our conversational notebook.

For text completions like novel writing, try this notebook.

[ ]

README.md:   0%|          | 0.00/11.6k [00:00<?, ?B/s]

alpaca_data_cleaned.json:   0%|          | 0.00/44.3M [00:00<?, ?B/s]

Generating train split:   0%|          | 0/51760 [00:00<?, ? examples/s]

Map:   0%|          | 0/51760 [00:00<?, ? examples/s]

Train the model

Now let's train our model. We do 60 steps to speed things up, but you can set num_train_epochs=1 for a full run, and turn off max_steps=None. We also support TRL's DPOTrainer!

[ ]

Map (num_proc=2):   0%|          | 0/51760 [00:00<?, ? examples/s]

max_steps is given, it will override any value given in num_train_epochs

[ ]

GPU = Tesla T4. Max memory = 14.748 GB.
12.486 GB of memory reserved.

[ ]

==((====))==  Unsloth - 2x faster free finetuning | Num GPUs = 1
   \\   /|    Num examples = 51,760 | Num Epochs = 1
O^O/ \_/ \    Batch size per device = 1 | Gradient Accumulation steps = 4
\        /    Total batch size = 4 | Total steps = 60
 "-____-"     Number of trainable parameters = 95,420,416

[ ]

859.5694 seconds used for training.
14.33 minutes used for training.
Peak reserved memory = 14.271 GB.
Peak reserved memory for training = 1.785 GB.
Peak reserved memory % of max memory = 96.766 %.
Peak reserved memory for training % of max memory = 12.103 %.

Inference

Let's run the model! You can change the instruction and input - leave the output blank!

[ ]

['<s>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\nContinue the fibonnaci sequence.\n\n### Input:\n1, 1, 2, 3, 5, 8\n\n### Response:\n1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89, 144, 233, 377, 610, 987, 1']

You can also use a TextStreamer for continuous inference - so you can see the generation token by token, instead of waiting the whole time!

[ ]

<s>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
Continue the fibonnaci sequence.

### Input:
1, 1, 2, 3, 5, 8

### Response:
1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89, 144, 233, 377, 610, 987, 1597, 2584, 4181, 6765, 10946, 17711, 28657, 46368, 75025, 121393

Saving, loading finetuned models

To save the final model as LoRA adapters, either use Huggingface's push_to_hub for an online save or save_pretrained for a local save.

[NOTE] This ONLY saves the LoRA adapters, and not the full model. To save to 16bit or GGUF, scroll down!

[ ]

('lora_model/tokenizer_config.json',
, 'lora_model/special_tokens_map.json',
, 'lora_model/tokenizer.model',
, 'lora_model/added_tokens.json',
, 'lora_model/tokenizer.json')

Now if you want to load the LoRA adapters we just saved for inference, set False to True:

[ ]

<s>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
What is a famous tall tower in Paris?

### Input:


### Response:
The Eiffel Tower is a famous tall tower in Paris.</s>

You can also use Hugging Face's AutoModelForPeftCausalLM. Only use this if you do not have unsloth installed. It can be hopelessly slow, since 4bit model downloading is not supported, and Unsloth's inference is 2x faster.

[ ]

Saving to float16 for VLLM

We also support saving to float16 directly. Select merged_16bit for float16 or merged_4bit for int4. We also allow lora adapters as a fallback. Use push_to_hub_merged to upload to your Hugging Face account! You can go to https://huggingface.co/settings/tokens for your personal tokens.

[ ]

GGUF / llama.cpp Conversion

To save to GGUF / llama.cpp, we support it natively now! We clone llama.cpp and we default save it to q8_0. We allow all methods like q4_k_m. Use save_pretrained_gguf for local saving and push_to_hub_gguf for uploading to HF.

Some supported quant methods (full list on our Wiki page):

q8_0 - Fast conversion. High resource use, but generally acceptable.
q4_k_m - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K.
q5_k_m - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K.

[NEW] To finetune and auto export to Ollama, try our Ollama notebook

[ ]