110 lines
4.8 KiB
Markdown
110 lines
4.8 KiB
Markdown
---
|
|
license: apache-2.0
|
|
datasets:
|
|
- cerebras/SlimPajama-627B
|
|
- bigcode/starcoderdata
|
|
- HuggingFaceH4/ultrachat_200k
|
|
- HuggingFaceH4/ultrafeedback_binarized
|
|
language:
|
|
- en
|
|
widget:
|
|
- text: "<|system|>\nYou are a chatbot who can help code!</s>\n<|user|>\nWrite me a function to calculate the first 10 digits of the fibonacci sequence in Python and print it out to the CLI.</s>\n<|assistant|>\n"
|
|
---
|
|
<div align="center">
|
|
|
|
# TinyLlama-1.1B ---My personal Test update
|
|
</div>
|
|
|
|
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
|
|-------------|-------|------|-----:|--------|-----:|---|-----:|
|
|
|arc_challenge|Yaml |none | 0|acc |0.2619|± |0.0128|
|
|
| | |none | 0|acc_norm|0.2892|± |0.0133|
|
|
|arc_easy |Yaml |none | 0|acc |0.4777|± |0.0102|
|
|
| | |none | 0|acc_norm|0.4461|± |0.0102|
|
|
|boolq |Yaml |none | 0|acc |0.6297|± |0.0084|
|
|
|hellaswag |Yaml |none | 0|acc |0.3934|± |0.0049|
|
|
| | |none | 0|acc_norm|0.4930|± |0.0050|
|
|
|openbookqa |Yaml |none | 0|acc |0.2120|± |0.0183|
|
|
| | |none | 0|acc_norm|0.3260|± |0.0210|
|
|
|piqa |Yaml |none | 0|acc |0.6915|± |0.0108|
|
|
| | |none | 0|acc_norm|0.6877|± |0.0108|
|
|
|winogrande |Yaml |none | 0|acc |0.5714|± |0.0139|
|
|
|
|
|
|
Llamafactory EVAL
|
|
|
|
|
|
!CUDA_VISIBLE_DEVICES=0 python src/evaluate.py \
|
|
--model_name_or_path Deathsquad10/TinyLlama-Remix \
|
|
--template vanilla \
|
|
--task mmlu \
|
|
--split test \
|
|
--lang en \
|
|
--n_shot 5 \
|
|
--use_unsloth \
|
|
--batch_size 1
|
|
|
|
|
|
Average: 26.29
|
|
STEM: 27.10
|
|
Social Sciences: 25.48
|
|
Humanities: 25.62
|
|
Other: 27.26
|
|
|
|
!CUDA_VISIBLE_DEVICES=0 python src/evaluate.py \
|
|
--model_name_or_path Deathsquad10/TinyLlama-Remix \
|
|
--template vanilla \
|
|
--task cmmlu \
|
|
--split test \
|
|
--lang en \
|
|
--n_shot 5 \
|
|
--use_unsloth \
|
|
--batch_size 2
|
|
|
|
|
|
Average: 24.98
|
|
STEM: 25.52
|
|
Social Sciences: 24.70
|
|
Humanities: 24.59
|
|
Other: 25.19
|
|
https://github.com/jzhang38/TinyLlama
|
|
|
|
The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.
|
|
|
|
|
|
We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
|
|
|
|
#### This Model
|
|
This is the chat model finetuned on top of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T). **We follow [HF's Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/edit/main/README.md)'s training recipe.** The model was " initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.
|
|
We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4."
|
|
|
|
|
|
#### How to use
|
|
You will need the transformers>=4.34
|
|
Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
|
|
|
|
```python
|
|
# Install transformers from source - only needed for versions <= v4.34
|
|
# pip install git+https://github.com/huggingface/transformers.git
|
|
# pip install accelerate
|
|
import torch
|
|
from transformers import pipeline
|
|
pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.bfloat16, device_map="auto")
|
|
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
|
|
messages = [
|
|
{
|
|
"role": "system",
|
|
"content": "You are a friendly chatbot who always responds in the style of a pirate",
|
|
},
|
|
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
|
|
]
|
|
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
|
print(outputs[0]["generated_text"])
|
|
# <|system|>
|
|
# You are a friendly chatbot who always responds in the style of a pirate.</s>
|
|
# <|user|>
|
|
# How many helicopters can a human eat in one sitting?</s>
|
|
# <|assistant|>
|
|
# ...
|
|
``` |