|
--- |
|
library_name: transformers |
|
license: llama2 |
|
datasets: |
|
- aqua_rat |
|
- microsoft/orca-math-word-problems-200k |
|
- m-a-p/CodeFeedback-Filtered-Instruction |
|
--- |
|
|
|
# Llama-3-Smaug-70B-Instruct |
|
|
|
### Built with Meta Llama 3 |
|
|
|
|
|
 |
|
|
|
This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to |
|
[meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct). |
|
|
|
The model outperforms Llama-3-70B-Instruct substantially, and is on par with GPT-4-Turbo, on MT-Bench (see below). We are conducting additional benchmark evaluations and will add those when available. |
|
|
|
### Model Description |
|
|
|
- **Developed by:** [Abacus.AI](https://abacus.ai) |
|
- **License:** https://llama.meta.com/llama3/license/ |
|
- **Finetuned from model:** [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct). |
|
|
|
|
|
## Evaluation |
|
|
|
### Arena-Hard |
|
|
|
Score vs selected others (sourced from: (https://lmsys.org/blog/2024-04-19-arena-hard/#full-leaderboard-with-gpt-4-turbo-as-judge)) |
|
|
|
| Model | Score | 95% Confidence Interval | Average Tokens | |
|
| :---- | ---------: | ----------: | ------: | |
|
| GPT-4-Turbo-2024-04-09 | 82.6 | (-1.8, 1.6) | 662 | |
|
| Claude-3-Opus-20240229 | 60.4 | (-3.3, 2.4) | 541 | |
|
| **Smaug-Llama-3-70B-Instruct** | 56.7 | (-2.2, 2.6) | 661 | |
|
| GPT-4-0314 | 50.0 | (-0.0, 0.0) | 423 | |
|
| Claude-3-Sonnet-20240229 | 46.8 | (-2.1, 2.2) | 552 | |
|
| Llama-3-70B-Instruct | 41.1 | (-2.5, 2.4) | 583 | |
|
| GPT-4-0613 | 37.9 | (-2.2, 2.0) | 354 | |
|
| Mistral-Large-2402 | 37.7 | (-1.9, 2.6) | 400 | |
|
| Mixtral-8x22B-Instruct-v0.1 | 36.4 | (-2.7, 2.9) | 430 | |
|
| Qwen1.5-72B-Chat | 36.1 | (-2.5, 2.2) | 474 | |
|
| Command-R-Plus | 33.1 | (-2.1, 2.2) | 541 | |
|
| Mistral-Medium | 31.9 | (-2.3, 2.4) | 485 | |
|
| GPT-3.5-Turbo-0613 | 24.8 | (-1.6, 2.0) | 401 | |
|
|
|
### MT-Bench |
|
|
|
``` |
|
########## First turn ########## |
|
score |
|
model turn |
|
Smaug-Llama-3-70B-Instruct 1 9.40000 |
|
GPT-4-Turbo 1 9.37500 |
|
Meta-Llama-3-70B-Instruct 1 9.21250 |
|
########## Second turn ########## |
|
score |
|
model turn |
|
Smaug-Llama-3-70B-Instruct 2 9.0125 |
|
GPT-4-Turbo 2 9.0000 |
|
Meta-Llama-3-70B-Instruct 2 8.8000 |
|
########## Average ########## |
|
score |
|
model |
|
Smaug-Llama-3-70B-Instruct 9.206250 |
|
GPT-4-Turbo 9.187500 |
|
Meta-Llama-3-70B-Instruct 9.006250 |
|
``` |
|
|
|
| Model | First turn | Second Turn | Average | |
|
| :---- | ---------: | ----------: | ------: | |
|
| **Smaug-Llama-3-70B-Instruct** | 9.40 | 9.01 | 9.21 | |
|
| GPT-4-Turbo | 9.38 | 9.00 | 9.19 | |
|
| Meta-Llama-3-70B-Instruct | 9.21 | 8.80 | 9.01 | |
|
|
|
This version of Smaug uses new techniques and new data compared to [Smaug-72B](https://huggingface.co/abacusai/Smaug-72B-v0.1), and more information will be released later on. For now, see the previous Smaug paper: https://arxiv.org/abs/2402.13228. |
