blockblockblock/Smaug-Llama-3-70B-Instruct-bpw3-exl2

Smaug-Llama-3-70B-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.

The model outperforms Llama-3-70B-Instruct substantially, and is on par with GPT-4-Turbo, on MT-Bench (see below).

EDIT: Smaug-Llama-3-70B-Instruct is the top open source model on Arena-Hard currently! It is also nearly on par with Claude Opus - see below.

We are conducting additional benchmark evaluations and will add those when available.

Model Description

• Developed by: Abacus.AI
• License: https://llama.meta.com/llama3/license/
• Finetuned from model: 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, and more information will be released later on. For now, see the previous Smaug paper: https://arxiv.org/abs/2402.13228.