--- library_name: transformers license: llama2 datasets: - aqua_rat - microsoft/orca-math-word-problems-200k - m-a-p/CodeFeedback-Filtered-Instruction --- **Exllamav2** quant (**exl2** / **3.0 bpw**) made with ExLlamaV2 v0.0.21 Other EXL2 quants: | **Quant** | **Model Size** | **lm_head** | | ----- | ---------- | ------- | |
**[2.2](https://huggingface.co/Zoyd/abacusai_Smaug-Llama-3-70B-Instruct-2_2bpw_exl2)**
|
20886 MB
|
6
| |
**[2.5](https://huggingface.co/Zoyd/abacusai_Smaug-Llama-3-70B-Instruct-2_5bpw_exl2)**
|
23192 MB
|
6
| |
**[3.0](https://huggingface.co/Zoyd/abacusai_Smaug-Llama-3-70B-Instruct-3_0bpw_exl2)**
|
27273 MB
|
6
| |
**[3.5](https://huggingface.co/Zoyd/abacusai_Smaug-Llama-3-70B-Instruct-3_5bpw_exl2)**
|
31356 MB
|
6
| |
**[3.75](https://huggingface.co/Zoyd/abacusai_Smaug-Llama-3-70B-Instruct-3_75bpw_exl2)**
|
33398 MB
|
6
| |
**[4.0](https://huggingface.co/Zoyd/abacusai_Smaug-Llama-3-70B-Instruct-4_0bpw_exl2)**
|
35434 MB
|
6
| |
**[4.25](https://huggingface.co/Zoyd/abacusai_Smaug-Llama-3-70B-Instruct-4_25bpw_exl2)**
|
37456 MB
|
6
| |
**[5.0](https://huggingface.co/Zoyd/abacusai_Smaug-Llama-3-70B-Instruct-5_0bpw_exl2)**
|
43598 MB
|
6
| |
**[6.0](https://huggingface.co/Zoyd/abacusai_Smaug-Llama-3-70B-Instruct-6_0bpw_exl2)**
|
51957 MB
|
8
| |
**[6.5](https://huggingface.co/Zoyd/abacusai_Smaug-Llama-3-70B-Instruct-6_5bpw_exl2)**
|
56014 MB
|
8
| |
**[8.0](https://huggingface.co/Zoyd/abacusai_Smaug-Llama-3-70B-Instruct-8_0bpw_exl2)**
|
60211 MB
|
8
| # Smaug-Llama-3-70B-Instruct ### Built with Meta Llama 3 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/ZxYuHKmU_AtuEJbGtuEBC.png) 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). 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](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.