Maverick Llama 3 8b 🏴‍☠️

1714015975262634.png

model is using ChatML prompt template format.

example:

<|im_start|>system
You are Maverick, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

🏆 Evaluation

eq-bench

Tasks Version Filter n-shot Metric Value Stderr
eq_bench 2.1 none 0 eqbench 56.8710 ± 2.8946
none 0 percent_parseable 99.4152 ± 0.5848

winogrande

Tasks Version Filter n-shot Metric Value Stderr
winogrande 1 none 0 acc 0.7372 ± 0.0124

gsm8k

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 strict-match 5 exact_match 0.5694 ± 0.0136
flexible-extract 5 exact_match 0.5701 ± 0.0136

mathqa

Tasks Version Filter n-shot Metric Value Stderr
mathqa 1 none 0 acc 0.3930 ± 0.0089
none 0 acc_norm 0.3869 ± 0.0089

This model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT

Downloads last month
35
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for feeltheAGI/maverick-llama3-8B

Quantizations
3 models

Dataset used to train feeltheAGI/maverick-llama3-8B