flyingllama-v2/README.md

language, license, model-index

language	license	model-index
en	apache-2.0	name results flyingllama-v2 task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 24.74 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/flyingllama-v2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 38.44 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/flyingllama-v2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 26.37 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/flyingllama-v2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 41.3 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/flyingllama-v2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 50.28 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/flyingllama-v2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 0.0 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/flyingllama-v2 Open LLM Leaderboard

Model Description

kevin009/flyingllama-v2 is a language model leveraging the Llama architecture. It is tailored for text generation and various natural language processing tasks. The model features a hidden size of 1024, incorporates 24 hidden layers, and is equipped with 16 attention heads. It utilizes a vocabulary comprising 50304 tokens and is fine-tuned using the SiLU activation function. Model Usage

This model is well-suited for tasks such as text generation, language modeling, and other natural language processing applications that require understanding and generating human-like language. Limitations

Like any model, kevin009/flyingllama may have limitations related to its architecture and training data. Users should assess its performance for specific use cases.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	30.19
AI2 Reasoning Challenge (25-Shot)	24.74
HellaSwag (10-Shot)	38.44
MMLU (5-Shot)	26.37
TruthfulQA (0-shot)	41.30
Winogrande (5-shot)	50.28
GSM8k (5-shot)	0.00