Ahma 7B Merge 10 by aapot

 ยป  All LLMs  ยป  aapot  ยป  Ahma 7B Merge 10   URL Share it on

  Merged Model   Arxiv:2203.05482   Autotrain compatible Base model:finetune:finnish-nl...   Base model:finnish-nlp/ahma-7b   Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/aapot/Ahma-7B-merge-10 

Ahma 7B Merge 10 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ahma 7B Merge 10 (aapot/Ahma-7B-merge-10)

Ahma 7B Merge 10 Parameters and Internals

LLM NameAhma 7B Merge 10
Repository ๐Ÿค—https://huggingface.co/aapot/Ahma-7B-merge-10 
Base Model(s)  Ahma 7B   Ahma 7B   Finnish-NLP/Ahma-7B   Finnish-NLP/Ahma-7B
Merged ModelYes
Model Size7b
Required VRAM14 GB
Updated2024-09-18
Maintaineraapot
Model Typellama
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   4.0 GB: 3-of-3
Model ArchitectureLlamaForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.44.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size64256
Torch Data Typefloat16

Best Alternatives to Ahma 7B Merge 10

Best Alternatives
Context / RAM
Downloads
Likes
...1M 1000000ctx AEZAKMI 3 1 17021024K / 13.5 GB661
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB31941
LlamaStock 8B128K / 16.1 GB211
SuperNeuralDreadDevil 8B128K / 16.1 GB151
Yarn Llama 2 7B 128K128K / 13.5 GB349339
LLaMA 7B PoSE YaRN 128K128K / 13.5 GB103
LLaMA 7B PoSE Linear 96K96K / 27 GB112
LLaMA 7B PoSE YaRN 96K96K / 13.5 GB131
Chat Llama2 7B 80K80K / 13.8 GB100
Llama2 7B 80K80K / 13.8 GB120
Note: green Score (e.g. "73.2") means that the model is better than aapot/Ahma-7B-merge-10.

Rank the Ahma 7B Merge 10 Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 41473 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227