LLM EXPLORER 60,645 MODELS INDEXED

Testing Semifinal by lilmeaty

By lilmeaty · 8 downloads
HF Repo ↗ Copy URL

Testing Semifinal is an open-source language model by lilmeaty. Features: 3.6b LLM, VRAM: 7.3GB, Context: 128K, Merged, LLM Explorer Score: 0.15.

  Merged Model   Arxiv:1910.09700   Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/lilmeaty/testing_semifinal 

Testing Semifinal Parameters and Internals

LLM NameTesting Semifinal
Repository 🤗https://huggingface.co/lilmeaty/testing_semifinal 
Base Model(s)  Mergekit Ties Qgcitfu   ValiantLabs/Llama3.2-3B-ShiningValiant2   CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct   Atharva26/llama-3.2-3b-mathdaily-chatbot   bunnycore/Llama-3.2-3B-ProdigyPlusPlus   disi-unibo-nlp/llama3.2-3B-SFT-medqa-triples-cot   Mergekit Ties Poovzrh   bunnycore/Llama-3.2-3B-Long-Think   noaebbot/llama3.2-3B-insights   ValiantLabs/Llama3.2-3B-Enigma   huihui-ai/Llama-3.2-3B-Instruct-abliterated   meta-llama/Llama-3.2-3B-Instruct   Mergekit Ties Pghuyfi   Diluksha/Llama_3.2_3B_sql_finetuned_full   bunnycore/Llama-3.2-3B-Mix   Mergekit Ties Xflmond   bunnycore/Llama-3.2-3B-Pure-RP   chuanli11/Llama-3.2-3B-Instruct-uncensored   EmTpro01/llama-3.2-Code-Generator   bunnycore/Llama-3.2-3B-Booval   bunnycore/Llama-3.2-3B-Prodigy   BrainWave-ML/llama3.2-3B-codemath-orpo   bunnycore/Llama-3.2-3B-TitanFusion   bunnycore/Llama-3.2-3B-CodeReactor   Mergekit Ties Kmlzhzo   Mergekit Ties Esawwda   bunnycore/Llama-3.2-3B-TitanFusion-v2   disi-unibo-nlp/llama3.2-3B-SFT-medmcqa-triples-cot   bunnycore/Llama-3.2-3B-Mix-Skill   bunnycore/Llama-3.2-3B-Sci-Think   AELLM/Llama-3.2-Chibi-3B   AcademieDuNumerique/Llama-3.2-3B-SQL-Instruct   roger33303/Best_Model-llama3.2-3b-Instruct-Finetune-website-QnA   Mergekit Ties Dkhnzcn   Isotonic/reasoning-llama3.2-3b   meta-llama/Llama-3.2-3B   bunnycore/Llama-3.2-3B-Apex   TroyDoesAI/BlackSheep-Llama3.2-3B-Context_Obedient   CK0607/llama3.2-3B-CodeP   bunnycore/Llama-3.2-3B-Stock   Hjgugugjhuhjggg/mergekit-ties-qgcitfu   ValiantLabs/Llama3.2-3B-ShiningValiant2   CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct   Atharva26/llama-3.2-3b-mathdaily-chatbot   bunnycore/Llama-3.2-3B-ProdigyPlusPlus   disi-unibo-nlp/llama3.2-3B-SFT-medqa-triples-cot   Hjgugugjhuhjggg/mergekit-ties-poovzrh   bunnycore/Llama-3.2-3B-Long-Think   noaebbot/llama3.2-3B-insights   ValiantLabs/Llama3.2-3B-Enigma   huihui-ai/Llama-3.2-3B-Instruct-abliterated   meta-llama/Llama-3.2-3B-Instruct   Hjgugugjhuhjggg/mergekit-ties-pghuyfi   Diluksha/Llama_3.2_3B_sql_finetuned_full   bunnycore/Llama-3.2-3B-Mix   Hjgugugjhuhjggg/mergekit-ties-xflmond   bunnycore/Llama-3.2-3B-Pure-RP   chuanli11/Llama-3.2-3B-Instruct-uncensored   EmTpro01/llama-3.2-Code-Generator   bunnycore/Llama-3.2-3B-Booval   bunnycore/Llama-3.2-3B-Prodigy   BrainWave-ML/llama3.2-3B-codemath-orpo   bunnycore/Llama-3.2-3B-TitanFusion   bunnycore/Llama-3.2-3B-CodeReactor   Hjgugugjhuhjggg/mergekit-ties-kmlzhzo   Hjgugugjhuhjggg/mergekit-ties-esawwda   bunnycore/Llama-3.2-3B-TitanFusion-v2   disi-unibo-nlp/llama3.2-3B-SFT-medmcqa-triples-cot   bunnycore/Llama-3.2-3B-Mix-Skill   bunnycore/Llama-3.2-3B-Sci-Think   AELLM/Llama-3.2-Chibi-3B   AcademieDuNumerique/Llama-3.2-3B-SQL-Instruct   roger33303/Best_Model-llama3.2-3b-Instruct-Finetune-website-QnA   Hjgugugjhuhjggg/mergekit-ties-dkhnzcn   Isotonic/reasoning-llama3.2-3b   meta-llama/Llama-3.2-3B   bunnycore/Llama-3.2-3B-Apex   TroyDoesAI/BlackSheep-Llama3.2-3B-Context_Obedient   CK0607/llama3.2-3B-CodeP   bunnycore/Llama-3.2-3B-Stock
Merged ModelYes
Model Size3.6b
Required VRAM7.3 GB
Updated2026-07-15
Maintainerlilmeaty
Model Typellama
Model Files  0.8 GB: 1-of-8   1.0 GB: 2-of-8   1.0 GB: 3-of-8   1.0 GB: 4-of-8   0.9 GB: 5-of-8   1.0 GB: 6-of-8   1.0 GB: 7-of-8   0.6 GB: 8-of-8
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.45.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Testing Semifinal

Best Alternatives
Context / RAM
Downloads
Likes
Coder0.1.3128K / 7.2 GB60
Keyframer2128K / 7.2 GB80
ColdBrew Aphid128K / 7.2 GB11
...kpoint 1314 DPO Checkpoint 7472K / 7.3 GB120
...ckpoint 564 DPO Checkpoint 2492K / 7.3 GB270
Numfalm Chat Full2K / 7.3 GB50
... ChatMusician Bnb 4bit Smashed2K / 4.2 GB170
Note: green Score (e.g. "73.2") means that the model is better than lilmeaty/testing_semifinal.