Autotrain compatible Conversational Endpoints compatible Llama Lora Region:us Safetensors Sharded Tensorflow
Semikong 8B V3 Parameters and Internals
| LLM Name | Semikong 8B V3 |
| Repository 🤗 | https://huggingface.co/sitloboi2012/semikong-8b-v3 |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2024-07-04 |
| Maintainer | sitloboi2012 |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|eot_id|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|k_proj|down_proj|o_proj|q_proj|gate_proj|up_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0 |
| R Param | 32 |
Best Alternatives to Semikong 8B V3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Trillama 8B | 8K / 16.1 GB | 35 | 3 |
| Llama3 8B | 8K / 16.1 GB | 7 | 0 |
| Medllama3 V20 | 0K / 16.1 GB | 25667 | 31 |
| Codelica | 0K / 16.1 GB | 111 | 0 |
| TalktoaiQT | 0K / 16.1 GB | 189 | 2 |
| MotherEarth Proverbs 8B | 0K / 16.1 GB | 73 | 1 |
| ...Instruct Persian Finetuned Sft | 0K / 0 GB | 140 | 5 |
| MotherEarth Proverbs 1.0 8B | 0K / 16.1 GB | 20 | 0 |
| Medical Llama3 V2 | 0K / 16.1 GB | 284 | 8 |
| Meta Llama 3.1 8B Instruct OAS | 0K / 16.1 GB | 97 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than sitloboi2012/semikong-8b-v3 .
Rank the Semikong 8B V3 Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 36599 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803