Arxiv:1910.09700 8-bit Autotrain compatible Bitsandbytes Conversational Endpoints compatible Llama Lora Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/kishorea/Llama3_medqa
Llama3 Medqa Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Llama3 Medqa Parameters and Internals
| LLM Name | Llama3 Medqa |
| Repository 🤗 | https://huggingface.co/kishorea/Llama3_medqa |
| Model Size | 8b |
| Required VRAM | 9.1 GB |
| Updated | 2024-12-21 |
| Maintainer | kishorea |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|begin_of_text|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|v_proj|q_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.1 |
| R Param | 32 |
Best Alternatives to Llama3 Medqa
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Trillama 8B | 8K / 16.1 GB | 33 | 3 |
| Llama3 8B | 8K / 16.1 GB | 7 | 0 |
| Medllama3 V20 | 0K / 16.1 GB | 14824 | 49 |
| 500tiao 100lun | 0K / 0.2 GB | 23 | 0 |
| Autotrain Pvqlj Odah2 | 0K / 0.2 GB | 18 | 0 |
| Codelica | 0K / 16.1 GB | 111 | 0 |
| ModeliCo 8B | 0K / 16.1 GB | 20 | 2 |
| Medical Llama3 V2 | 0K / 16.1 GB | 604 | 11 |
| Llama31 Eros | 0K / 16.1 GB | 22 | 1 |
| MotherEarth Proverbs 8B | 0K / 16.1 GB | 23 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than kishorea/Llama3_medqa .
Rank the Llama3 Medqa 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? 40013 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217