Arxiv:1910.09700 8-bit Autotrain compatible Conversational Custom code Endpoints compatible Gptq Lora Phi3 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/apry/best_8b
Best 8b 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)
Best 8B Parameters and Internals
| LLM Name | Best 8b |
| Repository 🤗 | https://huggingface.co/apry/best_8b |
| Model Size | 8b |
| Required VRAM | 0.1 GB |
| Updated | 2025-06-09 |
| Maintainer | apry |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | gate_up_proj|qkv_proj|down_proj|o_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.1 |
| R Param | 8 |
Best Alternatives to Best 8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.1 8B Instuct Uz | 128K / 16.1 GB | 817 | 14 |
| Trillama 8B | 8K / 16.1 GB | 15 | 3 |
| AutogenJune2000 | 8K / 33.8 GB | 14 | 0 |
| Llama3 8B | 8K / 16.1 GB | 15 | 0 |
| Medllama3 V20 | 0K / 16.1 GB | 25328 | 78 |
| Autotrain Pvqlj Odah2 | 0K / 0.2 GB | 18 | 0 |
| 500tiao 100lun | 0K / 0.2 GB | 12 | 0 |
| Medical Llama3 V2 | 0K / 16.1 GB | 2015 | 12 |
| Codelica | 0K / 16.1 GB | 111 | 0 |
| ModeliCo 8B | 0K / 16.1 GB | 17 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than apry/best_8b .
Rank the Best 8B 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? 48023 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124