Arxiv:1910.09700 Autotrain compatible Conversational Dataset:trelis/orpo-dpo-mix-40... En Endpoints compatible Gguf Instruct Llama Lora Q4 Quantized Region:us Safetensors Sharded Tensorflow
Llama 3 8B ORPO 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)
Llama 3 8B ORPO Parameters and Internals
| LLM Name | Llama 3 8B ORPO |
| Repository 🤗 | https://huggingface.co/kingabzpro/Llama-3-8B-ORPO |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2024-11-21 |
| Maintainer | kingabzpro |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | q4|gguf|q4_k |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|im_end|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|gate_proj|o_proj|q_proj|up_proj|down_proj|v_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Llama 3 8B ORPO
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| TalktoaiZERO | 0K / 16.1 GB | 285 | 3 |
| ...3 Project Management Assistant | 0K / 0.2 GB | 20 | 1 |
| ...ama 3 8B Instruct Bnb Telcom 3 | 0K / 0.2 GB | 12 | 0 |
| Llama30 | 0K / 16.1 GB | 12 | 0 |
| Llama26 | 0K / 16.1 GB | 9 | 0 |
| ...nstruct Bnb 4bit DadJokes 100K | 0K / 16.1 GB | 9 | 0 |
| Llama3 8B CPP | 0K / 0.2 GB | 69 | 0 |
| Codelica | 0K / 16.1 GB | 111 | 0 |
| ...Instruct Persian Finetuned Sft | 0K / 0 GB | 197 | 5 |
| ModeliCo 8B | 0K / 16.1 GB | 18 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than kingabzpro/Llama-3-8B-ORPO .
Rank the Llama 3 8B ORPO 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? 38149 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110