Arxiv:1910.09700 Autotrain compatible Conversational Endpoints compatible Instruct Llama Orpo Region:us Safetensors Sharded Tensorflow Trl
Model Card on HF 🤗: https://huggingface.co/coorung/EEVE_10b_ORPO_trained_v2
EEVE 10b ORPO Trained V2 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)
EEVE 10B ORPO Trained V2 Parameters and Internals
| LLM Name | EEVE 10b ORPO Trained V2 |
| Repository 🤗 | https://huggingface.co/coorung/EEVE_10b_ORPO_trained_v2 |
| Model Size | 10b |
| Required VRAM | 21.6 GB |
| Updated | 2024-12-22 |
| Maintainer | coorung |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 40960 |
| Torch Data Type | bfloat16 |
Best Alternatives to EEVE 10B ORPO Trained V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Falcon3 10B Instruct | 32K / 20.5 GB | 2905 | 55 |
| ...ma 3 10B It Kor Extented Chang | 8K / 19.6 GB | 4811 | 13 |
| EEVE 10b ORPO Trained | 4K / 21.6 GB | 9 | 0 |
| SOLAR 10B OrcaDPO Jawade | 4K / 21.4 GB | 826 | 4 |
| Falcon3 10B Instruct 1.58bit | 32K / 4 GB | 106 | 8 |
| ...truct Gptqmodel 4bit Vortex V1 | 32K / 5.6 GB | 11 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than coorung/EEVE_10b_ORPO_trained_v2 .
Rank the EEVE 10B ORPO Trained V2 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? 40123 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217