Merged Model Arxiv:2303.08774 Autotrain compatible Conversational Dataset:argilla/ultrafeedback-... Dataset:intel/orca dpo pairs Dataset:jondurbin/truthy-dpo-v... Dataset:wenbopan/chinese-dpo-p... En Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow Zh
Faro Yi 9B DPO Benchmarks
ARC: 64.16 vs 96.7 (so35)-33.7%
HellaSwag: 78.92 vs 95.3 (gpt4)-17.2%
MMLU: 70.74 vs 88.3 (so35)-19.9%
TruthfulQA: 56.25 vs 59 (gpt4)-4.7%
WinoGrande: 77.82 vs 87.5 (gpt4)-11.1%
GSM8K: 64.75 vs 96.4 (so35)-32.8%
LLME Score: 0.27921
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)
Faro Yi 9B DPO Parameters and Internals
| LLM Name | Faro Yi 9B DPO |
| Repository 🤗 | https://huggingface.co/wenbopan/Faro-Yi-9B-DPO |
| Merged Model | Yes |
| Model Size | 9b |
| Required VRAM | 17.7 GB |
| Updated | 2024-09-07 |
| Maintainer | wenbopan |
| Model Type | llama |
| Model Files | |
| Supported Languages | en zh |
| Model Architecture | LlamaForCausalLM |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.39.3 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 64000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Faro Yi 9B DPO
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Yi 9B 200K | 256K / 17.7 GB | 16503 | 75 |
| BigYi 15.75B 200K | 256K / 30.3 GB | 7 | 0 |
| Yi Coder 9B Chat | 128K / 17.7 GB | 1035 | 82 |
| Yi Coder 9B | 128K / 17.7 GB | 53 | 22 |
| Yi 1.5 9B 32K | 32K / 17.7 GB | 8275 | 18 |
| Faro Yi 9B | 32K / 17.7 GB | 5141 | 17 |
| Openbuddy Yi1.5 9B V21.1 32K | 32K / 17.8 GB | 664 | 1 |
| Yi 1.5 9B Chat 16K | 16K / 17.7 GB | 50014 | 31 |
| Peach 9B 8K Roleplay | 16K / 17.7 GB | 3149 | 75 |
| Yi 1.5 9B Chat 16K Abliterated | 16K / 17.7 GB | 38 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than wenbopan/Faro-Yi-9B-DPO .
Rank the Faro Yi 9B DPO 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803