Arxiv:1910.09700 Adapter Adapter-transformers Conversational Finetuned Lora Region:us Safetensors Zh
Model Card on HF 🤗: https://huggingface.co/cuidada/Hua-v0.1
Hua V0.1 Benchmarks
ARC: 44.62 vs 96.7 (so35)-53.9%
HellaSwag: 66.52 vs 95.3 (gpt4)-30.2%
MMLU: 44.22 vs 88.3 (so35)-49.9%
TruthfulQA: 43.18 vs 59 (gpt4)-26.8%
WinoGrande: 63.06 vs 87.5 (gpt4)-27.9%
GSM8K: 20.32 vs 96.4 (so35)-78.9%
LLME Score: 0.22122
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)
Hua V0.1 Parameters and Internals
| LLM Name | Hua V0.1 |
| Repository 🤗 | https://huggingface.co/cuidada/Hua-v0.1 |
| Required VRAM | 0 GB |
| Updated | 2024-08-15 |
| Maintainer | cuidada |
| Model Files | |
| Supported Languages | zh |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Model Max Length | 32768 |
| Is Biased | none |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | gate_proj|down_proj|k_proj|up_proj|v_proj|q_proj|o_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 8 |
| Errors | replace |
Best Alternatives to Hua V0.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 3 Mini 4K Instruct Sa V0.1 | 0K / 0 GB | 9 | 0 |
| Reflection Model | 0K / 0.2 GB | 0 | 1 |
| SpectraMind | 0K / 16.1 GB | 65 | 2 |
| SpectraMindQ | 0K / 0.2 GB | 10 | 1 |
| L3.1 Spark R64 LoRA | 0K / 0.4 GB | 41 | 0 |
| Mistral Small Fujin Qlora | 0K / 0.8 GB | 15 | 1 |
| Zephyr Phi 1 5 Sft Qlora | 0K / 0 GB | 5 | 0 |
| Ll3 C3 Lora New | 0K / 0 GB | 7 | 0 |
| Phi Openllm Lb Test | 0K / 0 GB | 5 | 0 |
| CodeHAWK | 0K / 0 GB | 8 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than cuidada/Hua-v0.1 .
Rank the Hua V0.1 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217