Model Card on HF 🤗: https://huggingface.co/Uni-MoE/Uni-MoE-v2-e2
Uni MoE V2 E2 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)
Uni MoE V2 E2 Parameters and Internals
| LLM Name | Uni MoE V2 E2 |
| Repository 🤗 | https://huggingface.co/Uni-MoE/Uni-MoE-v2-e2 |
| Required VRAM | 0 GB |
| Updated | 2025-02-22 |
| Maintainer | Uni-MoE |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Model Max Length | 2048 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | model.layers.17.self_attn.v_proj|model.layers.7.self_attn.o_proj|model.layers.26.self_attn.k_proj|model.layers.23.self_attn.o_proj|model.layers.28.self_attn.o_proj|model.layers.6.self_attn.q_proj|model.layers.22.self_attn.o_proj|model.layers.15.self_attn.o_proj|model.layers.29.self_attn.q_proj|model.layers.5.self_attn.v_proj|model.layers.16.self_attn.k_proj|model.layers.18.self_attn.k_proj|model.layers.3.self_attn.v_proj|model.layers.19.self_attn.v_proj|model.layers.7.self_attn.v_proj|model.layers.10.self_attn.v_proj|model.layers.3.self_attn.q_proj|model.layers.21.self_attn.q_proj|model.layers.31.self_attn.q_proj|model.layers.1.self_attn.v_proj|model.layers.13.self_attn.o_proj|model.layers.2.self_attn.k_proj|model.layers.12.self_attn.q_proj|model.layers.18.self_attn.o_proj|model.layers.24.self_attn.v_proj|model.layers.9.self_attn.o_proj|model.layers.11.self_attn.v_proj|model.layers.15.self_attn.q_proj|model.layers.8.self_attn.v_proj|model.layers.25.self_attn.o_proj|model.layers.24.self_attn.o_proj|model.layers.20.self_attn.v_proj|model.layers.27.self_attn.v_proj|model.layers.16.self_attn.v_proj|model.layers.10.self_attn.k_proj|model.layers.11.self_attn.q_proj|model.layers.17.self_attn.k_proj|model.layers.11.self_attn.o_proj|model.layers.4.self_attn.o_proj|model.layers.28.self_attn.k_proj|model.layers.23.self_attn.v_proj|model.layers.5.self_attn.o_proj|model.layers.8.self_attn.o_proj|model.layers.14.self_attn.v_proj|model.layers.14.self_attn.k_proj|model.layers.7.self_attn.q_proj|model.layers.1.self_attn.k_proj|model.layers.30.self_attn.v_proj|model.layers.22.self_attn.q_proj|model.layers.12.self_attn.k_proj|model.layers.25.self_attn.k_proj|model.layers.16.self_attn.q_proj|model.layers.25.self_attn.v_proj|model.layers.25.self_attn.q_proj|model.layers.19.self_attn.o_proj|model.layers.29.self_attn.k_proj|model.layers.3.self_attn.k_proj|model.layers.5.self_attn.k_proj|model.layers.6.self_attn.o_proj|model.layers.29.self_attn.o_proj|model.layers.9.self_attn.q_proj|model.layers.23.self_attn.k_proj|model.layers.4.self_attn.k_proj|model.layers.11.self_attn.k_proj|model.layers.17.self_attn.o_proj|model.layers.27.self_attn.k_proj|model.layers.1.self_attn.q_proj|model.layers.21.self_attn.v_proj|model.layers.12.self_attn.o_proj|model.layers.7.self_attn.k_proj|model.layers.6.self_attn.k_proj|model.layers.0.self_attn.q_proj|model.layers.0.self_attn.k_proj|model.layers.22.self_attn.k_proj|model.layers.15.self_attn.v_proj|model.layers.13.self_attn.k_proj|model.layers.3.self_attn.o_proj|model.layers.4.self_attn.q_proj|model.layers.5.self_attn.q_proj|model.layers.26.self_attn.q_proj|model.layers.16.self_attn.o_proj|model.layers.21.self_attn.o_proj|model.layers.13.self_attn.q_proj|model.layers.30.self_attn.k_proj|model.layers.31.self_attn.v_proj|model.layers.22.self_attn.v_proj|model.layers.31.self_attn.o_proj|model.layers.24.self_attn.q_proj|model.layers.28.self_attn.q_proj|model.layers.9.self_attn.v_proj|model.layers.1.self_attn.o_proj|model.layers.14.self_attn.q_proj|model.layers.29.self_attn.v_proj|model.layers.27.self_attn.q_proj|model.layers.13.self_attn.v_proj|model.layers.24.self_attn.k_proj|model.layers.2.self_attn.o_proj|model.layers.20.self_attn.o_proj|model.layers.27.self_attn.o_proj|model.layers.20.self_attn.k_proj|model.layers.2.self_attn.q_proj|model.layers.18.self_attn.q_proj|model.layers.6.self_attn.v_proj|model.layers.28.self_attn.v_proj|model.layers.17.self_attn.q_proj|model.layers.19.self_attn.q_proj|model.layers.0.self_attn.v_proj|model.layers.9.self_attn.k_proj|model.layers.8.self_attn.k_proj|model.layers.15.self_attn.k_proj|model.layers.26.self_attn.v_proj|model.layers.2.self_attn.v_proj|model.layers.21.self_attn.k_proj|model.layers.10.self_attn.q_proj|model.layers.30.self_attn.o_proj|model.layers.12.self_attn.v_proj|model.layers.14.self_attn.o_proj|model.layers.19.self_attn.k_proj|model.layers.10.self_attn.o_proj|model.layers.30.self_attn.q_proj|model.layers.31.self_attn.k_proj|model.layers.8.self_attn.q_proj|model.layers.18.self_attn.v_proj|model.layers.26.self_attn.o_proj|model.layers.20.self_attn.q_proj|model.layers.23.self_attn.q_proj|model.layers.4.self_attn.v_proj|model.layers.0.self_attn.o_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 8 |
Best Alternatives to Uni MoE V2 E2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Fine Tune Sentimental Llama | 0K / 0 GB | 92 | 0 |
| VLM2Vec LoRA | 0K / 0 GB | 133 | 7 |
| QuietStar Project | 0K / GB | 4 | 2 |
| Finetuned Llava Lora | 0K / 0.1 GB | 5 | 0 |
| Alphace Email | 0K / 0.1 GB | 7 | 0 |
| Qwen7B Haiguitang | 0K / 15.3 GB | 5 | 0 |
| Accel | 0K / 0 GB | 12 | 0 |
| Modelv3 | 0K / 13.5 GB | 5 | 0 |
| Chinese Poetry Generation | 0K / 0 GB | 8 | 0 |
| Partis Goodone | 0K / 16.1 GB | 3 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Uni-MoE/Uni-MoE-v2-e2 .
Rank the Uni MoE V2 E2 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227