Model Card on HF 🤗: https://huggingface.co/shtapm/llava_phi3
Llava Phi3 Parameters and Internals
| LLM Name | Llava Phi3 |
| Repository 🤗 | https://huggingface.co/shtapm/llava_phi3 |
| Required VRAM | 0.8 GB |
| Updated | 2024-07-04 |
| Maintainer | shtapm |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| Model Max Length | 2048 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | model.layers.6.self_attn.qkv_proj|model.layers.16.mlp.down_proj|model.layers.22.self_attn.qkv_proj|model.layers.1.self_attn.qkv_proj|model.layers.9.self_attn.o_proj|model.layers.18.mlp.gate_up_proj|model.layers.26.self_attn.qkv_proj|model.layers.23.mlp.down_proj|model.layers.5.self_attn.o_proj|model.layers.6.mlp.down_proj|model.layers.2.mlp.gate_up_proj|model.layers.11.mlp.down_proj|model.layers.2.self_attn.qkv_proj|model.layers.27.self_attn.qkv_proj|model.layers.30.self_attn.o_proj|model.layers.17.mlp.gate_up_proj|model.layers.13.mlp.gate_up_proj|model.layers.6.mlp.gate_up_proj|model.layers.20.mlp.gate_up_proj|model.layers.27.mlp.gate_up_proj|model.layers.5.mlp.down_proj|model.layers.22.mlp.gate_up_proj|model.layers.26.self_attn.o_proj|model.layers.31.self_attn.qkv_proj|model.layers.7.mlp.down_proj|model.layers.21.mlp.down_proj|model.layers.16.mlp.gate_up_proj|model.layers.3.mlp.gate_up_proj|model.layers.11.mlp.gate_up_proj|model.layers.15.self_attn.o_proj|model.layers.4.mlp.gate_up_proj|model.layers.26.mlp.down_proj|model.layers.24.mlp.down_proj|model.layers.26.mlp.gate_up_proj|model.layers.28.self_attn.o_proj|model.layers.5.mlp.gate_up_proj|model.layers.31.mlp.down_proj|model.layers.27.mlp.down_proj|model.layers.16.self_attn.o_proj|model.layers.9.mlp.gate_up_proj|model.layers.23.mlp.gate_up_proj|model.layers.7.mlp.gate_up_proj|model.layers.28.mlp.down_proj|model.layers.23.self_attn.o_proj|model.layers.12.mlp.gate_up_proj|model.layers.1.mlp.gate_up_proj|model.layers.3.mlp.down_proj|model.layers.2.mlp.down_proj|model.layers.29.mlp.gate_up_proj|model.layers.7.self_attn.o_proj|model.layers.8.self_attn.qkv_proj|model.layers.14.mlp.gate_up_proj|model.layers.20.self_attn.qkv_proj|model.layers.3.self_attn.o_proj|model.layers.8.mlp.down_proj|model.layers.12.mlp.down_proj|model.layers.15.mlp.gate_up_proj|model.layers.24.mlp.gate_up_proj|model.layers.29.mlp.down_proj|model.layers.4.mlp.down_proj|model.layers.16.self_attn.qkv_proj|model.layers.12.self_attn.o_proj|model.layers.10.mlp.gate_up_proj|model.layers.24.self_attn.o_proj|model.layers.13.self_attn.qkv_proj|model.layers.17.self_attn.o_proj|model.layers.11.self_attn.qkv_proj|model.layers.22.self_attn.o_proj|model.layers.29.self_attn.qkv_proj|model.layers.23.self_attn.qkv_proj|model.layers.25.self_attn.qkv_proj|model.layers.22.mlp.down_proj|model.layers.19.self_attn.qkv_proj|model.layers.17.mlp.down_proj|model.layers.18.mlp.down_proj|model.layers.19.self_attn.o_proj|model.layers.25.mlp.down_proj|model.layers.30.self_attn.qkv_proj|model.layers.14.self_attn.o_proj|model.layers.10.self_attn.o_proj|model.layers.11.self_attn.o_proj|model.layers.5.self_attn.qkv_proj|model.layers.28.self_attn.qkv_proj|model.layers.12.self_attn.qkv_proj|model.layers.0.mlp.gate_up_proj|model.layers.20.self_attn.o_proj|model.layers.30.mlp.gate_up_proj|model.layers.21.self_attn.o_proj|model.layers.14.self_attn.qkv_proj|model.layers.7.self_attn.qkv_proj|model.layers.31.mlp.gate_up_proj|model.layers.3.self_attn.qkv_proj|model.layers.15.self_attn.qkv_proj|model.layers.18.self_attn.qkv_proj|model.layers.21.self_attn.qkv_proj|model.layers.25.mlp.gate_up_proj|model.layers.10.self_attn.qkv_proj|model.layers.4.self_attn.o_proj|model.layers.10.mlp.down_proj|model.layers.1.mlp.down_proj|model.layers.0.self_attn.o_proj|model.layers.28.mlp.gate_up_proj|model.layers.8.mlp.gate_up_proj|model.layers.13.self_attn.o_proj|model.layers.1.self_attn.o_proj|model.layers.24.self_attn.qkv_proj|model.layers.6.self_attn.o_proj|model.layers.9.self_attn.qkv_proj|model.layers.25.self_attn.o_proj|model.layers.30.mlp.down_proj|model.layers.17.self_attn.qkv_proj|model.layers.20.mlp.down_proj|model.layers.8.self_attn.o_proj|model.layers.9.mlp.down_proj|model.layers.29.self_attn.o_proj|model.layers.2.self_attn.o_proj|model.layers.4.self_attn.qkv_proj|model.layers.15.mlp.down_proj|model.layers.21.mlp.gate_up_proj|model.layers.27.self_attn.o_proj|model.layers.0.mlp.down_proj|model.layers.19.mlp.down_proj|model.layers.31.self_attn.o_proj|model.layers.0.self_attn.qkv_proj|model.layers.14.mlp.down_proj|model.layers.18.self_attn.o_proj|model.layers.13.mlp.down_proj|model.layers.19.mlp.gate_up_proj |
| LoRA Alpha | 256 |
| LoRA Dropout | 0.05 |
| R Param | 128 |
Best Alternatives to Llava Phi3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Asdf | 0K / 0.1 GB | 14 | 0 |
| MS32 3 | 0K / 1.5 GB | 6 | 0 |
| MS32 2 | 0K / 0.7 GB | 5 | 0 |
| Tinyllama Cpt | 0K / 0.5 GB | 6 | 0 |
| Fine Tune Sentimental Llama | 0K / 0 GB | 5 | 0 |
| VLM2Vec LoRA | 0K / 0 GB | 31 | 11 |
| QuietStar Project | 0K / GB | 8 | 2 |
| Finetuned Llava Lora | 0K / 0.1 GB | 5 | 0 |
| Alphace Email | 0K / 0.1 GB | 6 | 0 |
| Qwen7B Haiguitang | 0K / 15.3 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than shtapm/llava_phi3 .
Rank the Llava Phi3 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124