Arxiv:1910.09700 Adapter Base model:adapter:microsoft/p... Base model:microsoft/phi-3-min... Finetuned Instruct Lora Peft Region:us Safetensors
Phi3AdapterModel 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)
Phi3AdapterModel Parameters and Internals
| LLM Name | Phi3AdapterModel |
| Repository 🤗 | https://huggingface.co/Frinkles/Phi3AdapterModel |
| Base Model(s) | |
| Required VRAM | 0.1 GB |
| Updated | 2024-08-16 |
| Maintainer | Frinkles |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Adapter |
| Model Max Length | 2048 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | o_proj|qkv_proj|down_proj|gate_up_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Quantized Models of the Phi3AdapterModel
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| Phi 3 Mini 4K Instruct GGUF | 15 | 2242 | 1 GB |
Best Alternatives to Phi3AdapterModel
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Test | 0K / 0 GB | 5 | 0 |
| Vfgf | 0K / 0 GB | 5 | 0 |
| Results | 0K / 0 GB | 5 | 0 |
| Results Phi3 Medium 4k | 0K / 0.1 GB | 6 | 0 |
| Results | 0K / 0.1 GB | 7 | 0 |
| Phi 3 Mini 4K Instruct Ru Lora | 0K / 0.1 GB | 6 | 0 |
| Phi 3 Mini 4K Instruct Sft CoT | 0K / 0.1 GB | 5 | 0 |
| Phi 3 Mini 4K Instruct Sft | 0K / 0 GB | 6 | 0 |
| Phi 3 Mini QLoRA | 0K / 0 GB | 148 | 0 |
| ...tral 8x7b Instruct V0.1 Phase2 | 0K / 0.5 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Frinkles/Phi3AdapterModel .
Rank the Phi3AdapterModel 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803