Adapter Base model:adapter:microsoft/p... Base model:microsoft/phi-3-med... Finetuned Generated from trainer Instruct Lora Peft Region:us Safetensors Sft Trl
Model Card on HF 🤗: https://huggingface.co/kostasman1/results_Phi3_medium_4k
Results Phi3 Medium 4k 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)
Results Phi3 Medium 4K Parameters and Internals
| LLM Name | Results Phi3 Medium 4k |
| Repository 🤗 | https://huggingface.co/kostasman1/results_Phi3_medium_4k |
| Base Model(s) | |
| Required VRAM | 0.1 GB |
| Updated | 2024-11-02 |
| Maintainer | kostasman1 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Adapter |
| License | mit |
| Model Max Length | 4096 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | o_proj|v_proj|k_proj|gate_proj|down_proj|up_proj|q_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Results Phi3 Medium 4K
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 3 Mini 4K Instruct Sa V0.1 | 0K / 0 GB | 9 | 0 |
| Mistral Small Fujin Qlora | 0K / 0.8 GB | 15 | 1 |
| Test | 0K / 0 GB | 5 | 0 |
| Vfgf | 0K / 0 GB | 6 | 0 |
| Results | 0K / 0 GB | 5 | 0 |
| Phi 3 Mini QLoRA | 0K / 0 GB | 180 | 0 |
| Results | 0K / 0.1 GB | 5 | 0 |
| Phi3AdapterModel | 0K / 0.1 GB | 5 | 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 |
Note: green Score (e.g. "73.2") means that the model is better than kostasman1/results_Phi3_medium_4k .
Rank the Results Phi3 Medium 4K 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