base_model, inference, license, license_link, license_name, model_creator, model_name, pipeline_tag, quantized_by, tags
| base_model | inference | license | license_link | license_name | model_creator | model_name | pipeline_tag | quantized_by | tags | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1 | false | other | https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE | microsoft-research-license | Yhyu13 | phi-2-sft-alpaca_gpt4_en-ep1 | text-generation | afrideva |
|
Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1-GGUF
Quantized GGUF model files for phi-2-sft-alpaca_gpt4_en-ep1 from Yhyu13
| Name | Quant method | Size |
|---|---|---|
| phi-2-sft-alpaca_gpt4_en-ep1.fp16.gguf | fp16 | 5.56 GB |
| phi-2-sft-alpaca_gpt4_en-ep1.q2_k.gguf | q2_k | 1.17 GB |
| phi-2-sft-alpaca_gpt4_en-ep1.q3_k_m.gguf | q3_k_m | 1.48 GB |
| phi-2-sft-alpaca_gpt4_en-ep1.q4_k_m.gguf | q4_k_m | 1.79 GB |
| phi-2-sft-alpaca_gpt4_en-ep1.q5_k_m.gguf | q5_k_m | 2.07 GB |
| phi-2-sft-alpaca_gpt4_en-ep1.q6_k.gguf | q6_k | 2.29 GB |
| phi-2-sft-alpaca_gpt4_en-ep1.q8_0.gguf | q8_0 | 2.96 GB |
Original Model Card:
This is the merged model for LoRA https://huggingface.co/Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1-lora
From this https://huggingface.co/microsoft/phi-2/discussions/38
Since phi2 requires remote code which HF open llm leaderboard would not accept at this moment,
I ran phi2 and my sft to the AlpcaEval benchmark
https://tatsu-lab.github.io/alpaca_eval/
Here is result evaluated by chatpgpt https://github.com/tatsu-lab/alpaca_eval/pull/183
win_rate standard_error n_total avg_length
gpt4 73.79 1.54 805 1365
claude 70.37 1.60 805 1082
chatgpt 66.09 1.66 805 811
wizardlm-13b 65.16 1.67 805 985
vicuna-13b 64.10 1.69 805 1037
guanaco-65b 62.36 1.71 805 1249
oasst-rlhf-llama-33b 62.05 1.71 805 1079
alpaca-farm-ppo-human 60.25 1.72 805 803
falcon-40b-instruct 56.52 1.74 805 662
phi-2-alpaca-gpt4(new) 54.23 1.75 804 1138
text_davinci_003 50.00 0.00 805 307
alpaca-7b 45.22 1.74 805 396
phi-2(new) 43.79 1.74 805 924
text_davinci_001 28.07 1.56 805 296
It could be a milestone for small models, we finally have one open model can run for everyone which surpass GPT3.5!