初始化项目，由ModelHub XC社区提供模型

Model: afrideva/phi-2-sft-alpaca_gpt4_en-ep1-GGUF Source: Original Platform
2026-05-10 22:25:49 +08:00
commit 296b4e1082
9 changed files with 136 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,73 @@
+---
+base_model: Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1
+inference: false
+license: other
+license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
+license_name: microsoft-research-license
+model_creator: Yhyu13
+model_name: phi-2-sft-alpaca_gpt4_en-ep1
+pipeline_tag: text-generation
+quantized_by: afrideva
+tags:
+- gguf
+- ggml
+- quantized
+- q2_k
+- q3_k_m
+- q4_k_m
+- q5_k_m
+- q6_k
+- q8_0
+---
+# Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1-GGUF
+
+Quantized GGUF model files for [phi-2-sft-alpaca_gpt4_en-ep1](https://huggingface.co/Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1) from [Yhyu13](https://huggingface.co/Yhyu13)
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [phi-2-sft-alpaca_gpt4_en-ep1.fp16.gguf](https://huggingface.co/afrideva/phi-2-sft-alpaca_gpt4_en-ep1-GGUF/resolve/main/phi-2-sft-alpaca_gpt4_en-ep1.fp16.gguf) | fp16 | 5.56 GB  |
+| [phi-2-sft-alpaca_gpt4_en-ep1.q2_k.gguf](https://huggingface.co/afrideva/phi-2-sft-alpaca_gpt4_en-ep1-GGUF/resolve/main/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](https://huggingface.co/afrideva/phi-2-sft-alpaca_gpt4_en-ep1-GGUF/resolve/main/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](https://huggingface.co/afrideva/phi-2-sft-alpaca_gpt4_en-ep1-GGUF/resolve/main/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](https://huggingface.co/afrideva/phi-2-sft-alpaca_gpt4_en-ep1-GGUF/resolve/main/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](https://huggingface.co/afrideva/phi-2-sft-alpaca_gpt4_en-ep1-GGUF/resolve/main/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](https://huggingface.co/afrideva/phi-2-sft-alpaca_gpt4_en-ep1-GGUF/resolve/main/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!