初始化项目，由ModelHub XC社区提供模型

Model: RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf Source: Original Platform
2026-10-24 04:22:17 +08:00
commit fe3364cdd0
24 changed files with 358 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,235 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+phi-2-orange-v2 - GGUF
+- Model creator: https://huggingface.co/rhysjones/
+- Original model: https://huggingface.co/rhysjones/phi-2-orange-v2/
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [phi-2-orange-v2.Q2_K.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q2_K.gguf) | Q2_K | 1.03GB |
+| [phi-2-orange-v2.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.IQ3_XS.gguf) | IQ3_XS | 1.12GB |
+| [phi-2-orange-v2.IQ3_S.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.IQ3_S.gguf) | IQ3_S | 1.16GB |
+| [phi-2-orange-v2.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q3_K_S.gguf) | Q3_K_S | 1.16GB |
+| [phi-2-orange-v2.IQ3_M.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.IQ3_M.gguf) | IQ3_M | 1.23GB |
+| [phi-2-orange-v2.Q3_K.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q3_K.gguf) | Q3_K | 1.33GB |
+| [phi-2-orange-v2.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q3_K_M.gguf) | Q3_K_M | 1.33GB |
+| [phi-2-orange-v2.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q3_K_L.gguf) | Q3_K_L | 1.47GB |
+| [phi-2-orange-v2.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.IQ4_XS.gguf) | IQ4_XS | 1.43GB |
+| [phi-2-orange-v2.Q4_0.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q4_0.gguf) | Q4_0 | 1.49GB |
+| [phi-2-orange-v2.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.IQ4_NL.gguf) | IQ4_NL | 1.5GB |
+| [phi-2-orange-v2.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q4_K_S.gguf) | Q4_K_S | 1.51GB |
+| [phi-2-orange-v2.Q4_K.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q4_K.gguf) | Q4_K | 1.62GB |
+| [phi-2-orange-v2.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q4_K_M.gguf) | Q4_K_M | 1.62GB |
+| [phi-2-orange-v2.Q4_1.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q4_1.gguf) | Q4_1 | 1.65GB |
+| [phi-2-orange-v2.Q5_0.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q5_0.gguf) | Q5_0 | 1.8GB |
+| [phi-2-orange-v2.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q5_K_S.gguf) | Q5_K_S | 1.8GB |
+| [phi-2-orange-v2.Q5_K.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q5_K.gguf) | Q5_K | 1.87GB |
+| [phi-2-orange-v2.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q5_K_M.gguf) | Q5_K_M | 1.87GB |
+| [phi-2-orange-v2.Q5_1.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q5_1.gguf) | Q5_1 | 1.95GB |
+| [phi-2-orange-v2.Q6_K.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q6_K.gguf) | Q6_K | 2.13GB |
+| [phi-2-orange-v2.Q8_0.gguf](https://huggingface.co/RichardErkhov/rhysjones_-_phi-2-orange-v2-gguf/blob/main/phi-2-orange-v2.Q8_0.gguf) | Q8_0 | 2.75GB |
+
+
+
+
+Original model description:
+---
+license: mit
+datasets:
+- Open-Orca/SlimOrca-Dedup
+- migtissera/Synthia-v1.3
+- LDJnr/Verified-Camel
+- LDJnr/Pure-Dove
+- LDJnr/Capybara
+- meta-math/MetaMathQA
+- Intel/orca_dpo_pairs
+- argilla/ultrafeedback-binarized-preferences-cleaned
+widget:
+  - example_title: "Example interaction"
+    text: "Why is the sky blue?"
+inference: 
+  parameters:
+    do_sample: True
+    temperature: 0.1
+model-index:
+- name: phi-2-orange-v2
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 61.86
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rhysjones/phi-2-orange-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 76.32
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rhysjones/phi-2-orange-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 55.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rhysjones/phi-2-orange-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 54.84
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rhysjones/phi-2-orange-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 75.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rhysjones/phi-2-orange-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 57.62
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rhysjones/phi-2-orange-v2
+      name: Open LLM Leaderboard
+---
+![Phi-2 Orange](https://huggingface.co/rhysjones/phi-2-orange-v2/resolve/main/phi-2-orange.jpg)
+
+# Phi-2 Orange Version 2
+
+A two-step finetune of Phi-2, with a bit more zest.
+
+This is an improved version of the original [Phi-2-Orange](https://huggingface.co/rhysjones/phi-2-orange) that 
+uses an updated training process on the same datasets.
+
+It also uses the latest updated model from Microsoft's [Phi-2](https://huggingface.co/microsoft/phi-2), making it directly usable
+within Hugging Face's Transformers library (without the need for trust remote code).
+
+# Prompt Format
+
+Phi-2 Orange v2 uses ChatML as the prompt format.  
+(Update 12th March 2024: fixed eos_token issue)
+
+It's recommended to always prompt with a system instruction (use whatever system prompt you like):
+
+```
+<|im_start|>system
+You are a helpful assistant for Python which outputs in Markdown format.<|im_end|>
+<|im_start|>user
+Write a function to calculate the Fibonacci sequence<|im_end|>
+<|im_start|>assistant
+
+```
+
+For example, if you find the model's output to be overly verbose, instruct it to be short and concise:
+
+```
+<|im_start|>system
+You are a helpful assistant. Be short and direct in your answers.<|im_end|>
+<|im_start|>user
+Was Tom Hanks in the movie Forrest Gump? If so, who did he play and give details of the plot.<|im_end|>
+<|im_start|>assistant
+```
+
+# Evaluations
+
+
+[Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)  
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_rhysjones__phi-2-orange-v2)
+|             Metric              |Value|
+|---------------------------------|----:|
+|Average                          |63.67|
+|AI2 Reasoning Challenge (25-Shot)|61.86|
+|HellaSwag (10-Shot)              |76.32|
+|MMLU (5-Shot)                    |55.72|
+|TruthfulQA (0-shot)              |54.84|
+|Winogrande (5-shot)              |75.69|
+|GSM8k (5-shot)                   |57.62|
+
+[YALL - Yet Another LLM Leaderboard](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard)  
+Evaluation from	[mlabonne](https://huggingface.co/mlabonne)'s alternative LLM leaderboard:
+|             Metric              |Value|
+|---------------------------------|----:|
+|Average                          |49.64|
+|AGIEval                          |34.55|
+|GPT4All                          |70.96|
+|TruthfulQA                       |54.87|
+|Bigbench                         |38.17|
+
+# Limitations
+
+This model shares the same limitations as the underlying Phi-2 model, details of which are found [here](https://huggingface.co/microsoft/phi-2#limitations-of-phi-2).
+
+
+
+