Crataco's picture
Update README.md
1193bb3 verified
|
raw
history blame
6.8 kB
---
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
---
[Still uploading...]
This is [rhysjones/phi-2-orange-v2](https://huggingface.co/rhysjones/phi-2-orange-v2), quantized with the help of an importance matrix so it could offer better performance for being quantized, and have quantization levels available for lower-memory devices to run.
[Kalomaze's "groups_merged.txt"](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) was used for the importance matrix, with context set to 2,048.
Here's a chart that provides an approximation of the HellaSwag score (out of 1,000 tasks). Thanks to the randomization of tasks, it may be slightly unprecise:
|Quantization|HellaSwag|
|------------|---------|
|IQ1_S |32.5% |
|IQ2_XXS |56.3% |
|IQ2_XS |64.7% |
|IQ2_S |67.0% |
|Q2_K_S | |
|Q2_K |69.2% |
|IQ3_XXS | |
|IQ3_XS | |
|IQ3_S | |
|IQ3_M | |
|Q3_K_M |73.8% |
|IQ4_XS |74.0% |
|IQ4_NL |73.6% |
|Q4_0 |74.1% |
|Q4_K_M |74.4% |
|Q5_K_M | |
Original model card below.
***
![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).