Instructions to use RichardErkhov/Amu_-_spin-phi2-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/Amu_-_spin-phi2-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RichardErkhov/Amu_-_spin-phi2-gguf",
	filename="spin-phi2.IQ3_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RichardErkhov/Amu_-_spin-phi2-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/Amu_-_spin-phi2-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/Amu_-_spin-phi2-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/Amu_-_spin-phi2-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/Amu_-_spin-phi2-gguf:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf RichardErkhov/Amu_-_spin-phi2-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/Amu_-_spin-phi2-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf RichardErkhov/Amu_-_spin-phi2-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/Amu_-_spin-phi2-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/Amu_-_spin-phi2-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/Amu_-_spin-phi2-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/Amu_-_spin-phi2-gguf:Q4_K_M
```

Unsloth Studio

How to use RichardErkhov/Amu_-_spin-phi2-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RichardErkhov/Amu_-_spin-phi2-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RichardErkhov/Amu_-_spin-phi2-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RichardErkhov/Amu_-_spin-phi2-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use RichardErkhov/Amu_-_spin-phi2-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/Amu_-_spin-phi2-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/Amu_-_spin-phi2-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/Amu_-_spin-phi2-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Amu_-_spin-phi2-gguf-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

spin-phi2 - GGUF

Model creator: https://huggingface.co/Amu/
Original model: https://huggingface.co/Amu/spin-phi2/

Name	Quant method	Size
spin-phi2.Q2_K.gguf	Q2_K	1.03GB
spin-phi2.IQ3_XS.gguf	IQ3_XS	1.12GB
spin-phi2.IQ3_S.gguf	IQ3_S	1.16GB
spin-phi2.Q3_K_S.gguf	Q3_K_S	1.16GB
spin-phi2.IQ3_M.gguf	IQ3_M	1.23GB
spin-phi2.Q3_K.gguf	Q3_K	1.33GB
spin-phi2.Q3_K_M.gguf	Q3_K_M	1.33GB
spin-phi2.Q3_K_L.gguf	Q3_K_L	1.47GB
spin-phi2.IQ4_XS.gguf	IQ4_XS	1.43GB
spin-phi2.Q4_0.gguf	Q4_0	1.49GB
spin-phi2.IQ4_NL.gguf	IQ4_NL	1.5GB
spin-phi2.Q4_K_S.gguf	Q4_K_S	1.51GB
spin-phi2.Q4_K.gguf	Q4_K	1.62GB
spin-phi2.Q4_K_M.gguf	Q4_K_M	1.62GB
spin-phi2.Q4_1.gguf	Q4_1	1.65GB
spin-phi2.Q5_0.gguf	Q5_0	1.8GB
spin-phi2.Q5_K_S.gguf	Q5_K_S	1.8GB
spin-phi2.Q5_K.gguf	Q5_K	1.87GB
spin-phi2.Q5_K_M.gguf	Q5_K_M	1.87GB
spin-phi2.Q5_1.gguf	Q5_1	1.95GB
spin-phi2.Q6_K.gguf	Q6_K	2.13GB
spin-phi2.Q8_0.gguf	Q8_0	2.75GB

Original model description:

language: - en license: apache-2.0 tags: - alignment-handbook - generated_from_trainer base_model: microsoft/phi-2 pipeline_tag: text-generation model-index: - name: spin-phi2 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: 63.57 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=amu/spin-phi2 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: 75.57 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=amu/spin-phi2 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: 57.93 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=amu/spin-phi2 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: 46.22 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=amu/spin-phi2 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: 73.48 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=amu/spin-phi2 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: 53.3 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=amu/spin-phi2 name: Open LLM Leaderboard

outputs

This model is a fine-tuned version of microsoft/phi-2 using SPIN on ultrachat_200k dataset.

What's new

I think SPIN not only can use on a SFT model, but also it can use on a pretrained model. Therefore, I use SPIN on a pretrained model microsoft/phi-2. And I get a higher score better than origin pretrained model. You can check the open llm leaderboard.

But the ultrachat_200k dataset is a alignment dataset for sft model. I think there should use a alignment dataset for pretrained model.

I Think the best paradigm for training a conversational Large Language Model (LLM): pretrain -> dpo(spin) -> sft -> dpo(spin)

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Framework versions

Transformers 4.37.0
Pytorch 2.1.2+cu121
Datasets 2.14.6
Tokenizers 0.15.2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	61.68
AI2 Reasoning Challenge (25-Shot)	63.57
HellaSwag (10-Shot)	75.57
MMLU (5-Shot)	57.93
TruthfulQA (0-shot)	46.22
Winogrande (5-shot)	73.48
GSM8k (5-shot)	53.30

Downloads last month: 117

GGUF

Model size

3B params

Architecture

phi2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support