Instructions to use Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5

SGLang

How to use Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5 with Docker Model Runner:
```
docker model run hf.co/Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5
```

Description

This model was trained as part of the Reinforcement Learning - 24 project at Peking University, focusing on [simpo].

Authors

Ejafa Bassam
Yaroslav Ponomarenko

phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5

This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on the princeton-nlp/llama3-ultrafeedback dataset. It achieves the following results on the evaluation set:

Loss: 1.6226
Rewards/chosen: -2.2430
Rewards/rejected: -2.6527
Rewards/accuracies: 0.625
Rewards/margins: 0.4097
Logps/rejected: -1.0611
Logps/chosen: -0.8972
Logits/rejected: 2.0148
Logits/chosen: 2.0096

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
train_batch_size: 2
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
1.6417	0.8549	400	1.6236	-2.2390	-2.6457	0.6210	0.4067	-1.0583	-0.8956	2.0190	2.0146

Framework versions

Transformers 4.41.2
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Downloads last month: 5

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5

Base model

microsoft/Phi-3-mini-128k-instruct

Finetuned

(44)

this model

Merges

1 model

Dataset used to train Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5

Collection including Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5

policy optimization

Collection

4 items • Updated Oct 30, 2025