Instructions to use cstr/phi-3-orpo-v9_4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cstr/phi-3-orpo-v9_4 with Transformers:

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

pipe = pipeline("text-generation", model="cstr/phi-3-orpo-v9_4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cstr/phi-3-orpo-v9_4")
model = AutoModelForCausalLM.from_pretrained("cstr/phi-3-orpo-v9_4", device_map="auto")
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 Settings

vLLM

How to use cstr/phi-3-orpo-v9_4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cstr/phi-3-orpo-v9_4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cstr/phi-3-orpo-v9_4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cstr/phi-3-orpo-v9_4

SGLang

How to use cstr/phi-3-orpo-v9_4 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 "cstr/phi-3-orpo-v9_4" \
    --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": "cstr/phi-3-orpo-v9_4",
		"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 "cstr/phi-3-orpo-v9_4" \
        --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": "cstr/phi-3-orpo-v9_4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use cstr/phi-3-orpo-v9_4 with Docker Model Runner:
```
docker model run hf.co/cstr/phi-3-orpo-v9_4
```

Uploaded model

Developed by: cstr
License: apache-2.0
Finetuned from model : cstr/phi-3-orpo-v8_16

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

EU AI Act Art. 53 — provider obligations

Added 2026-08-02 during an account-wide provenance review.

This is a fine-tune, not a format conversion. Most cstr/* repositories are GGUF conversions where the upstream research team remains the provider of the model and conversion changes only the numeric representation of the weights. Training changes the model itself, so under Regulation (EU) 2024/1689 the maintainer of this repository is plausibly the provider of the model it produced, and the obligations that survive the Art. 53(2) free-and-open-source exemption — Art. 53(1)(c) and 53(1)(d) — attach here.

Art. 53(1)(c) — copyright policy. This model shares its training pipeline with cstr/phi-3-orpo-v9_16, which used johannhartmann/mistralorpo. The specific run parameters for this variant are not recorded in this repository. No text or data mining was performed to assemble a corpus for this repository, so no rights reservation under Art. 4(3) of Directive (EU) 2019/790 was engaged by this step. Any credible claim that this model was trained on material without the necessary rights will be acted on — contact via the Community tab.

Art. 53(1)(d) — training content. ORPO steps on German preference data on top of cstr/phi-3-orpo-v8_16. This card records fewer run details than its sibling cstr/phi-3-orpo-v9_16, and the difference between the two variants is not documented here — stated as a gap rather than guessed at. The underlying training content is Microsoft's Phi-3-mini, documented by its provider.

Base model. cstr/phi-3-orpo-v8_16 — the training built on those weights and inherits their terms.

Downloads last month: 16

Safetensors

Model size

4B params

Tensor type

F16

Model tree for cstr/phi-3-orpo-v9_4

Base model

vonjack/Phi-3-mini-4k-instruct-LLaMAfied

Finetuned

cstr/phi-3-orpo-v8_16

Quantized

(2)

this model