Instructions to use microsoft/phi-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/phi-4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="microsoft/phi-4") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-4") model = AutoModelForCausalLM.from_pretrained("microsoft/phi-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]:])) - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use microsoft/phi-4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "microsoft/phi-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": "microsoft/phi-4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/microsoft/phi-4
- SGLang
How to use microsoft/phi-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 "microsoft/phi-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": "microsoft/phi-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 "microsoft/phi-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": "microsoft/phi-4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use microsoft/phi-4 with Docker Model Runner:
docker model run hf.co/microsoft/phi-4
Restore <|endoftext|> (100257) as a stop token in generation_config
Browse files## Summary
Set `generation_config.json` `eos_token_id` back to `[100257, 100265]`, restoring
`<|endoftext|>` (100257) alongside `<|im_end|>` (100265) as a stop token. This reverts
only the `eos_token_id` change from #21 while keeping that PR's other improvements
(chat template fix, `pad_token` -> `<|dummy_85|>`).
## Problem
With `eos_token_id` set to `100265` only, the model can fail to stop: it produces a
correct answer and then continues emitting unrelated text until `max_tokens` is reached
(reported as "random tokens until the max token limit").
## Root cause
phi-4 ends many (typically terse) assistant turns with `<|endoftext|>` (100257) rather
than `<|im_end|>` (100265). Since #21, `generation_config.json` only lists `100265`, so
when the model emits `100257` no stop criterion fires; decoding runs past the turn
boundary (the following `<|im_start|>user<|im_sep|>` gets stripped on output, leaving a
stray `user`) and free-runs until the token cap.
## Evidence
- Reproduced with bare HF `model.generate()` at temperature 0 (greedy). Identical on
transformers 4.47 and 5.13, so it is not a transformers-version issue.
- Reproduced with vLLM 0.18.0 and 0.24.0 — byte-identical output to HF.
- Next-token distribution right after "The capital of France is Paris.":
`P(<|endoftext|>=100257) = 0.72` vs `P(<|im_end|>=100265) = 0.27`, so greedy decoding
deterministically selects the token the current config does not stop on.
- With `eos_token_id = [100257, 100265]`, generation stops cleanly on all three engines.
## Scope
Only `generation_config.json` is changed. `config.json` and the tokenizer files are left
as-is; this is the minimal change that both `transformers` and vLLM honor for stopping.
- generation_config.json +4 -1
|
@@ -1,7 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 100257,
|
| 4 |
-
"eos_token_id":
|
|
|
|
|
|
|
|
|
|
| 5 |
"pad_token_id": 100349,
|
| 6 |
"transformers_version": "4.47.0"
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
100257,
|
| 6 |
+
100265
|
| 7 |
+
],
|
| 8 |
"pad_token_id": 100349,
|
| 9 |
"transformers_version": "4.47.0"
|
| 10 |
}
|