Instructions to use Jlonge4/phi4-mini-judge-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jlonge4/phi4-mini-judge-merged with Transformers:

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

pipe = pipeline("text-generation", model="Jlonge4/phi4-mini-judge-merged", 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("Jlonge4/phi4-mini-judge-merged", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Jlonge4/phi4-mini-judge-merged", 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 Jlonge4/phi4-mini-judge-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jlonge4/phi4-mini-judge-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jlonge4/phi4-mini-judge-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jlonge4/phi4-mini-judge-merged

SGLang

How to use Jlonge4/phi4-mini-judge-merged 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 "Jlonge4/phi4-mini-judge-merged" \
    --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": "Jlonge4/phi4-mini-judge-merged",
		"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 "Jlonge4/phi4-mini-judge-merged" \
        --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": "Jlonge4/phi4-mini-judge-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jlonge4/phi4-mini-judge-merged with Docker Model Runner:
```
docker model run hf.co/Jlonge4/phi4-mini-judge-merged
```

Jlonge4 commited on Sep 28, 2025

Commit

dcc9c8d

verified ·

1 Parent(s): cc10110

Upload Phi3ForCausalLM

Browse files

Files changed (2) hide show

config.json +3 -2
generation_config.json +3 -5

config.json CHANGED Viewed

@@ -12,7 +12,7 @@
   "bos_token_id": 199999,
   "dtype": "bfloat16",
   "embd_pdrop": 0.0,
-  "eos_token_id": 199999,
   "full_attn_mod": 1,
   "hidden_act": "silu",
   "hidden_size": 3072,
@@ -27,7 +27,7 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "original_max_position_embeddings": 4096,
-  "pad_token_id": 199999,
   "partial_rotary_factor": 0.75,
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
@@ -138,6 +138,7 @@
   "sliding_window": 262144,
   "tie_word_embeddings": true,
   "transformers_version": "4.56.0",
   "use_cache": true,
   "vocab_size": 200064
 }

   "bos_token_id": 199999,
   "dtype": "bfloat16",
   "embd_pdrop": 0.0,
+  "eos_token_id": 200020,
   "full_attn_mod": 1,
   "hidden_act": "silu",
   "hidden_size": 3072,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "original_max_position_embeddings": 4096,
+  "pad_token_id": 200029,
   "partial_rotary_factor": 0.75,
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
   "sliding_window": 262144,
   "tie_word_embeddings": true,
   "transformers_version": "4.56.0",
+  "unsloth_fixed": true,
   "use_cache": true,
   "vocab_size": 200064
 }

generation_config.json CHANGED Viewed

@@ -1,10 +1,8 @@
 {
   "_from_model_config": true,
   "bos_token_id": 199999,
-  "eos_token_id": [
-    200020,
-    199999
-  ],
-  "pad_token_id": 199999,
   "transformers_version": "4.56.0"
 }

 {
   "_from_model_config": true,
   "bos_token_id": 199999,
+  "eos_token_id": 200020,
+  "max_length": 131072,
+  "pad_token_id": 200029,
   "transformers_version": "4.56.0"
 }