Instructions to use jkim96/phi-4-DASHQ-INT3-g128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jkim96/phi-4-DASHQ-INT3-g128 with Transformers:

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

pipe = pipeline("text-generation", model="jkim96/phi-4-DASHQ-INT3-g128", 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("jkim96/phi-4-DASHQ-INT3-g128", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("jkim96/phi-4-DASHQ-INT3-g128", trust_remote_code=True, 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 jkim96/phi-4-DASHQ-INT3-g128 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jkim96/phi-4-DASHQ-INT3-g128"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jkim96/phi-4-DASHQ-INT3-g128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jkim96/phi-4-DASHQ-INT3-g128

SGLang

How to use jkim96/phi-4-DASHQ-INT3-g128 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 "jkim96/phi-4-DASHQ-INT3-g128" \
    --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": "jkim96/phi-4-DASHQ-INT3-g128",
		"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 "jkim96/phi-4-DASHQ-INT3-g128" \
        --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": "jkim96/phi-4-DASHQ-INT3-g128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jkim96/phi-4-DASHQ-INT3-g128 with Docker Model Runner:
```
docker model run hf.co/jkim96/phi-4-DASHQ-INT3-g128
```

jkim96 commited on 4 days ago

Commit

0a8e207

verified ·

1 Parent(s): 5bdba90

Add DASH-Q remote-code inference (Triton decode kernel)

Browse files

Files changed (1) hide show

README.md +16 -12

README.md CHANGED Viewed

@@ -1,17 +1,20 @@
 ---
-license: apache-2.0
 base_model: microsoft/phi-4
 library_name: transformers
 tags:
 - dashq
 - quantized
 - post-training-quantization
 ---
-# phi-4-DASHQ-INT3-g128
-This repository contains a DASH-Q packed quantized checkpoint for `microsoft/phi-4`.
-DASH-Q checkpoints require the lightweight DASH-Q runtime package for loading. They are not plain Transformers checkpoints because linear layers are stored as `PackedQuantizedLinear` modules.
 ## Usage
@@ -47,14 +50,15 @@ Without Triton, or on CPU, it falls back to dequantize-and-matmul in PyTorch.
 | Field | Value |
 | --- | --- |
 | Base model | `microsoft/phi-4` |
-| Bits | `3` |
-| Group size | `128` |
-| Scale/zero dtype | `float16` |
-| Calibration dataset | `wikitext2` |
-| Calibration samples | `128` |
-| Sequence length | `2048` |
-| Original size | `29.3190 GB` |
-| Quantized size | `7.9347 GB` |
 ## Evaluation

 ---
+license: mit
 base_model: microsoft/phi-4
+base_model_relation: quantized
 library_name: transformers
 tags:
 - dashq
 - quantized
 - post-training-quantization
+- int3
 ---
+![DASH-Q](https://raw.githubusercontent.com/JaeminK/dashq/main/assets/dashq_banner.png)
+# phi-4-DASHQ-INT3-g128
+> **DASH-Q** — Diagonal-Aware Shrinkage for Robust PTQ.
+> `INT3` · group size 128 · **7.9347 GB** (from 29.3190 GB — **3.7x smaller**)
 ## Usage
 | Field | Value |
 | --- | --- |
 | Base model | `microsoft/phi-4` |
+| Precision | INT3, group size 128 |
+| Scale / zero dtype | float16 |
+| Calibration | wikitext2, 128 samples x 2048 |
+| Size | 7.9347 GB  ·  original 29.3190 GB  ·  3.7x compression |
+## Benchmarks
+Full zero-shot / few-shot results for every DASH-Q checkpoint:
+**[github.com/JaeminK/dashq#benchmarks](https://github.com/JaeminK/dashq#benchmarks)**
 ## Evaluation