Instructions to use c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4 with Transformers:

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

pipe = pipeline("text-generation", model="c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4")
model = AutoModelForMultimodalLM.from_pretrained("c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4")
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 c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4

SGLang

How to use c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4 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 "c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4" \
    --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": "c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4",
		"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 "c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4" \
        --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": "c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4 with Docker Model Runner:
```
docker model run hf.co/c01zaut/Qwen2.5-3B-Instruct-RK3588-1.1.4
```

c01zaut commited on Dec 15, 2024

Commit

46936ed

verified ·

1 Parent(s): c81917e

Upload folder using huggingface_hub

Browse files

Files changed (20) hide show

.gitattributes +12 -0
Qwen2.5-3B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-0.0.rkllm +1 -1
Qwen2.5-3B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-0.5.rkllm +1 -1
Qwen2.5-3B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-1.0.rkllm +1 -1
Qwen2.5-3B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.0.rkllm +1 -1
Qwen2.5-3B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.5.rkllm +1 -1
Qwen2.5-3B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-1.0.rkllm +1 -1
Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-0-hybrid-ratio-0.0.rkllm +3 -0
Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-0-hybrid-ratio-0.5.rkllm +3 -0
Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-0-hybrid-ratio-1.0.rkllm +3 -0
Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-1-hybrid-ratio-0.0.rkllm +3 -0
Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-1-hybrid-ratio-0.5.rkllm +3 -0
Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-1-hybrid-ratio-1.0.rkllm +3 -0
Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-0-hybrid-ratio-0.0.rkllm +3 -0
Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-0-hybrid-ratio-0.5.rkllm +3 -0
Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-0-hybrid-ratio-1.0.rkllm +3 -0
Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-1-hybrid-ratio-0.0.rkllm +3 -0
Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-1-hybrid-ratio-0.5.rkllm +3 -0
Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-1-hybrid-ratio-1.0.rkllm +3 -0
README.md +1 -1

.gitattributes CHANGED Viewed

@@ -39,3 +39,15 @@ Qwen2.5-3B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs
 Qwen2.5-3B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
 Qwen2.5-3B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
 Qwen2.5-3B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text

 Qwen2.5-3B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
 Qwen2.5-3B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
 Qwen2.5-3B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-0-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-0-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-0-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-1-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-1-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-1-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-0-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-0-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-0-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-1-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-1-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-1-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text

Qwen2.5-3B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-0.0.rkllm CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a05bf822f5fdffae4845a903eceefa6cc9188a8eee96522cf512bebb5704714b
 size 3738346748

 version https://git-lfs.github.com/spec/v1
+oid sha256:ec95582efedb94b8ebf2a3ca2fa73bd49814cfb35b86c8bc94a3b423c6a73513
 size 3738346748

Qwen2.5-3B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-0.5.rkllm CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a05bf822f5fdffae4845a903eceefa6cc9188a8eee96522cf512bebb5704714b
 size 3738346748

 version https://git-lfs.github.com/spec/v1
+oid sha256:ec95582efedb94b8ebf2a3ca2fa73bd49814cfb35b86c8bc94a3b423c6a73513
 size 3738346748

Qwen2.5-3B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-1.0.rkllm CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a05bf822f5fdffae4845a903eceefa6cc9188a8eee96522cf512bebb5704714b
 size 3738346748

 version https://git-lfs.github.com/spec/v1
+oid sha256:ec95582efedb94b8ebf2a3ca2fa73bd49814cfb35b86c8bc94a3b423c6a73513
 size 3738346748

Qwen2.5-3B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.0.rkllm CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67bd9b8abff97cbc60b9e8a32c86b1a63715968c3a76a8a01b5821fd0282b24e
 size 3738346748

 version https://git-lfs.github.com/spec/v1
+oid sha256:b44a9906d1566f6f32fd9c79f42ead0c1b1aeabe25bbe62904b94cdb4a6240db
 size 3738346748

Qwen2.5-3B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.5.rkllm CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67bd9b8abff97cbc60b9e8a32c86b1a63715968c3a76a8a01b5821fd0282b24e
 size 3738346748

 version https://git-lfs.github.com/spec/v1
+oid sha256:b44a9906d1566f6f32fd9c79f42ead0c1b1aeabe25bbe62904b94cdb4a6240db
 size 3738346748

Qwen2.5-3B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-1.0.rkllm CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67bd9b8abff97cbc60b9e8a32c86b1a63715968c3a76a8a01b5821fd0282b24e
 size 3738346748

 version https://git-lfs.github.com/spec/v1
+oid sha256:b44a9906d1566f6f32fd9c79f42ead0c1b1aeabe25bbe62904b94cdb4a6240db
 size 3738346748

Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-0-hybrid-ratio-0.0.rkllm ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5d380b0f352105a68fc4644ebe0d2d0655e0a7014ca2b816b38c93847fcf21e2
+size 3969098164

Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-0-hybrid-ratio-0.5.rkllm ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5d380b0f352105a68fc4644ebe0d2d0655e0a7014ca2b816b38c93847fcf21e2
+size 3969098164

Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-0-hybrid-ratio-1.0.rkllm ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5d380b0f352105a68fc4644ebe0d2d0655e0a7014ca2b816b38c93847fcf21e2
+size 3969098164

Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-1-hybrid-ratio-0.0.rkllm ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f67bf999b75e8e9f82208644c3283a08dbfc216211e7075ea5a31157ac2301
+size 3949984532

Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-1-hybrid-ratio-0.5.rkllm ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f67bf999b75e8e9f82208644c3283a08dbfc216211e7075ea5a31157ac2301
+size 3949984532

Qwen2.5-3B-Instruct-rk3588-w8a8_g128-opt-1-hybrid-ratio-1.0.rkllm ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f67bf999b75e8e9f82208644c3283a08dbfc216211e7075ea5a31157ac2301
+size 3949984532

Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-0-hybrid-ratio-0.0.rkllm ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c217bae5969f51587c7aa537e24b4b72d88418bec1cfaf94fda8f6d56751f08c
+size 3849410292

Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-0-hybrid-ratio-0.5.rkllm ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c217bae5969f51587c7aa537e24b4b72d88418bec1cfaf94fda8f6d56751f08c
+size 3849410292

Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-0-hybrid-ratio-1.0.rkllm ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c217bae5969f51587c7aa537e24b4b72d88418bec1cfaf94fda8f6d56751f08c
+size 3849410292

Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-1-hybrid-ratio-0.0.rkllm ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:413a02d4fccfba707afe778ed8b95d0e0d46a44fc09323d4e155c39f3c8c6e09
+size 3840479444

Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-1-hybrid-ratio-0.5.rkllm ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:413a02d4fccfba707afe778ed8b95d0e0d46a44fc09323d4e155c39f3c8c6e09
+size 3840479444

Qwen2.5-3B-Instruct-rk3588-w8a8_g256-opt-1-hybrid-ratio-1.0.rkllm ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:413a02d4fccfba707afe778ed8b95d0e0d46a44fc09323d4e155c39f3c8c6e09
+size 3840479444

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ tags:
 ---
 # Qwen2.5-3B-Instruct-RK3588-1.1.2
-This version of Qwen2.5-3B-Instruct has been converted to run on the RK3588 NPU using ['w8a8'] quantization.
 This model has been optimized with the following LoRA:
 Compatible with RKLLM version: 1.1.2

 ---
 # Qwen2.5-3B-Instruct-RK3588-1.1.2
+This version of Qwen2.5-3B-Instruct has been converted to run on the RK3588 NPU using ['w8a8', 'w8a8_g128', 'w8a8_g256', 'w8a8_g512'] quantization.
 This model has been optimized with the following LoRA:
 Compatible with RKLLM version: 1.1.2