Instructions to use amd/PARD2-Qwen3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amd/PARD2-Qwen3-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="amd/PARD2-Qwen3-8B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("amd/PARD2-Qwen3-8B") model = AutoModelForCausalLM.from_pretrained("amd/PARD2-Qwen3-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use amd/PARD2-Qwen3-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "amd/PARD2-Qwen3-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amd/PARD2-Qwen3-8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/amd/PARD2-Qwen3-8B
- SGLang
How to use amd/PARD2-Qwen3-8B 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 "amd/PARD2-Qwen3-8B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amd/PARD2-Qwen3-8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "amd/PARD2-Qwen3-8B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amd/PARD2-Qwen3-8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use amd/PARD2-Qwen3-8B with Docker Model Runner:
docker model run hf.co/amd/PARD2-Qwen3-8B
Upload folder using huggingface_hub
Browse files- config.json +1 -1
- model.safetensors +2 -2
- warp_model.bin +2 -2
config.json
CHANGED
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"pard2": true,
|
| 22 |
"pard2_proj_bias": false,
|
| 23 |
"pard2_scale": 0.02,
|
| 24 |
-
"pard2_target_dim":
|
| 25 |
"pard2_target_layers": [
|
| 26 |
-1,
|
| 27 |
-8,
|
|
|
|
| 21 |
"pard2": true,
|
| 22 |
"pard2_proj_bias": false,
|
| 23 |
"pard2_scale": 0.02,
|
| 24 |
+
"pard2_target_dim": 16384,
|
| 25 |
"pard2_target_layers": [
|
| 26 |
-1,
|
| 27 |
-8,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf1a6c0e69db76420f1f58381b03263711e8f1ae5938b955a0ce49b7aa60502e
|
| 3 |
+
size 1503300456
|
warp_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fa85c78591b18eecb160f131ddafc109ed5d2fb52467415818b83dd54ba0f1c
|
| 3 |
+
size 33556094
|