Instructions to use redityaa/Qwen3-8B-PKH with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use redityaa/Qwen3-8B-PKH with Transformers:

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

pipe = pipeline("text-generation", model="redityaa/Qwen3-8B-PKH")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("redityaa/Qwen3-8B-PKH")
model = AutoModelForCausalLM.from_pretrained("redityaa/Qwen3-8B-PKH")
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 redityaa/Qwen3-8B-PKH with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "redityaa/Qwen3-8B-PKH"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redityaa/Qwen3-8B-PKH",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/redityaa/Qwen3-8B-PKH

SGLang

How to use redityaa/Qwen3-8B-PKH 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 "redityaa/Qwen3-8B-PKH" \
    --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": "redityaa/Qwen3-8B-PKH",
		"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 "redityaa/Qwen3-8B-PKH" \
        --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": "redityaa/Qwen3-8B-PKH",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use redityaa/Qwen3-8B-PKH with Docker Model Runner:
```
docker model run hf.co/redityaa/Qwen3-8B-PKH
```

redityaa commited on 6 days ago

Commit

260a0f1

verified ·

1 Parent(s): 7de47e3

Upload Qwen3ForCausalLM

Browse files

Files changed (3) hide show

config.json +2 -2
generation_config.json +2 -4
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -6,7 +6,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": null,
   "dtype": "bfloat16",
-  "eos_token_id": 151643,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
@@ -56,7 +56,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 36,
   "num_key_value_heads": 8,
-  "pad_token_id": 151643,
   "rms_norm_eps": 1e-06,
   "rope_parameters": {
     "rope_theta": 1000000,

   "attention_dropout": 0.0,
   "bos_token_id": null,
   "dtype": "bfloat16",
+  "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "num_attention_heads": 32,
   "num_hidden_layers": 36,
   "num_key_value_heads": 8,
+  "pad_token_id": 151645,
   "rms_norm_eps": 1e-06,
   "rope_parameters": {
     "rope_theta": 1000000,

generation_config.json CHANGED Viewed

@@ -1,9 +1,7 @@
 {
   "_from_model_config": true,
-  "eos_token_id": [
-    151643
-  ],
-  "pad_token_id": 151643,
   "transformers_version": "5.8.1",
   "use_cache": true
 }

 {
   "_from_model_config": true,
+  "eos_token_id": 151643,
+  "pad_token_id": 151669,
   "transformers_version": "5.8.1",
   "use_cache": true
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c58a3d390580d233ad51b371510aae0a063494d755a19ebb72b990615fd51579
 size 16381517208

 version https://git-lfs.github.com/spec/v1
+oid sha256:67ac2dbc0c7ab8077aca492526b113d55fc1f16dee7ab8189cbf67a6d22c3716
 size 16381517208