Instructions to use OpceanAI/qwenti-inference with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpceanAI/qwenti-inference with Transformers:

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

pipe = pipeline("text-generation", model="OpceanAI/qwenti-inference")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpceanAI/qwenti-inference")
model = AutoModelForCausalLM.from_pretrained("OpceanAI/qwenti-inference", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpceanAI/qwenti-inference with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OpceanAI/qwenti-inference

SGLang

How to use OpceanAI/qwenti-inference 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 "OpceanAI/qwenti-inference" \
    --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": "OpceanAI/qwenti-inference",
		"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 "OpceanAI/qwenti-inference" \
        --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": "OpceanAI/qwenti-inference",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpceanAI/qwenti-inference with Docker Model Runner:
```
docker model run hf.co/OpceanAI/qwenti-inference
```

qwenti-inference / scripts /asmtest.c

OpceanAI

Model card, paper, figures, logs and scripts

2049fc8 verified 1 day ago

Raw History Blame Contribute Delete

548 Bytes

#include <stdint.h>
#include "rt.h"
#include "weights_tl.h"
extern void vk_8_init_scaled(int32_t *, int, int, const int32_t *, int32_t);
const int8_t *vk_x;
static int8_t act[64] __attribute__((aligned(4)));
static int32_t S[4] = {1, 1, 1, 1}, out[4];
int main(void) {
    for (int i = 0; i < 64; i++) act[i] = 0;
    act[0] = 100; act[1] = 50; act[2] = -30;
    vk_x = act;
    vk_8_init_scaled(out, G_HEAD, 4, S, 1 << 30);
    volatile int32_t *dump = (volatile int32_t *)0xE000;
    for (int k = 0; k < 4; k++) dump[k] = out[k];
    return 0;
}

	#include <stdint.h>
	#include "rt.h"
	#include "weights_tl.h"
	extern void vk_8_init_scaled(int32_t , int, int, const int32_t , int32_t);
	const int8_t *vk_x;
	static int8_t act[64] __attribute__((aligned(4)));
	static int32_t S[4] = {1, 1, 1, 1}, out[4];
	int main(void) {
	for (int i = 0; i < 64; i++) act[i] = 0;
	act[0] = 100; act[1] = 50; act[2] = -30;
	vk_x = act;
	vk_8_init_scaled(out, G_HEAD, 4, S, 1 << 30);
	volatile int32_t dump = (volatile int32_t )0xE000;
	for (int k = 0; k < 4; k++) dump[k] = out[k];
	return 0;
	}