Instructions to use iproskurina/qwen-hf-r100-seeded-recursive-np-iter1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iproskurina/qwen-hf-r100-seeded-recursive-np-iter1 with Transformers:

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

pipe = pipeline("text-generation", model="iproskurina/qwen-hf-r100-seeded-recursive-np-iter1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("iproskurina/qwen-hf-r100-seeded-recursive-np-iter1")
model = AutoModelForCausalLM.from_pretrained("iproskurina/qwen-hf-r100-seeded-recursive-np-iter1", 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 iproskurina/qwen-hf-r100-seeded-recursive-np-iter1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iproskurina/qwen-hf-r100-seeded-recursive-np-iter1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iproskurina/qwen-hf-r100-seeded-recursive-np-iter1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/iproskurina/qwen-hf-r100-seeded-recursive-np-iter1

SGLang

How to use iproskurina/qwen-hf-r100-seeded-recursive-np-iter1 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 "iproskurina/qwen-hf-r100-seeded-recursive-np-iter1" \
    --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": "iproskurina/qwen-hf-r100-seeded-recursive-np-iter1",
		"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 "iproskurina/qwen-hf-r100-seeded-recursive-np-iter1" \
        --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": "iproskurina/qwen-hf-r100-seeded-recursive-np-iter1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use iproskurina/qwen-hf-r100-seeded-recursive-np-iter1 with Docker Model Runner:
```
docker model run hf.co/iproskurina/qwen-hf-r100-seeded-recursive-np-iter1
```

qwen-hf-r100-seeded-recursive-np-iter1 / trainer_log.jsonl

iproskurina

Upload folder using huggingface_hub

4e4f7de verified 14 days ago

Raw

History Blame Contribute Delete

1.69 kB

	{"current_steps": 100, "total_steps": 814, "loss": 2.0775, "lr": 4.9933489107396326e-05, "epoch": 0.12298232129131437, "percentage": 12.29, "elapsed_time": "0:04:29", "remaining_time": "0:32:00"}
	{"current_steps": 200, "total_steps": 814, "loss": 2.2188, "lr": 4.6913866856909926e-05, "epoch": 0.24596464258262873, "percentage": 24.57, "elapsed_time": "0:08:58", "remaining_time": "0:27:33"}
	{"current_steps": 300, "total_steps": 814, "loss": 2.2347, "lr": 3.991940046522724e-05, "epoch": 0.3689469638739431, "percentage": 36.86, "elapsed_time": "0:13:27", "remaining_time": "0:23:03"}
	{"current_steps": 400, "total_steps": 814, "loss": 2.2132, "lr": 3.0218780389368545e-05, "epoch": 0.49192928516525747, "percentage": 49.14, "elapsed_time": "0:17:55", "remaining_time": "0:18:32"}
	{"current_steps": 500, "total_steps": 814, "loss": 2.1841, "lr": 1.9571552451450542e-05, "epoch": 0.6149116064565718, "percentage": 61.43, "elapsed_time": "0:22:24", "remaining_time": "0:14:04"}
	{"current_steps": 600, "total_steps": 814, "loss": 2.15, "lr": 9.908962828396607e-06, "epoch": 0.7378939277478862, "percentage": 73.71, "elapsed_time": "0:26:53", "remaining_time": "0:09:35"}
	{"current_steps": 700, "total_steps": 814, "loss": 2.1234, "lr": 2.98365919315127e-06, "epoch": 0.8608762490392006, "percentage": 86.0, "elapsed_time": "0:31:22", "remaining_time": "0:05:06"}
	{"current_steps": 800, "total_steps": 814, "loss": 2.0872, "lr": 5.178692436005883e-08, "epoch": 0.9838585703305149, "percentage": 98.28, "elapsed_time": "0:35:50", "remaining_time": "0:00:37"}
	{"current_steps": 814, "total_steps": 814, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:36:43", "remaining_time": "0:00:00"}