Instructions to use modrill/nothink_8b_100k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modrill/nothink_8b_100k with Transformers:

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

pipe = pipeline("text-generation", model="modrill/nothink_8b_100k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("modrill/nothink_8b_100k")
model = AutoModelForCausalLM.from_pretrained("modrill/nothink_8b_100k")
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 modrill/nothink_8b_100k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modrill/nothink_8b_100k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modrill/nothink_8b_100k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/modrill/nothink_8b_100k

SGLang

How to use modrill/nothink_8b_100k 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 "modrill/nothink_8b_100k" \
    --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": "modrill/nothink_8b_100k",
		"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 "modrill/nothink_8b_100k" \
        --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": "modrill/nothink_8b_100k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use modrill/nothink_8b_100k with Docker Model Runner:
```
docker model run hf.co/modrill/nothink_8b_100k
```

nothink_8b_100k / trainer_log.jsonl

modrill

Upload folder using huggingface_hub

038c25d verified 21 days ago

Raw

History Blame Contribute Delete

1.17 kB

	{"current_steps": 10, "total_steps": 3126, "loss": 0.5239128112792969, "lr": 1.9148936170212767e-06, "epoch": 0.0064, "percentage": 0.32, "elapsed_time": "0:02:29", "remaining_time": "12:55:50"}
	{"current_steps": 20, "total_steps": 3126, "loss": 0.45125980377197267, "lr": 4.042553191489362e-06, "epoch": 0.0128, "percentage": 0.64, "elapsed_time": "0:04:55", "remaining_time": "12:43:42"}
	{"current_steps": 30, "total_steps": 3126, "loss": 0.426483154296875, "lr": 6.170212765957447e-06, "epoch": 0.0192, "percentage": 0.96, "elapsed_time": "0:07:21", "remaining_time": "12:39:41"}
	{"current_steps": 40, "total_steps": 3126, "loss": 0.38501999378204343, "lr": 8.297872340425532e-06, "epoch": 0.0256, "percentage": 1.28, "elapsed_time": "0:09:49", "remaining_time": "12:38:25"}
	{"current_steps": 50, "total_steps": 3126, "loss": 0.37038569450378417, "lr": 1.0425531914893619e-05, "epoch": 0.032, "percentage": 1.6, "elapsed_time": "0:12:15", "remaining_time": "12:33:41"}
	{"current_steps": 60, "total_steps": 3126, "loss": 0.3537989377975464, "lr": 1.2553191489361702e-05, "epoch": 0.0384, "percentage": 1.92, "elapsed_time": "0:14:42", "remaining_time": "12:31:57"}