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

Libraries

How to use mlfoundations-dev/difficulty_sorting_easy_seed_code with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlfoundations-dev/difficulty_sorting_easy_seed_code")
model = AutoModelForCausalLM.from_pretrained("mlfoundations-dev/difficulty_sorting_easy_seed_code")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mlfoundations-dev/difficulty_sorting_easy_seed_code with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mlfoundations-dev/difficulty_sorting_easy_seed_code

SGLang

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

Docker Model Runner
How to use mlfoundations-dev/difficulty_sorting_easy_seed_code with Docker Model Runner:
```
docker model run hf.co/mlfoundations-dev/difficulty_sorting_easy_seed_code
```

difficulty_sorting_easy_seed_code / trainer_log.jsonl

sedrickkeh

Training in progress, epoch 2

b64f213 verified over 1 year ago

raw

history blame

5.84 kB

	{"current_steps": 1, "total_steps": 30, "loss": 1.1951, "lr": 3.3333333333333333e-06, "epoch": 0.09523809523809523, "percentage": 3.33, "elapsed_time": "0:00:28", "remaining_time": "0:13:53"}
	{"current_steps": 2, "total_steps": 30, "loss": 1.2188, "lr": 6.666666666666667e-06, "epoch": 0.19047619047619047, "percentage": 6.67, "elapsed_time": "0:00:45", "remaining_time": "0:10:43"}
	{"current_steps": 3, "total_steps": 30, "loss": 1.1466, "lr": 1e-05, "epoch": 0.2857142857142857, "percentage": 10.0, "elapsed_time": "0:01:05", "remaining_time": "0:09:50"}
	{"current_steps": 4, "total_steps": 30, "loss": 1.0925, "lr": 9.966191788709716e-06, "epoch": 0.38095238095238093, "percentage": 13.33, "elapsed_time": "0:01:25", "remaining_time": "0:09:15"}
	{"current_steps": 5, "total_steps": 30, "loss": 1.0697, "lr": 9.86522435289912e-06, "epoch": 0.47619047619047616, "percentage": 16.67, "elapsed_time": "0:01:45", "remaining_time": "0:08:47"}
	{"current_steps": 6, "total_steps": 30, "loss": 1.0761, "lr": 9.698463103929542e-06, "epoch": 0.5714285714285714, "percentage": 20.0, "elapsed_time": "0:02:05", "remaining_time": "0:08:23"}
	{"current_steps": 7, "total_steps": 30, "loss": 1.0359, "lr": 9.468163201617063e-06, "epoch": 0.6666666666666666, "percentage": 23.33, "elapsed_time": "0:02:23", "remaining_time": "0:07:52"}
	{"current_steps": 8, "total_steps": 30, "loss": 0.9778, "lr": 9.177439057064684e-06, "epoch": 0.7619047619047619, "percentage": 26.67, "elapsed_time": "0:02:41", "remaining_time": "0:07:23"}
	{"current_steps": 9, "total_steps": 30, "loss": 0.9634, "lr": 8.83022221559489e-06, "epoch": 0.8571428571428571, "percentage": 30.0, "elapsed_time": "0:03:01", "remaining_time": "0:07:02"}
	{"current_steps": 10, "total_steps": 30, "loss": 0.9079, "lr": 8.43120818934367e-06, "epoch": 0.9523809523809523, "percentage": 33.33, "elapsed_time": "0:03:19", "remaining_time": "0:06:38"}
	{"current_steps": 11, "total_steps": 30, "loss": 1.3387, "lr": 7.985792958513932e-06, "epoch": 1.0476190476190477, "percentage": 36.67, "elapsed_time": "0:04:25", "remaining_time": "0:07:38"}
	{"current_steps": 12, "total_steps": 30, "loss": 0.9057, "lr": 7.500000000000001e-06, "epoch": 1.1428571428571428, "percentage": 40.0, "elapsed_time": "0:04:44", "remaining_time": "0:07:06"}
	{"current_steps": 13, "total_steps": 30, "loss": 0.8104, "lr": 6.980398830195785e-06, "epoch": 1.2380952380952381, "percentage": 43.33, "elapsed_time": "0:05:00", "remaining_time": "0:06:32"}
	{"current_steps": 14, "total_steps": 30, "loss": 0.8269, "lr": 6.434016163555452e-06, "epoch": 1.3333333333333333, "percentage": 46.67, "elapsed_time": "0:05:15", "remaining_time": "0:06:00"}
	{"current_steps": 15, "total_steps": 30, "loss": 0.9437, "lr": 5.8682408883346535e-06, "epoch": 1.4285714285714286, "percentage": 50.0, "elapsed_time": "0:05:36", "remaining_time": "0:05:36"}
	{"current_steps": 16, "total_steps": 30, "loss": 0.8208, "lr": 5.290724144552379e-06, "epoch": 1.5238095238095237, "percentage": 53.33, "elapsed_time": "0:05:53", "remaining_time": "0:05:09"}
	{"current_steps": 17, "total_steps": 30, "loss": 0.8353, "lr": 4.7092758554476215e-06, "epoch": 1.619047619047619, "percentage": 56.67, "elapsed_time": "0:06:14", "remaining_time": "0:04:46"}
	{"current_steps": 18, "total_steps": 30, "loss": 0.8716, "lr": 4.131759111665349e-06, "epoch": 1.7142857142857144, "percentage": 60.0, "elapsed_time": "0:06:39", "remaining_time": "0:04:26"}
	{"current_steps": 19, "total_steps": 30, "loss": 0.7681, "lr": 3.5659838364445505e-06, "epoch": 1.8095238095238095, "percentage": 63.33, "elapsed_time": "0:06:58", "remaining_time": "0:04:02"}
	{"current_steps": 20, "total_steps": 30, "loss": 0.8329, "lr": 3.019601169804216e-06, "epoch": 1.9047619047619047, "percentage": 66.67, "elapsed_time": "0:07:20", "remaining_time": "0:03:40"}
	{"current_steps": 21, "total_steps": 30, "loss": 1.2754, "lr": 2.5000000000000015e-06, "epoch": 2.0, "percentage": 70.0, "elapsed_time": "0:07:37", "remaining_time": "0:03:16"}
	{"current_steps": 22, "total_steps": 30, "loss": 0.8055, "lr": 2.0142070414860704e-06, "epoch": 2.0952380952380953, "percentage": 73.33, "elapsed_time": "0:08:52", "remaining_time": "0:03:13"}
	{"current_steps": 23, "total_steps": 30, "loss": 0.8038, "lr": 1.5687918106563326e-06, "epoch": 2.1904761904761907, "percentage": 76.67, "elapsed_time": "0:09:10", "remaining_time": "0:02:47"}
	{"current_steps": 24, "total_steps": 30, "loss": 0.7889, "lr": 1.1697777844051105e-06, "epoch": 2.2857142857142856, "percentage": 80.0, "elapsed_time": "0:09:29", "remaining_time": "0:02:22"}
	{"current_steps": 25, "total_steps": 30, "loss": 0.8067, "lr": 8.225609429353187e-07, "epoch": 2.380952380952381, "percentage": 83.33, "elapsed_time": "0:09:46", "remaining_time": "0:01:57"}
	{"current_steps": 26, "total_steps": 30, "loss": 0.8279, "lr": 5.318367983829393e-07, "epoch": 2.4761904761904763, "percentage": 86.67, "elapsed_time": "0:10:06", "remaining_time": "0:01:33"}
	{"current_steps": 27, "total_steps": 30, "loss": 0.7699, "lr": 3.015368960704584e-07, "epoch": 2.571428571428571, "percentage": 90.0, "elapsed_time": "0:10:20", "remaining_time": "0:01:08"}
	{"current_steps": 28, "total_steps": 30, "loss": 0.7895, "lr": 1.3477564710088097e-07, "epoch": 2.6666666666666665, "percentage": 93.33, "elapsed_time": "0:10:42", "remaining_time": "0:00:45"}
	{"current_steps": 29, "total_steps": 30, "loss": 0.8391, "lr": 3.3808211290284886e-08, "epoch": 2.761904761904762, "percentage": 96.67, "elapsed_time": "0:11:01", "remaining_time": "0:00:22"}
	{"current_steps": 30, "total_steps": 30, "loss": 0.767, "lr": 0.0, "epoch": 2.857142857142857, "percentage": 100.0, "elapsed_time": "0:11:20", "remaining_time": "0:00:00"}
	{"current_steps": 30, "total_steps": 30, "epoch": 2.857142857142857, "percentage": 100.0, "elapsed_time": "0:13:04", "remaining_time": "0:00:00"}