Instructions to use sofyanwaldy/SmolLM2-360M-Instruct-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sofyanwaldy/SmolLM2-360M-Instruct-finetuned with Transformers:

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

pipe = pipeline("text-generation", model="sofyanwaldy/SmolLM2-360M-Instruct-finetuned")
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("sofyanwaldy/SmolLM2-360M-Instruct-finetuned")
model = AutoModelForCausalLM.from_pretrained("sofyanwaldy/SmolLM2-360M-Instruct-finetuned", 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 sofyanwaldy/SmolLM2-360M-Instruct-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sofyanwaldy/SmolLM2-360M-Instruct-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sofyanwaldy/SmolLM2-360M-Instruct-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sofyanwaldy/SmolLM2-360M-Instruct-finetuned

SGLang

How to use sofyanwaldy/SmolLM2-360M-Instruct-finetuned 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 "sofyanwaldy/SmolLM2-360M-Instruct-finetuned" \
    --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": "sofyanwaldy/SmolLM2-360M-Instruct-finetuned",
		"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 "sofyanwaldy/SmolLM2-360M-Instruct-finetuned" \
        --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": "sofyanwaldy/SmolLM2-360M-Instruct-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sofyanwaldy/SmolLM2-360M-Instruct-finetuned with Docker Model Runner:
```
docker model run hf.co/sofyanwaldy/SmolLM2-360M-Instruct-finetuned
```

SmolLM2-360M-Instruct-finetuned / trainer_state.json

sofyanwaldy

Model save

58200e3 verified almost 2 years ago

Raw History Blame Contribute Delete

1.56 kB

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 9.421496391296387,
      "eval_runtime": 0.858,
      "eval_samples_per_second": 2.331,
      "eval_steps_per_second": 2.331,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_loss": 6.097255706787109,
      "eval_runtime": 0.8528,
      "eval_samples_per_second": 2.345,
      "eval_steps_per_second": 2.345,
      "step": 2
    },
    {
      "epoch": 3.0,
      "eval_loss": 4.5291948318481445,
      "eval_runtime": 0.7724,
      "eval_samples_per_second": 2.589,
      "eval_steps_per_second": 2.589,
      "step": 3
    },
    {
      "epoch": 3.0,
      "step": 3,
      "total_flos": 17398068019200.0,
      "train_loss": 10.406506856282553,
      "train_runtime": 53.0496,
      "train_samples_per_second": 0.339,
      "train_steps_per_second": 0.057
    }
  ],
  "logging_steps": 500,
  "max_steps": 3,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 17398068019200.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}

	{
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 3.0,
	"eval_steps": 500,
	"global_step": 3,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 1.0,
	"eval_loss": 9.421496391296387,
	"eval_runtime": 0.858,
	"eval_samples_per_second": 2.331,
	"eval_steps_per_second": 2.331,
	"step": 1
	},
	{
	"epoch": 2.0,
	"eval_loss": 6.097255706787109,
	"eval_runtime": 0.8528,
	"eval_samples_per_second": 2.345,
	"eval_steps_per_second": 2.345,
	"step": 2
	},
	{
	"epoch": 3.0,
	"eval_loss": 4.5291948318481445,
	"eval_runtime": 0.7724,
	"eval_samples_per_second": 2.589,
	"eval_steps_per_second": 2.589,
	"step": 3
	},
	{
	"epoch": 3.0,
	"step": 3,
	"total_flos": 17398068019200.0,
	"train_loss": 10.406506856282553,
	"train_runtime": 53.0496,
	"train_samples_per_second": 0.339,
	"train_steps_per_second": 0.057
	}
	],
	"logging_steps": 500,
	"max_steps": 3,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 3,
	"save_steps": 500,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": true
	},
	"attributes": {}
	}
	},
	"total_flos": 17398068019200.0,
	"train_batch_size": 1,
	"trial_name": null,
	"trial_params": null
	}