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

Libraries

How to use lukehg/dev with Transformers:

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

pipe = pipeline("text-generation", model="lukehg/dev")
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("lukehg/dev")
model = AutoModelForCausalLM.from_pretrained("lukehg/dev", 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 lukehg/dev with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lukehg/dev

SGLang

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

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

dev / trainer_state.json

lukehg

Model save

5a4e161 verified over 1 year ago

Raw History Blame

1.37 kB

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002488722974023954,
  "eval_steps": 500,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 389.40849685668945,
      "epoch": 0.002488722974023954,
      "grad_norm": 0.11305962966298544,
      "kl": 0.0,
      "learning_rate": 0.0,
      "loss": -0.0,
      "reward": 0.5111607313156128,
      "reward_std": 0.5251041390001774,
      "rewards/correctness": 0.04464285960420966,
      "rewards/format": 0.466517873108387,
      "step": 2
    },
    {
      "epoch": 0.002488722974023954,
      "step": 2,
      "total_flos": 0.0,
      "train_loss": -2.6609217051998257e-09,
      "train_runtime": 213.9149,
      "train_samples_per_second": 0.262,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 2,
  "max_steps": 1,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}

	{
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 0.002488722974023954,
	"eval_steps": 500,
	"global_step": 2,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"completion_length": 389.40849685668945,
	"epoch": 0.002488722974023954,
	"grad_norm": 0.11305962966298544,
	"kl": 0.0,
	"learning_rate": 0.0,
	"loss": -0.0,
	"reward": 0.5111607313156128,
	"reward_std": 0.5251041390001774,
	"rewards/correctness": 0.04464285960420966,
	"rewards/format": 0.466517873108387,
	"step": 2
	},
	{
	"epoch": 0.002488722974023954,
	"step": 2,
	"total_flos": 0.0,
	"train_loss": -2.6609217051998257e-09,
	"train_runtime": 213.9149,
	"train_samples_per_second": 0.262,
	"train_steps_per_second": 0.005
	}
	],
	"logging_steps": 2,
	"max_steps": 1,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 1,
	"save_steps": 25,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": true
	},
	"attributes": {}
	}
	},
	"total_flos": 0.0,
	"train_batch_size": 1,
	"trial_name": null,
	"trial_params": null
	}