Instructions to use Dev-the-dev91/syllabus-extractor-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dev-the-dev91/syllabus-extractor-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "Dev-the-dev91/syllabus-extractor-lora")

Transformers

How to use Dev-the-dev91/syllabus-extractor-lora with Transformers:

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

pipe = pipeline("text-generation", model="Dev-the-dev91/syllabus-extractor-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Dev-the-dev91/syllabus-extractor-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dev-the-dev91/syllabus-extractor-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dev-the-dev91/syllabus-extractor-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dev-the-dev91/syllabus-extractor-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dev-the-dev91/syllabus-extractor-lora

SGLang

How to use Dev-the-dev91/syllabus-extractor-lora 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 "Dev-the-dev91/syllabus-extractor-lora" \
    --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": "Dev-the-dev91/syllabus-extractor-lora",
		"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 "Dev-the-dev91/syllabus-extractor-lora" \
        --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": "Dev-the-dev91/syllabus-extractor-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Dev-the-dev91/syllabus-extractor-lora with Docker Model Runner:
```
docker model run hf.co/Dev-the-dev91/syllabus-extractor-lora
```

syllabus-extractor-lora / checkpoint-33 /trainer_state.json

Dev-the-dev91

LoRA adapter from HF Jobs syllabus SFT

26aa50d verified about 1 month ago

Raw

History Blame Contribute Delete

1.96 kB

Invalid JSON:Unexpected token 'N', ..."al_loss": NaN, "... is not valid JSON

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 3.0,
	"eval_steps": 100,
	"global_step": 33,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"entropy": 0.17733469381928443,
	"epoch": 0.9876543209876543,
	"grad_norm": 1.6561490297317505,
	"learning_rate": 7.500000000000001e-05,
	"loss": 19.02234802246094,
	"mean_token_accuracy": 0.09697876162827015,
	"num_tokens": 162113.0,
	"step": 10
	},
	{
	"entropy": 0.1562326379018287,
	"epoch": 1.8888888888888888,
	"grad_norm": 0.4980040490627289,
	"learning_rate": 4.375e-05,
	"loss": 12.02085189819336,
	"mean_token_accuracy": 0.09252177444222855,
	"num_tokens": 309890.0,
	"step": 20
	},
	{
	"entropy": 0.21534234203704417,
	"epoch": 2.7901234567901234,
	"grad_norm": 0.6889352202415466,
	"learning_rate": 1.25e-05,
	"loss": 1.2283188819885253,
	"mean_token_accuracy": 0.0909152039109844,
	"num_tokens": 458756.0,
	"step": 30
	},
	{
	"epoch": 3.0,
	"eval_entropy": 0.09051553408304851,
	"eval_loss": NaN,
	"eval_mean_token_accuracy": 0.0862596763504876,
	"eval_num_tokens": 492483.0,
	"eval_runtime": 10.3363,
	"eval_samples_per_second": 0.871,
	"eval_steps_per_second": 0.871,
	"step": 33
	}
	],
	"logging_steps": 10,
	"max_steps": 33,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 3,
	"save_steps": 100,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": true
	},
	"attributes": {}
	}
	},
	"total_flos": 1060747676575488.0,
	"train_batch_size": 1,
	"trial_name": null,
	"trial_params": null
	}