Instructions to use chhao/Weak-Driven-Learning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chhao/Weak-Driven-Learning with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chhao/Weak-Driven-Learning")
model = AutoModelForCausalLM.from_pretrained("chhao/Weak-Driven-Learning")
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 chhao/Weak-Driven-Learning with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/chhao/Weak-Driven-Learning

SGLang

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

Docker Model Runner
How to use chhao/Weak-Driven-Learning with Docker Model Runner:
```
docker model run hf.co/chhao/Weak-Driven-Learning
```

Weak-Driven-Learning

File size: 2,979 Bytes

8d84170

{
  "_name_or_path": "weights/llmboost/Qwen3-4B-Base/stage2_m2/checkpoint-436",
  "add_cross_attention": false,
  "architectures": [
    "Qwen3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bad_words_ids": null,
  "begin_suppress_tokens": null,
  "bos_token_id": null,
  "chunk_size_feed_forward": 0,
  "cross_attention_hidden_size": null,
  "decoder_start_token_id": null,
  "diversity_penalty": 0.0,
  "do_sample": false,
  "dtype": "bfloat16",
  "early_stopping": false,
  "encoder_no_repeat_ngram_size": 0,
  "eos_token_id": 151643,
  "exponential_decay_length_penalty": null,
  "finetuning_task": null,
  "forced_bos_token_id": null,
  "forced_eos_token_id": null,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2560,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "initializer_range": 0.02,
  "intermediate_size": 9728,
  "is_decoder": false,
  "is_encoder_decoder": false,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "length_penalty": 1.0,
  "max_length": 20,
  "max_position_embeddings": 32768,
  "max_window_layers": 36,
  "min_length": 0,
  "model_type": "qwen3",
  "no_repeat_ngram_size": 0,
  "num_attention_heads": 32,
  "num_beam_groups": 1,
  "num_beams": 1,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "num_return_sequences": 1,
  "output_attentions": false,
  "output_hidden_states": false,
  "output_scores": false,
  "pad_token_id": 151643,
  "prefix": null,
  "problem_type": null,
  "pruned_heads": {},
  "remove_invalid_values": false,
  "repetition_penalty": 1.0,
  "return_dict": true,
  "return_dict_in_generate": false,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sep_token_id": null,
  "sliding_window": null,
  "suppress_tokens": null,
  "task_specific_params": null,
  "temperature": 1.0,
  "tf_legacy_loss": false,
  "tie_encoder_decoder": false,
  "tie_word_embeddings": true,
  "tokenizer_class": null,
  "top_k": 50,
  "top_p": 1.0,
  "torchscript": false,
  "transformers_version": "4.57.1",
  "typical_p": 1.0,
  "use_bfloat16": false,
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}