Instructions to use wasmdashai/asg-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wasmdashai/asg-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="wasmdashai/asg-v1", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("wasmdashai/asg-v1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use wasmdashai/asg-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "wasmdashai/asg-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wasmdashai/asg-v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/wasmdashai/asg-v1
- SGLang
How to use wasmdashai/asg-v1 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 "wasmdashai/asg-v1" \ --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": "wasmdashai/asg-v1", "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 "wasmdashai/asg-v1" \ --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": "wasmdashai/asg-v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use wasmdashai/asg-v1 with Docker Model Runner:
docker model run hf.co/wasmdashai/asg-v1
| { | |
| "architectures": [ | |
| "ASGTransformerForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_asg_transformer.ASGTransformerConfig", | |
| "AutoModelForCausalLM": "modeling_asg_transformer.ASGTransformerForCausalLM" | |
| }, | |
| "base_model_config": { | |
| "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "chunk_size_feed_forward": 0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 896, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4864, | |
| "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" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 21, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 14, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "pad_token_id": null, | |
| "problem_type": null, | |
| "return_dict": true, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.13.1", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "bos_token_id": null, | |
| "dtype": "bfloat16", | |
| "duration_bins": [ | |
| 15, | |
| 30, | |
| 45, | |
| 60, | |
| 90, | |
| 120, | |
| 180, | |
| 240 | |
| ], | |
| "duration_loss_weight": 0.1, | |
| "eos_token_id": 151645, | |
| "initializer_range": 0.02, | |
| "knowledge_file": "knowledge/catalog.json", | |
| "knowledge_top_k": 8, | |
| "max_knowledge_chars": 6000, | |
| "model_type": "asg_transformer", | |
| "num_scenario_labels": 8, | |
| "pad_token_id": 151643, | |
| "prompt_template_file": "knowledge/prompt_template.txt", | |
| "scenario_labels": [ | |
| "awareness", | |
| "initial_access", | |
| "credential_protection", | |
| "lateral_movement_detection", | |
| "persistence_detection", | |
| "incident_response", | |
| "recovery", | |
| "executive_tabletop" | |
| ], | |
| "scenario_loss_weight": 0.1, | |
| "semantic_loss_weight": 0.1, | |
| "semantic_projection_dim": 384, | |
| "transformers_version": "5.13.1", | |
| "vocab_size": 151665 | |
| } | |