| """ |
| Test script for GptOssDense model with trust_remote_code=True |
| """ |
| from transformers import AutoConfig, AutoModelForCausalLM |
| import torch |
|
|
| |
| print("=" * 60) |
| print("Test 1: Loading config from Hub") |
| print("=" * 60) |
| config = AutoConfig.from_pretrained( |
| 'marksverdhei/gpt-oss-dense', |
| trust_remote_code=True |
| ) |
| print(f"✓ Config loaded: {type(config).__name__}") |
| print(f" Model type: {config.model_type}") |
| print(f" Hidden size: {config.hidden_size}") |
| print(f" Num layers: {config.num_hidden_layers}") |
| print(f" Intermediate size: {config.intermediate_size}") |
| print(f" Num attention heads: {config.num_attention_heads}") |
|
|
| |
| print("\n" + "=" * 60) |
| print("Test 2: Initializing model from config") |
| print("=" * 60) |
| model = AutoModelForCausalLM.from_config( |
| config, |
| trust_remote_code=True |
| ) |
| print(f"✓ Model initialized: {type(model).__name__}") |
|
|
| |
| print("\n" + "=" * 60) |
| print("Test 3: Verifying MLP structure (Dense, not MoE)") |
| print("=" * 60) |
| mlp = model.model.layers[0].mlp |
| print(f"MLP type: {type(mlp).__name__}") |
| print(f" Has router: {hasattr(mlp, 'router')}") |
| print(f" Has experts: {hasattr(mlp, 'experts')}") |
| print(f" Has gate_up_proj: {hasattr(mlp, 'gate_up_proj')}") |
| print(f" Has down_proj: {hasattr(mlp, 'down_proj')}") |
| print(f" Alpha (GLU): {mlp.alpha}") |
| print(f" Limit (clamping): {mlp.limit}") |
|
|
| |
| print("\n" + "=" * 60) |
| print("Test 4: Running forward pass") |
| print("=" * 60) |
| input_ids = torch.randint(0, config.vocab_size, (2, 16)) |
| model.eval() |
| with torch.no_grad(): |
| outputs = model(input_ids) |
| print(f"✓ Forward pass successful") |
| print(f" Input shape: {input_ids.shape}") |
| print(f" Output shape: {outputs.logits.shape}") |
|
|
| |
| print("\n" + "=" * 60) |
| print("Test 5: Model parameters") |
| print("=" * 60) |
| total_params = sum(p.numel() for p in model.parameters()) |
| print(f"Total parameters: {total_params:,}") |
|
|
| print("\n" + "=" * 60) |
| print("✅ All tests passed!") |
| print("=" * 60) |
| print("\nTo save the model weights:") |
| print(" model.save_pretrained('/path/to/save')") |
| print(" # Then upload to Hub with: huggingface-cli upload marksverdhei/gpt-oss-dense /path/to/save") |
|
|
