| { |
| "architectures": [ |
| "GptOssForCausalLM" |
| ], |
| "attention_bias": true, |
| "attention_dropout": 0.0, |
| "dtype": "bfloat16", |
| "eos_token_id": 200002, |
| "experts_per_token": 4, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 2880, |
| "initial_context_length": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 2880, |
| "layer_types": [ |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 131072, |
| "model_type": "gpt_oss", |
| "num_attention_heads": 64, |
| "num_experts_per_tok": 4, |
| "num_hidden_layers": 24, |
| "num_key_value_heads": 8, |
| "num_local_experts": 32, |
| "output_router_logits": false, |
| "pad_token_id": 199999, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "pack-quantized", |
| "input_activations": null, |
| "output_activations": null, |
| "targets": [ |
| "re:.*self_attn\\.(q_proj|k_proj|v_proj|o_proj)$" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "channel", |
| "symmetric": true, |
| "type": "int", |
| "zp_dtype": null |
| } |
| }, |
| "group_1": { |
| "format": "mxfp4-pack-quantized", |
| "input_activations": null, |
| "output_activations": null, |
| "targets": [ |
| "re:.*mlp\\.experts\\.experts\\.\\d+\\.(gate_proj|up_proj|down_proj)$" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 32, |
| "num_bits": 4, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": "torch.uint8", |
| "strategy": "group", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "mixed-precision", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.16.0" |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "beta_fast": 32.0, |
| "beta_slow": 1.0, |
| "factor": 32.0, |
| "original_max_position_embeddings": 4096, |
| "rope_theta": 150000, |
| "rope_type": "yarn", |
| "truncate": false |
| }, |
| "rope_scaling": { |
| "beta_fast": 32.0, |
| "beta_slow": 1.0, |
| "factor": 32.0, |
| "original_max_position_embeddings": 4096, |
| "rope_type": "yarn", |
| "truncate": false |
| }, |
| "rope_theta": 150000.0, |
| "router_aux_loss_coef": 0.9, |
| "sliding_window": 128, |
| "swiglu_limit": 7.0, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.57.6", |
| "use_cache": true, |
| "vocab_size": 201088 |
| } |
