RedHatAI/phi-4-quantized.w8a8
54.3k
1{2 "_name_or_path": "microsoft/phi-4",3 "architectures": [4 "Phi3ForCausalLM"5 ],6 "attention_bias": false,7 "attention_dropout": 0.0,8 "bos_token_id": 100257,9 "embd_pdrop": 0.0,10 "eos_token_id": 100265,11 "hidden_act": "silu",12 "hidden_size": 5120,13 "initializer_range": 0.02,14 "intermediate_size": 17920,15 "max_position_embeddings": 16384,16 "model_type": "phi3",17 "num_attention_heads": 40,18 "num_hidden_layers": 40,19 "num_key_value_heads": 10,20 "original_max_position_embeddings": 16384,21 "pad_token_id": 100349,22 "partial_rotary_factor": 1.0,23 "quantization_config": {24 "config_groups": {25 "group_0": {26 "input_activations": {27 "actorder": null,28 "block_structure": null,29 "dynamic": true,30 "group_size": null,31 "num_bits": 8,32 "observer": null,33 "observer_kwargs": {},34 "strategy": "token",35 "symmetric": true,36 "type": "int"37 },38 "output_activations": null,39 "targets": [40 "Linear"41 ],42 "weights": {43 "actorder": null,44 "block_structure": null,45 "dynamic": false,46 "group_size": null,47 "num_bits": 8,48 "observer": "mse",49 "observer_kwargs": {},50 "strategy": "channel",51 "symmetric": true,52 "type": "int"53 }54 }55 },56 "format": "int-quantized",57 "global_compression_ratio": 1.2816636668151653,58 "ignore": [59 "lm_head"60 ],61 "kv_cache_scheme": null,62 "quant_method": "compressed-tensors",63 "quantization_status": "compressed"64 },65 "resid_pdrop": 0.0,66 "rms_norm_eps": 1e-05,67 "rope_scaling": null,68 "rope_theta": 250000,69 "sliding_window": null,70 "tie_word_embeddings": false,71 "torch_dtype": "bfloat16",72 "transformers_version": "4.49.0",73 "use_cache": true,74 "vocab_size": 10035275}