Phi-4-mini-onnx-qnn-npu / model_config.json
lokinfey's picture
Upload folder using huggingface_hub
4d2a2bf verified
{
"type": "compositemodel",
"config": {
"model_path": "/dev_olive/cache/default_workflow/runs/19b7fc7d/models",
"model_component_names": [
"embeddings",
"context_ctx",
"iterator_ctx",
"lm_head"
],
"model_attributes": {
"vocab_size": 200064,
"hidden_size": 3072,
"intermediate_size": 8192,
"num_hidden_layers": 32,
"num_attention_heads": 24,
"num_key_value_heads": 8,
"resid_pdrop": 0.0,
"embd_pdrop": 0.0,
"attention_dropout": 0.0,
"hidden_act": "silu",
"max_position_embeddings": 131072,
"original_max_position_embeddings": 4096,
"initializer_range": 0.02,
"rms_norm_eps": 1e-05,
"use_cache": true,
"rope_theta": 10000.0,
"rope_scaling": {
"long_factor": [
1,
1.118320672,
1.250641126,
1.398617824,
1.564103225,
1.74916897,
1.956131817,
2.187582649,
2.446418898,
2.735880826,
3.059592084,
3.421605075,
3.826451687,
4.279200023,
4.785517845,
5.351743533,
5.984965424,
6.693110555,
7.485043894,
8.370679318,
9.36110372,
10.4687158,
11.70738129,
13.09260651,
14.64173252,
16.37415215,
18.31155283,
20.47818807,
22.90118105,
25.61086418,
28.64115884,
32.03,
32.1,
32.13,
32.23,
32.6,
32.61,
32.64,
32.66,
32.7,
32.71,
32.93,
32.97,
33.28,
33.49,
33.5,
44.16,
47.77
],
"short_factor": [
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0
],
"type": "longrope"
},
"partial_rotary_factor": 0.75,
"sliding_window": 262144,
"return_dict": true,
"output_hidden_states": false,
"torchscript": false,
"torch_dtype": "bfloat16",
"use_bfloat16": false,
"tf_legacy_loss": false,
"pruned_heads": {},
"tie_word_embeddings": false,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"architectures": [
"Phi3ForCausalLM"
],
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"tokenizer_class": null,
"prefix": null,
"bos_token_id": 199999,
"pad_token_id": 199999,
"eos_token_id": 199999,
"sep_token_id": null,
"decoder_start_token_id": null,
"task_specific_params": null,
"problem_type": null,
"_name_or_path": "/dev_olive/cache/default_workflow/runs/92019462/models",
"transformers_version": "4.53.1",
"attention_bias": false,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
"AutoTokenizer": "Xenova/gpt-4o"
},
"full_attn_mod": 1,
"interpolate_factor": 1,
"lm_head_bias": false,
"mlp_bias": false,
"model_type": "phi3",
"quantization_config": {
"bits": 4,
"damp_percent": 0.01,
"desc_act": true,
"group_size": -1,
"is_marlin_format": false,
"model_file_base_name": "model",
"model_name_or_path": null,
"quant_method": "gptq",
"static_groups": false,
"sym": true,
"true_sequential": false,
"use_exllama": false
},
"output_attentions": false,
"split_assignments": {
"model.embed_tokens": 0,
"model.layers.0": 1,
"model.layers.1": 1,
"model.layers.2": 1,
"model.layers.3": 1,
"model.layers.4": 1,
"model.layers.5": 1,
"model.layers.6": 1,
"model.layers.7": 1,
"model.layers.8": 2,
"model.layers.9": 2,
"model.layers.10": 2,
"model.layers.11": 2,
"model.layers.12": 2,
"model.layers.13": 2,
"model.layers.14": 2,
"model.layers.15": 2,
"model.layers.16": 3,
"model.layers.17": 3,
"model.layers.18": 3,
"model.layers.19": 3,
"model.layers.20": 3,
"model.layers.21": 3,
"model.layers.22": 3,
"model.layers.23": 3,
"model.layers.24": 4,
"model.layers.25": 4,
"model.layers.26": 4,
"model.layers.27": 4,
"model.layers.28": 4,
"model.layers.29": 4,
"model.layers.30": 4,
"model.layers.31": 4,
"lm_head": 5
},
"additional_files": [
"/dev_olive/models/phi4-qnn/model/added_tokens.json",
"/dev_olive/models/phi4-qnn/model/chat_template.jinja",
"/dev_olive/models/phi4-qnn/model/config.json",
"/dev_olive/models/phi4-qnn/model/configuration_phi3.py",
"/dev_olive/models/phi4-qnn/model/genai_config.json",
"/dev_olive/models/phi4-qnn/model/generation_config.json",
"/dev_olive/models/phi4-qnn/model/merges.txt",
"/dev_olive/models/phi4-qnn/model/modeling_phi3.py",
"/dev_olive/models/phi4-qnn/model/special_tokens_map.json",
"/dev_olive/models/phi4-qnn/model/tokenizer.json",
"/dev_olive/models/phi4-qnn/model/tokenizer_config.json",
"/dev_olive/models/phi4-qnn/model/vocab.json"
],
"llm_pipeline": {
"embeddings": "embeddings",
"context": [
"context_ctx"
],
"iterator": [
"iterator_ctx"
],
"lm_head": "lm_head"
}
},
"model_components": [
{
"type": "onnxmodel",
"config": {
"model_path": "/dev_olive/models/phi4-qnn/model",
"onnx_file_name": "embeddings.onnx",
"inference_settings": null,
"use_ort_extensions": false,
"external_initializers_file_name": null,
"constant_inputs_file_name": null,
"model_attributes": {
"additional_files": [
"/dev_olive/cache/default_workflow/runs/952a3079/models/added_tokens.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/chat_template.jinja",
"/dev_olive/cache/default_workflow/runs/952a3079/models/config.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/configuration_phi3.py",
"/dev_olive/cache/default_workflow/runs/952a3079/models/generation_config.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/merges.txt",
"/dev_olive/cache/default_workflow/runs/952a3079/models/modeling_phi3.py",
"/dev_olive/cache/default_workflow/runs/952a3079/models/special_tokens_map.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/tokenizer.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/tokenizer_config.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/vocab.json",
"/dev_olive/cache/default_workflow/runs/19b7fc7d/models/genai_config.json"
]
}
}
},
{
"type": "onnxmodel",
"config": {
"model_path": "/dev_olive/models/phi4-qnn/model",
"onnx_file_name": "context_ctx.onnx",
"inference_settings": null,
"use_ort_extensions": false,
"external_initializers_file_name": null,
"constant_inputs_file_name": null,
"model_attributes": {
"additional_files": [
"/dev_olive/cache/default_workflow/runs/952a3079/models/added_tokens.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/chat_template.jinja",
"/dev_olive/cache/default_workflow/runs/952a3079/models/config.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/configuration_phi3.py",
"/dev_olive/cache/default_workflow/runs/952a3079/models/generation_config.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/merges.txt",
"/dev_olive/cache/default_workflow/runs/952a3079/models/modeling_phi3.py",
"/dev_olive/cache/default_workflow/runs/952a3079/models/special_tokens_map.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/tokenizer.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/tokenizer_config.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/vocab.json",
"/dev_olive/cache/default_workflow/runs/19b7fc7d/models/genai_config.json"
]
}
}
},
{
"type": "onnxmodel",
"config": {
"model_path": "/dev_olive/models/phi4-qnn/model",
"onnx_file_name": "iterator_ctx.onnx",
"inference_settings": null,
"use_ort_extensions": false,
"external_initializers_file_name": null,
"constant_inputs_file_name": null,
"model_attributes": {
"additional_files": [
"/dev_olive/cache/default_workflow/runs/952a3079/models/added_tokens.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/chat_template.jinja",
"/dev_olive/cache/default_workflow/runs/952a3079/models/config.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/configuration_phi3.py",
"/dev_olive/cache/default_workflow/runs/952a3079/models/generation_config.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/merges.txt",
"/dev_olive/cache/default_workflow/runs/952a3079/models/modeling_phi3.py",
"/dev_olive/cache/default_workflow/runs/952a3079/models/special_tokens_map.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/tokenizer.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/tokenizer_config.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/vocab.json",
"/dev_olive/cache/default_workflow/runs/19b7fc7d/models/genai_config.json"
]
}
}
},
{
"type": "onnxmodel",
"config": {
"model_path": "/dev_olive/models/phi4-qnn/model",
"onnx_file_name": "lm_head.onnx",
"inference_settings": null,
"use_ort_extensions": false,
"external_initializers_file_name": null,
"constant_inputs_file_name": null,
"model_attributes": {
"additional_files": [
"/dev_olive/cache/default_workflow/runs/952a3079/models/added_tokens.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/chat_template.jinja",
"/dev_olive/cache/default_workflow/runs/952a3079/models/config.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/configuration_phi3.py",
"/dev_olive/cache/default_workflow/runs/952a3079/models/generation_config.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/merges.txt",
"/dev_olive/cache/default_workflow/runs/952a3079/models/modeling_phi3.py",
"/dev_olive/cache/default_workflow/runs/952a3079/models/special_tokens_map.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/tokenizer.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/tokenizer_config.json",
"/dev_olive/cache/default_workflow/runs/952a3079/models/vocab.json",
"/dev_olive/cache/default_workflow/runs/19b7fc7d/models/genai_config.json"
]
}
}
}
]
}
}