Files
ModelHub XC 83a5654de3 初始化项目,由ModelHub XC社区提供模型
Model: Apolo81/granite-4-350m-map-commands-gguf
Source: Original Platform
2026-05-08 17:12:19 +08:00

132 lines
3.1 KiB
JSON

{
"vocab_size": 100352,
"max_position_embeddings": 32768,
"hidden_size": 1024,
"intermediate_size": 2048,
"num_hidden_layers": 28,
"num_attention_heads": 16,
"num_key_value_heads": 4,
"hidden_act": "silu",
"initializer_range": 0.1,
"rms_norm_eps": 1e-05,
"use_cache": true,
"rope_theta": 10000000,
"rope_scaling": null,
"attention_bias": false,
"embedding_multiplier": 12,
"logits_scaling": 4,
"residual_multiplier": 0.263,
"attention_multiplier": 0.015625,
"attention_dropout": 0.0,
"num_local_experts": 0,
"num_experts_per_tok": 0,
"output_router_logits": false,
"router_aux_loss_coef": 0.01,
"shared_intermediate_size": 2048,
"position_embedding_type": "rope",
"mamba_n_heads": 128,
"mamba_d_head": 16,
"mamba_n_groups": 1,
"mamba_d_state": 256,
"mamba_d_conv": 4,
"mamba_chunk_size": 256,
"mamba_conv_bias": true,
"mamba_proj_bias": false,
"mamba_expand": 2,
"layer_types": [
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention",
"attention"
],
"return_dict": true,
"output_hidden_states": false,
"torchscript": false,
"dtype": "float32",
"pruned_heads": {},
"tie_word_embeddings": true,
"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,
"architectures": [
"GraniteMoeHybridForCausalLM"
],
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"task_specific_params": null,
"problem_type": null,
"tokenizer_class": null,
"prefix": null,
"bos_token_id": 100257,
"pad_token_id": 100256,
"eos_token_id": 100257,
"sep_token_id": null,
"decoder_start_token_id": null,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"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,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"_name_or_path": "Apolo81/granite-4.0-h-350m-map-commands-fp16",
"transformers_version": "4.57.1",
"init_method": "mup",
"model_type": "granitemoehybrid",
"normalization_function": "rmsnorm",
"tf_legacy_loss": false,
"use_bfloat16": false,
"output_attentions": false
}