YModel3.2-fm-1B / config.json
SnifferCaptain's picture
Upload ./config.json with huggingface_hub
154b42c verified
Raw History Blame Contribute Delete
2.42 kB
{
"return_dict": true,
"output_hidden_states": false,
"output_attentions": false,
"torchscript": false,
"torch_dtype": null,
"use_bfloat16": false,
"tf_legacy_loss": false,
"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,
"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": [
"YForCausalLM32"
],
"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": 151644,
"pad_token_id": 151643,
"eos_token_id": 151645,
"sep_token_id": null,
"decoder_start_token_id": null,
"task_specific_params": null,
"problem_type": null,
"_name_or_path": "",
"_commit_hash": null,
"_attn_implementation_internal": null,
"_attn_implementation_autoset": false,
"transformers_version": null,
"dropout": 0.0,
"hidden_size": 1024,
"num_hidden_layers": 31,
"max_position_embeddings": 8192,
"vocab_size": 151669,
"rms_norm_eps": 1e-06,
"rope_theta": 50000.0,
"rope_scaling": null,
"dtype": "bfloat16",
"intermediate_size": 3072,
"num_heads": 8,
"num_key_value_heads": 2,
"head_dim": 256,
"group_size": 8,
"group_size_options": [
8
],
"layer_pattern": "fgggggfgggggfgggggfgggggfgggggf",
"use_sengram": true,
"sengram_bucket_size": 16384,
"sengram_topk": 12,
"use_dcp": false,
"dynamic_compression_probe_hidden_size": 1024,
"model_type": "ynet32",
"auto_map": {
"AutoConfig": "modeling_ymodel32.YConfig32",
"AutoModelForCausalLM": "modeling_ymodel32.YForCausalLM32"
}
}