07cdfa23fd
Model: AmanPriyanshu/gpt-oss-13.7b-specialized-math-pruned-moe-only-20-experts Source: Original Platform
123 lines
2.9 KiB
JSON
123 lines
2.9 KiB
JSON
{
|
|
"vocab_size": 201088,
|
|
"hidden_size": 2880,
|
|
"intermediate_size": 2880,
|
|
"num_hidden_layers": 24,
|
|
"num_attention_heads": 64,
|
|
"num_local_experts": 20,
|
|
"sliding_window": 128,
|
|
"num_experts_per_tok": 4,
|
|
"num_key_value_heads": 8,
|
|
"hidden_act": "silu",
|
|
"initializer_range": 0.02,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_theta": 150000,
|
|
"rope_scaling": {
|
|
"beta_fast": 32.0,
|
|
"beta_slow": 1.0,
|
|
"factor": 32.0,
|
|
"original_max_position_embeddings": 4096,
|
|
"rope_type": "yarn",
|
|
"truncate": false
|
|
},
|
|
"attention_dropout": 0.0,
|
|
"head_dim": 64,
|
|
"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"
|
|
],
|
|
"attention_bias": true,
|
|
"max_position_embeddings": 131072,
|
|
"router_aux_loss_coef": 0.9,
|
|
"output_router_logits": false,
|
|
"use_cache": true,
|
|
"return_dict": true,
|
|
"output_hidden_states": false,
|
|
"torchscript": false,
|
|
"torch_dtype": null,
|
|
"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,
|
|
"architectures": [
|
|
"GptOssForCausalLM"
|
|
],
|
|
"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": null,
|
|
"pad_token_id": 199999,
|
|
"eos_token_id": 200002,
|
|
"sep_token_id": null,
|
|
"decoder_start_token_id": null,
|
|
"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,
|
|
"_name_or_path": "openai/gpt-oss-20b",
|
|
"transformers_version": "4.55.0",
|
|
"experts_per_token": 4,
|
|
"initial_context_length": 4096,
|
|
"model_type": "gpt_oss",
|
|
"swiglu_limit": 7.0,
|
|
"tf_legacy_loss": false,
|
|
"use_bfloat16": false,
|
|
"output_attentions": false
|
|
} |