初始化项目,由ModelHub XC社区提供模型

Model: AI4PD/ProtGPT3-1.3B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-30 23:59:20 +08:00
commit 03253c18c5
8 changed files with 506 additions and 0 deletions

32
config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"architectures": [
"MixtralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": null,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"max_position_embeddings": 1025,
"model_type": "mixtral",
"num_attention_heads": 16,
"num_experts_per_tok": 2,
"num_hidden_layers": 17,
"num_key_value_heads": 4,
"num_local_experts": 8,
"output_router_logits": false,
"pad_token_id": 0,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.01,
"router_jitter_noise": 0.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.55.2",
"use_cache": true,
"vocab_size": 31
}