File size: 1,258 Bytes
c62b8b4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 | {
"architectures": [
"MarkForCausalLM"
],
"model_type": "mark",
"model_name": "Mark General 1.5B",
"model_version": "1.0.0",
"total_parameters": 1502301456,
"active_parameters_per_token": "315M (padrao) a 440M (top-4)",
"vocab_size": 4377,
"hidden_size": 1280,
"intermediate_size": 3840,
"num_hidden_layers": 16,
"num_attention_heads": 16,
"num_key_value_heads": 4,
"use_mla": true,
"q_lora_rank": 640,
"kv_lora_rank": 320,
"qk_rope_head_dim": 32,
"v_head_dim": 96,
"n_routed_experts": 16,
"n_shared_experts": 1,
"num_experts_per_tok": 2,
"moe_intermediate_size": 1504,
"recursive_depth_loops": 2,
"mtp_depth": 1,
"max_position_embeddings": 4096,
"rms_norm_eps": 1e-05,
"rope_theta": 500000.0,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"quantization": "IQ4_NL",
"target_platforms": ["LM Studio", "Ollama", "llama.cpp", "PyTorch"],
"download": {
"gguf_url": "https://github.com/thu12dta3/Mark-AI/releases/download/v1.0.0-general-1.5b/mark_general_1_5b_iq4_nl.gguf",
"pt_url": "https://github.com/thu12dta3/Mark-AI/releases/download/v1.0.0-general-1.5b/mark_general_1_5b_iq4_nl.pt",
"sha256": "cb573604d2d0990208fc84e47027e4104c870399063b0566121674e5850de124"
}
}
|