293 lines
8.5 KiB
JSON
293 lines
8.5 KiB
JSON
{
|
|
"meta-llama/Llama-3.1-8B-Instruct": {
|
|
"hidden_size": 4096,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 8
|
|
},
|
|
"meta-llama/Llama-3.1-70B-Instruct": {
|
|
"hidden_size": 8192,
|
|
"num_attention_heads": 64,
|
|
"num_hidden_layers": 80,
|
|
"num_key_value_heads": 8
|
|
},
|
|
"mistralai/Mistral-7B-Instruct-v0.2": {
|
|
"hidden_size": 4096,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 8
|
|
},
|
|
"mistralai/Mistral-Large-Instruct-2407": {
|
|
"hidden_size": 12288,
|
|
"num_attention_heads": 96,
|
|
"num_hidden_layers": 88,
|
|
"num_key_value_heads": 8
|
|
},
|
|
"lmsys/longchat-7b-16k": {
|
|
"hidden_size": 4096,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 32
|
|
},
|
|
"Sao10K/L3-8B-Lunaris-v1": {
|
|
"hidden_size": 4096,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 8
|
|
},
|
|
"meta-llama/Llama-3.2-3B-Instruct": {
|
|
"hidden_size": 3072,
|
|
"num_attention_heads": 24,
|
|
"num_hidden_layers": 28,
|
|
"num_key_value_heads": 8
|
|
},
|
|
"deepseek-ai/DeepSeek-V3": {
|
|
"hidden_size": 7168,
|
|
"num_attention_heads": 128,
|
|
"num_hidden_layers": 61,
|
|
"num_key_value_heads": 128,
|
|
"kv_lora_rank": 512,
|
|
"qk_rope_head_dim": 64
|
|
},
|
|
"deepseek-ai/DeepSeek-R1": {
|
|
"hidden_size": 7168,
|
|
"num_attention_heads": 128,
|
|
"num_hidden_layers": 61,
|
|
"num_key_value_heads": 128,
|
|
"kv_lora_rank": 512,
|
|
"qk_rope_head_dim": 64
|
|
},
|
|
"moonshotai/Kimi-K2.6": {
|
|
"hidden_size": 7168,
|
|
"num_attention_heads": 64,
|
|
"num_hidden_layers": 61,
|
|
"num_key_value_heads": 64,
|
|
"kv_lora_rank": 512,
|
|
"qk_rope_head_dim": 64
|
|
},
|
|
"deepseek-ai/DeepSeek-V4-Pro": {
|
|
"num_hidden_layers": 61,
|
|
"head_dim": 512,
|
|
"qk_rope_head_dim": 64,
|
|
"sliding_window": 128,
|
|
"index_head_dim": 128,
|
|
"nope_bytes": 1,
|
|
"rope_bytes": 2,
|
|
"indexer_bytes": 0.5,
|
|
"compress_ratios": [128, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 0]
|
|
},
|
|
"deepseek-ai/DeepSeek-V4-Flash": {
|
|
"num_hidden_layers": 43,
|
|
"head_dim": 512,
|
|
"qk_rope_head_dim": 64,
|
|
"sliding_window": 128,
|
|
"index_head_dim": 128,
|
|
"nope_bytes": 1,
|
|
"rope_bytes": 2,
|
|
"indexer_bytes": 0.5,
|
|
"compress_ratios": [0, 0, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 0]
|
|
},
|
|
"zai-org/GLM-5.1": {
|
|
"num_hidden_layers": 78,
|
|
"kv_lora_rank": 512,
|
|
"qk_rope_head_dim": 64,
|
|
"index_head_dim": 128
|
|
},
|
|
"MiniMaxAI/MiniMax-M2.5": {
|
|
"hidden_size": 3072,
|
|
"num_attention_heads": 48,
|
|
"num_hidden_layers": 62,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 128
|
|
},
|
|
"MiniMaxAI/MiniMax-M2.7": {
|
|
"hidden_size": 3072,
|
|
"num_attention_heads": 48,
|
|
"num_hidden_layers": 62,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 128
|
|
},
|
|
"Qwen/Qwen3-235B-A22B": {
|
|
"hidden_size": 4096,
|
|
"num_attention_heads": 64,
|
|
"num_hidden_layers": 94,
|
|
"num_key_value_heads": 4,
|
|
"head_dim": 128
|
|
},
|
|
"Qwen/Qwen3.5-397B-A17B-FP8": {
|
|
"hidden_size": 4096,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 60,
|
|
"num_key_value_heads": 2,
|
|
"head_dim": 256,
|
|
"full_attention_layers": 15,
|
|
"linear_attention_layers": 45,
|
|
"linear_num_value_heads": 64,
|
|
"linear_key_head_dim": 128,
|
|
"linear_value_head_dim": 128
|
|
},
|
|
"Qwen/Qwen3-30B-A3B": {
|
|
"hidden_size": 2048,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 48,
|
|
"num_key_value_heads": 4,
|
|
"head_dim": 128
|
|
},
|
|
"Qwen/Qwen3-Coder-30B-A3B-Instruct": {
|
|
"hidden_size": 2048,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 48,
|
|
"num_key_value_heads": 4,
|
|
"head_dim": 128
|
|
},
|
|
"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
|
|
"hidden_size": 6144,
|
|
"num_attention_heads": 96,
|
|
"num_hidden_layers": 62,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 128
|
|
},
|
|
"meta-llama/Llama-3.1-405B": {
|
|
"hidden_size": 16384,
|
|
"num_attention_heads": 128,
|
|
"num_hidden_layers": 126,
|
|
"num_key_value_heads": 8
|
|
},
|
|
"meta-llama/Llama-3.2-1B-Instruct": {
|
|
"hidden_size": 2048,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 16,
|
|
"num_key_value_heads": 8
|
|
},
|
|
"Qwen/Qwen3-32B": {
|
|
"hidden_size": 5120,
|
|
"num_attention_heads": 64,
|
|
"num_hidden_layers": 64,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 128
|
|
},
|
|
"Qwen/Qwen3-14B": {
|
|
"hidden_size": 5120,
|
|
"num_attention_heads": 40,
|
|
"num_hidden_layers": 40,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 128
|
|
},
|
|
"Qwen/Qwen3-8B": {
|
|
"hidden_size": 4096,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 36,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 128
|
|
},
|
|
"Qwen/Qwen3-4B": {
|
|
"hidden_size": 2560,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 36,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 128
|
|
},
|
|
"Qwen/Qwen3-0.6B": {
|
|
"hidden_size": 1024,
|
|
"num_attention_heads": 16,
|
|
"num_hidden_layers": 28,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 128
|
|
},
|
|
"Qwen/Qwen2.5-7B-Instruct": {
|
|
"hidden_size": 3584,
|
|
"num_attention_heads": 28,
|
|
"num_hidden_layers": 28,
|
|
"num_key_value_heads": 4
|
|
},
|
|
"Qwen/Qwen2.5-3B-Instruct": {
|
|
"hidden_size": 2048,
|
|
"num_attention_heads": 16,
|
|
"num_hidden_layers": 36,
|
|
"num_key_value_heads": 2
|
|
},
|
|
"Qwen/Qwen2.5-0.5B": {
|
|
"hidden_size": 896,
|
|
"num_attention_heads": 14,
|
|
"num_hidden_layers": 24,
|
|
"num_key_value_heads": 2
|
|
},
|
|
"Qwen/Qwen-7B": {
|
|
"hidden_size": 4096,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 32
|
|
},
|
|
"zai-org/GLM-4.5": {
|
|
"hidden_size": 5120,
|
|
"num_attention_heads": 96,
|
|
"num_hidden_layers": 92,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 128
|
|
},
|
|
"zai-org/GLM-4.6": {
|
|
"hidden_size": 5120,
|
|
"num_attention_heads": 96,
|
|
"num_hidden_layers": 92,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 128
|
|
},
|
|
"google/gemma-4-31B-it": {
|
|
"hidden_size": 5376,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 60,
|
|
"num_key_value_heads": 16,
|
|
"head_dim": 256,
|
|
"sliding_window": 1024,
|
|
"full_attention_layers": 10,
|
|
"sliding_attention_layers": 50
|
|
},
|
|
"openai/gpt-oss-120b": {
|
|
"hidden_size": 2880,
|
|
"num_attention_heads": 64,
|
|
"num_hidden_layers": 36,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 64,
|
|
"sliding_window": 128,
|
|
"full_attention_layers": 18,
|
|
"sliding_attention_layers": 18
|
|
},
|
|
"openai/gpt-oss-20b": {
|
|
"hidden_size": 2880,
|
|
"num_attention_heads": 64,
|
|
"num_hidden_layers": 24,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 64,
|
|
"sliding_window": 128,
|
|
"full_attention_layers": 12,
|
|
"sliding_attention_layers": 12
|
|
},
|
|
"poolside/Laguna-XS.2": {
|
|
"hidden_size": 2048,
|
|
"num_attention_heads": 48,
|
|
"num_hidden_layers": 40,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 128,
|
|
"sliding_window": 512,
|
|
"full_attention_layers": 10,
|
|
"sliding_attention_layers": 30
|
|
},
|
|
"tencent/Hy3-preview": {
|
|
"hidden_size": 4096,
|
|
"num_attention_heads": 64,
|
|
"num_hidden_layers": 80,
|
|
"num_key_value_heads": 8,
|
|
"head_dim": 128
|
|
},
|
|
"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8": {
|
|
"hidden_size": 4096,
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 88,
|
|
"num_key_value_heads": 2,
|
|
"head_dim": 128,
|
|
"full_attention_layers": 8,
|
|
"linear_attention_layers": 40,
|
|
"linear_attention_type": "Mamba2 SSM"
|
|
}
|
|
}
|