{ "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 }, "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 }, "Qwen/Qwen3-30B-A3B-Instruct-2507": { "hidden_size": 2048, "num_attention_heads": 32, "num_hidden_layers": 48, "num_key_value_heads": 4, "head_dim": 128 }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "hidden_size": 4096, "num_attention_heads": 64, "num_hidden_layers": 94, "num_key_value_heads": 4, "head_dim": 128 }, "tencent/Hunyuan-0.5B-Instruct": { "hidden_size": 1024, "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 8, "head_dim": 128 }, "tencent/Hunyuan-1.8B-Instruct": { "hidden_size": 2048, "num_attention_heads": 16, "num_hidden_layers": 32, "num_key_value_heads": 4, "head_dim": 128 }, "tencent/Hunyuan-4B-Instruct": { "hidden_size": 3072, "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "head_dim": 128 }, "tencent/Hunyuan-7B-Instruct": { "hidden_size": 4096, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "head_dim": 128 }, "tencent/Hunyuan-A13B-Instruct": { "hidden_size": 4096, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "head_dim": 128 }, "tencent/Hunyuan-Large": { "hidden_size": 6400, "num_attention_heads": 80, "num_hidden_layers": 64, "num_key_value_heads": 8, "cla_share_factor": 2 } }