1 line
10 KiB
JSON
1 line
10 KiB
JSON
|
{"cfg": {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "head_dim": 64, "hidden_act": "silu", "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 2048, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 12, "num_hidden_layers": 12, "num_key_value_heads": 12, "pad_token_id": null, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_parameters": {"rope_theta": 10000.0, "rope_type": "default"}, "tie_word_embeddings": true, "transformers_version": "5.14.1", "use_cache": true, "vocab_size": 49152}, "params": [{"name": "model.embed_tokens.weight", "shape": [49152, 768], "numel": 37748736}, {"name": "model.layers.0.self_attn.q_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.0.self_attn.k_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.0.self_attn.v_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.0.self_attn.o_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.0.mlp.gate_proj.weight", "shape": [2048, 768], "numel": 1572864}, {"name": "model.layers.0.mlp.up_proj.weight", "shape": [2048, 768], "numel": 1572864}, {"name": "model.layers.0.mlp.down_proj.weight", "shape": [768, 2048], "numel": 1572864}, {"name": "model.layers.0.input_layernorm.weight", "shape": [768], "numel": 768}, {"name": "model.layers.0.post_attention_layernorm.weight", "shape": [768], "numel": 768}, {"name": "model.layers.1.self_attn.q_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.1.self_attn.k_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.1.self_attn.v_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.1.self_attn.o_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.1.mlp.gate_proj.weight", "shape": [2048, 768], "numel": 1572864}, {"name": "model.layers.1.mlp.up_proj.weight", "shape": [2048, 768], "numel": 1572864}, {"name": "model.layers.1.mlp.down_proj.weight", "shape": [768, 2048], "numel": 1572864}, {"name": "model.layers.1.input_layernorm.weight", "shape": [768], "numel": 768}, {"name": "model.layers.1.post_attention_layernorm.weight", "shape": [768], "numel": 768}, {"name": "model.layers.2.self_attn.q_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.2.self_attn.k_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.2.self_attn.v_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.2.self_attn.o_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.2.mlp.gate_proj.weight", "shape": [2048, 768], "numel": 1572864}, {"name": "model.layers.2.mlp.up_proj.weight", "shape": [2048, 768], "numel": 1572864}, {"name": "model.layers.2.mlp.down_proj.weight", "shape": [768, 2048], "numel": 1572864}, {"name": "model.layers.2.input_layernorm.weight", "shape": [768], "numel": 768}, {"name": "model.layers.2.post_attention_layernorm.weight", "shape": [768], "numel": 768}, {"name": "model.layers.3.self_attn.q_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.3.self_attn.k_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.3.self_attn.v_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.3.self_attn.o_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.3.mlp.gate_proj.weight", "shape": [2048, 768], "numel": 1572864}, {"name": "model.layers.3.mlp.up_proj.weight", "shape": [2048, 768], "numel": 1572864}, {"name": "model.layers.3.mlp.down_proj.weight", "shape": [768, 2048], "numel": 1572864}, {"name": "model.layers.3.input_layernorm.weight", "shape": [768], "numel": 768}, {"name": "model.layers.3.post_attention_layernorm.weight", "shape": [768], "numel": 768}, {"name": "model.layers.4.self_attn.q_proj.weight", "shape": [768, 768], "numel": 589824}, {"name": "model.layers.4.self_attn.k_proj.weight", "shape": [768, 76
|