first commit

config.json

@@ -0,0 +1,16 @@
+{
+    "num_key_value_heads": 8,
+    "intermediate_size": 4096,
+    "hidden_size": 1536,
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-05,
+    "max_position_embeddings": 2048,
+    "hidden_act": "silu",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 16,
+    "rope_scaling": null,
+    "rope_theta": 100000,
+    "tie_word_embeddings": false,
+    "vocab_size": 128256,
+    "model_type": "llama"
+}

pytorch_model-00001-of-00001.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9666ab053464c4ca64ce31665c28cf083d5d753b06c8670e0587abae8426dbb9
+size 3237206831

pytorch_model.bin.index.json

@@ -0,0 +1,154 @@
+{
+    "metadata": {
+        "total_size": 3237156864
+    },
+    "weight_map": {
+        "model.embed_tokens.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00001.bin",
+        "model.norm.weight": "pytorch_model-00001-of-00001.bin",
+        "lm_head.weight": "pytorch_model-00001-of-00001.bin"
+    }
+}