增加模型

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "huggyllama/llama-13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model-0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51835e8f58a03ea2db1913b61d3cd9cb6af6d15b918d2e836dac5dce65b074fa
+size 4291442165

pytorch_model-1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ca51c499a1320815b3e0b6347091f2cc8d36ff3e6591c634ca2f37f252f340
+size 1551941091

pytorch_model-2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b7e99a3ae85e17a6f4d91721c67275c8b7dd0dc95dcfda074f3ff24c1ddae4e
+size 4283599620

pytorch_model-3.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c08f1bad19452a0efa314405f55069fa412d4c92c1fef3863c062f6110da18f4
+size 1373683171

pytorch_model-4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0644dc38c7e788419b5b9cf9d155fced0da1e363d3ecf358c32675aaf6f0127b
+size 4157770825

pytorch_model-5.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb99fd1af303d259db2227be1cb808c9776d4bfb1a1fb0d11176a1f5d1ef383
+size 2021211004

pytorch_model-6.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c85cebd88414457bee7a8f9058e96c2678505a0f51c32ba553a0850a7359399
+size 4157770825

pytorch_model-7.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79480f2f166b6974db0ea6e3132e4babf040e65f91c5adf6e96a164a57e23737
+size 4194449530

pytorch_model.bin.index.json

@@ -0,0 +1 @@
+{"weight_map": {"model.embed_tokens.weight": "pytorch_model-0.bin", "model.layers.0.self_attn.q_proj.weight": "pytorch_model-0.bin", "model.layers.0.self_attn.k_proj.weight": "pytorch_model-0.bin", "model.layers.0.self_attn.v_proj.weight": "pytorch_model-0.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model-0.bin", "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-0.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model-0.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model-0.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model-0.bin", "model.layers.0.input_layernorm.weight": "pytorch_model-0.bin", "model.layers.0.post_attention_layernorm.weight": "pytorch_model-0.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model-0.bin", "model.layers.1.self_attn.k_proj.weight": "pytorch_model-0.bin", "model.layers.1.self_attn.v_proj.weight": "pytorch_model-0.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model-0.bin", "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-0.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model-0.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model-0.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model-0.bin", "model.layers.1.input_layernorm.weight": "pytorch_model-0.bin", "model.layers.1.post_attention_layernorm.weight": "pytorch_model-0.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model-0.bin", "model.layers.2.self_attn.k_proj.weight": "pytorch_model-0.bin", "model.layers.2.self_attn.v_proj.weight": "pytorch_model-0.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model-0.bin", "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-0.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model-0.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model-0.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model-0.bin", "model.layers.2.input_layernorm.weight": "pytorch_model-0.bin", "model.layers.2.post_attention_layernorm.weight": "pytorch_model-0.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model-0.bin", "model.layers.3.self_attn.k_proj.weight": "pytorch_model-0.bin", "model.layers.3.self_attn.v_proj.weight": "pytorch_model-0.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model-0.bin", "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-0.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model-0.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model-0.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model-0.bin", "model.layers.3.input_layernorm.weight": "pytorch_model-0.bin", "model.layers.3.post_attention_layernorm.weight": "pytorch_model-0.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model-0.bin", "model.layers.4.self_attn.k_proj.weight": "pytorch_model-0.bin", "model.layers.4.self_attn.v_proj.weight": "pytorch_model-0.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model-0.bin", "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-0.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model-0.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model-0.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model-0.bin", "model.layers.4.input_layernorm.weight": "pytorch_model-0.bin", "model.layers.4.post_attention_layernorm.weight": "pytorch_model-0.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model-0.bin", "model.layers.5.self_attn.k_proj.weight": "pytorch_model-0.bin", "model.layers.5.self_attn.v_proj.weight": "pytorch_model-0.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model-0.bin", "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-0.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model-0.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model-0.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model-0.bin", "model.layers.5.input_layernorm.weight": "pytorch_model-0.bin", "model.layers.5.post_attention_layernorm.weight": "pytorch_model-0.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model-0.bin", "model.layers.6.self_attn.k_proj.weight": "pytorch_model-0.bin", "model.layers.6.self_attn.v_proj.weight": "pytorch_model-0.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model-1.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model-1.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model-1.bin", "model.layers.28.input_layernorm.weight": "pytorch_model-1.bin", "model.layers.28.post_attention_layernorm.weight": "pytorch_model-1.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model-1.bin", "model.layers.29.self_attn.k_proj.weight": "pytorch_model-1.bin", "model.layers.29.self_attn.v_proj.weight": "pytorch_model-1.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model-1.bin", "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-1.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model-1.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model-1.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model-1.bin", "model.layers.29.input_layernorm.weight": "pytorch_model-1.bin", "model.layers.29.post_attention_layernorm.weight": "pytorch_model-1.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model-1.bin", "model.layers.30.self_attn.k_proj.weight": "pytorch_model-1.bin", "model.layers.30.self_attn.v_proj.weight": "pytorch_model-1.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model-1.bin", "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-1.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model-1.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model-1.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model-2.bin", "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-2.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model-2.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model-2.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model-2.bin", "model.layers.6.input_layernorm.weight": "pytorch_model-2.bin", "model.layers.6.post_attention_layernorm.weight": "pytorch_model-2.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model-2.bin", "model.layers.7.self_attn.k_proj.weight": "pytorch_model-2.bin", "model.layers.7.self_attn.v_proj.weight": "pytorch_model-2.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model-2.bin", "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-2.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model-2.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model-2.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model-2.bin", "model.layers.7.input_layernorm.weight": "pytorch_model-2.bin", "model.layers.7.post_attention_layernorm.weight": "pytorch_model-2.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model-2.bin", "model.layers.8.self_attn.k_proj.weight": "pytorch_model-2.bin", "model.layers.8.self_attn.v_proj.weight": "pytorch_model-2.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model-2.bin", "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-2.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model-2.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model-2.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model-2.bin", "model.layers.8.input_layernorm.weight": "pytorch_model-2.bin", "model.layers.8.post_attention_layernorm.weight": "pytorch_model-2.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model-2.bin", "model.layers.9.self_attn.k_proj.weight": "pytorch_model-2.bin", "model.layers.9.self_attn.v_proj.weight": "pytorch_model-2.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model-2.bin", "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-2.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model-2.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model-2.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model-2.bin", "model.layers.9.input_layernorm.weight": "pytorch_model-2.bin", "model.layers.9.post_attention_layernorm.weight": "pytorch_model-2.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model-2.bin", "model.layers.10.self_attn.k_proj.weight": "pytorch_model-2.bin", "model.layers.10.self_attn.v_proj.weight": "pytorch_model-2.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model-2.bin", "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-2.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model-2.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model-2.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model-2.bin", "model.layers.10.input_layernorm.weight": "pytorch_model-2.bin", "model.layers.10.post_attention_layernorm.weight": "pytorch_model-2.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model-2.bin", "model.layers.11.self_attn.k_proj.weight": "pytorch_model-2.bin", "model.layers.11.self_attn.v_proj.weight": "pytorch_model-2.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model-2.bin", "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-2.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model-2.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model-2.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model-2.bin", "model.layers.11.input_layernorm.weight": "pytorch_model-2.bin", "model.layers.11.post_attention_layernorm.weight": "pytorch_model-2.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model-2.bin", "model.layers.12.self_attn.k_proj.weight": "pytorch_model-2.bin", "model.layers.12.self_attn.v_proj.weight": "pytorch_model-2.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model-2.bin", "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-2.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model-2.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model-2.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model-2.bin", "model.layers.12.input_layernorm.weight": "pytorch_model-2.bin", "model.layers.12.post_attention_layernorm.weight": "pytorch_model-2.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model-3.bin", "model.layers.13.self_attn.k_proj.weight": "pytorch_model-3.bin", "model.layers.13.self_attn.v_proj.weight": "pytorch_model-3.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model-3.bin", "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-3.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model-3.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model-3.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model-3.bin", "model.layers.13.input_layernorm.weight": "pytorch_model-3.bin", "model.layers.13.post_attention_layernorm.weight": "pytorch_model-3.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model-3.bin", "model.layers.14.self_attn.k_proj.weight": "pytorch_model-3.bin", "model.layers.14.self_attn.v_proj.weight": "pytorch_model-3.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model-3.bin", "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-3.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model-3.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model-3.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model-3.bin", "model.layers.14.input_layernorm.weight": "pytorch_model-3.bin", "model.layers.14.post_attention_layernorm.weight": "pytorch_model-3.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model-3.bin", "model.layers.15.self_attn.k_proj.weight": "pytorch_model-3.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model-4.bin", "model.layers.30.input_layernorm.weight": "pytorch_model-4.bin", "model.layers.30.post_attention_layernorm.weight": "pytorch_model-4.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model-4.bin", "model.layers.31.self_attn.k_proj.weight": "pytorch_model-4.bin", "model.layers.31.self_attn.v_proj.weight": "pytorch_model-4.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model-4.bin", "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-4.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model-4.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model-4.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model-4.bin", "model.layers.31.input_layernorm.weight": "pytorch_model-4.bin", "model.layers.31.post_attention_layernorm.weight": "pytorch_model-4.bin", "model.layers.32.self_attn.q_proj.weight": "pytorch_model-4.bin", "model.layers.32.self_attn.k_proj.weight": "pytorch_model-4.bin", "model.layers.32.self_attn.v_proj.weight": "pytorch_model-4.bin", "model.layers.32.self_attn.o_proj.weight": "pytorch_model-4.bin", "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-4.bin", "model.layers.32.mlp.gate_proj.weight": "pytorch_model-4.bin", "model.layers.32.mlp.down_proj.weight": "pytorch_model-4.bin", "model.layers.32.mlp.up_proj.weight": "pytorch_model-4.bin", "model.layers.32.input_layernorm.weight": "pytorch_model-4.bin", "model.layers.32.post_attention_layernorm.weight": "pytorch_model-4.bin", "model.layers.33.self_attn.q_proj.weight": "pytorch_model-4.bin", "model.layers.33.self_attn.k_proj.weight": "pytorch_model-4.bin", "model.layers.33.self_attn.v_proj.weight": "pytorch_model-4.bin", "model.layers.33.self_attn.o_proj.weight": "pytorch_model-4.bin", "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-4.bin", "model.layers.33.mlp.gate_proj.weight": "pytorch_model-4.bin", "model.layers.33.mlp.down_proj.weight": "pytorch_model-4.bin", "model.layers.33.mlp.up_proj.weight": "pytorch_model-4.bin", "model.layers.33.input_layernorm.weight": "pytorch_model-4.bin", "model.layers.33.post_attention_layernorm.weight": "pytorch_model-4.bin", "model.layers.34.self_attn.q_proj.weight": "pytorch_model-4.bin", "model.layers.34.self_attn.k_proj.weight": "pytorch_model-4.bin", "model.layers.34.self_attn.v_proj.weight": "pytorch_model-4.bin", "model.layers.34.self_attn.o_proj.weight": "pytorch_model-4.bin", "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-4.bin", "model.layers.34.mlp.gate_proj.weight": "pytorch_model-4.bin", "model.layers.34.mlp.down_proj.weight": "pytorch_model-4.bin", "model.layers.34.mlp.up_proj.weight": "pytorch_model-4.bin", "model.layers.34.input_layernorm.weight": "pytorch_model-4.bin", "model.layers.34.post_attention_layernorm.weight": "pytorch_model-4.bin", "model.layers.35.self_attn.q_proj.weight": "pytorch_model-4.bin", "model.layers.35.self_attn.k_proj.weight": "pytorch_model-4.bin", "model.layers.35.self_attn.v_proj.weight": "pytorch_model-4.bin", "model.layers.35.self_attn.o_proj.weight": "pytorch_model-4.bin", "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-4.bin", "model.layers.35.mlp.gate_proj.weight": "pytorch_model-4.bin", "model.layers.35.mlp.down_proj.weight": "pytorch_model-4.bin", "model.layers.35.mlp.up_proj.weight": "pytorch_model-4.bin", "model.layers.35.input_layernorm.weight": "pytorch_model-4.bin", "model.layers.35.post_attention_layernorm.weight": "pytorch_model-4.bin", "model.layers.36.self_attn.q_proj.weight": "pytorch_model-4.bin", "model.layers.36.self_attn.k_proj.weight": "pytorch_model-4.bin", "model.layers.36.self_attn.v_proj.weight": "pytorch_model-4.bin", "model.layers.36.self_attn.o_proj.weight": "pytorch_model-4.bin", "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-4.bin", "model.layers.36.mlp.gate_proj.weight": "pytorch_model-4.bin", "model.layers.36.mlp.down_proj.weight": "pytorch_model-4.bin", "model.layers.36.mlp.up_proj.weight": "pytorch_model-4.bin", "model.layers.36.input_layernorm.weight": "pytorch_model-4.bin", "model.layers.36.post_attention_layernorm.weight": "pytorch_model-4.bin", "model.layers.37.self_attn.q_proj.weight": "pytorch_model-4.bin", "model.layers.37.self_attn.k_proj.weight": "pytorch_model-4.bin", "model.layers.37.self_attn.v_proj.weight": "pytorch_model-4.bin", "model.layers.37.self_attn.o_proj.weight": "pytorch_model-4.bin", "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-4.bin", "model.layers.37.mlp.gate_proj.weight": "pytorch_model-5.bin", "model.layers.37.mlp.down_proj.weight": "pytorch_model-5.bin", "model.layers.37.mlp.up_proj.weight": "pytorch_model-5.bin", "model.layers.37.input_layernorm.weight": "pytorch_model-5.bin", "model.layers.37.post_attention_layernorm.weight": "pytorch_model-5.bin", "model.layers.38.self_attn.q_proj.weight": "pytorch_model-5.bin", "model.layers.38.self_attn.k_proj.weight": "pytorch_model-5.bin", "model.layers.38.self_attn.v_proj.weight": "pytorch_model-5.bin", "model.layers.38.self_attn.o_proj.weight": "pytorch_model-5.bin", "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-5.bin", "model.layers.38.mlp.gate_proj.weight": "pytorch_model-5.bin", "model.layers.38.mlp.down_proj.weight": "pytorch_model-5.bin", "model.layers.38.mlp.up_proj.weight": "pytorch_model-5.bin", "model.layers.38.input_layernorm.weight": "pytorch_model-5.bin", "model.layers.38.post_attention_layernorm.weight": "pytorch_model-5.bin", "model.layers.39.self_attn.q_proj.weight": "pytorch_model-5.bin", "model.layers.39.self_attn.k_proj.weight": "pytorch_model-5.bin", "model.layers.39.self_attn.v_proj.weight": "pytorch_model-5.bin", "model.layers.39.self_attn.o_proj.weight": "pytorch_model-5.bin", "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-5.bin", "model.layers.39.mlp.gate_proj.weight": "pytorch_model-5.bin", "model.layers.39.mlp.down_proj.weight": "pytorch_model-5.bin", "model.layers.39.mlp.up_proj.weight": "pytorch_model-5.bin", "model.layers.39.input_layernorm.weight": "pytorch_model-5.bin", "model.layers.39.post_attention_layernorm.weight": "pytorch_model-5.bin", "model.norm.weight": "pytorch_model-5.bin", "lm_head.weight": "pytorch_model-5.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model-6.bin", "model.layers.21.input_layernorm.weight": "pytorch_model-6.bin", "model.layers.21.post_attention_layernorm.weight": "pytorch_model-6.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model-6.bin", "model.layers.22.self_attn.k_proj.weight": "pytorch_model-6.bin", "model.layers.22.self_attn.v_proj.weight": "pytorch_model-6.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model-6.bin", "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-6.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model-6.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model-6.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model-6.bin", "model.layers.22.input_layernorm.weight": "pytorch_model-6.bin", "model.layers.22.post_attention_layernorm.weight": "pytorch_model-6.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model-6.bin", "model.layers.23.self_attn.k_proj.weight": "pytorch_model-6.bin", "model.layers.23.self_attn.v_proj.weight": "pytorch_model-6.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model-6.bin", "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-6.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model-6.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model-6.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model-6.bin", "model.layers.23.input_layernorm.weight": "pytorch_model-6.bin", "model.layers.23.post_attention_layernorm.weight": "pytorch_model-6.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model-6.bin", "model.layers.24.self_attn.k_proj.weight": "pytorch_model-6.bin", "model.layers.24.self_attn.v_proj.weight": "pytorch_model-6.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model-6.bin", "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-6.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model-6.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model-6.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model-6.bin", "model.layers.24.input_layernorm.weight": "pytorch_model-6.bin", "model.layers.24.post_attention_layernorm.weight": "pytorch_model-6.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model-6.bin", "model.layers.25.self_attn.k_proj.weight": "pytorch_model-6.bin", "model.layers.25.self_attn.v_proj.weight": "pytorch_model-6.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model-6.bin", "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-6.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model-6.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model-6.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model-6.bin", "model.layers.25.input_layernorm.weight": "pytorch_model-6.bin", "model.layers.25.post_attention_layernorm.weight": "pytorch_model-6.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model-6.bin", "model.layers.26.self_attn.k_proj.weight": "pytorch_model-6.bin", "model.layers.26.self_attn.v_proj.weight": "pytorch_model-6.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model-6.bin", "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-6.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model-6.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model-6.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model-6.bin", "model.layers.26.input_layernorm.weight": "pytorch_model-6.bin", "model.layers.26.post_attention_layernorm.weight": "pytorch_model-6.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model-6.bin", "model.layers.27.self_attn.k_proj.weight": "pytorch_model-6.bin", "model.layers.27.self_attn.v_proj.weight": "pytorch_model-6.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model-6.bin", "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-6.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model-6.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model-6.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model-6.bin", "model.layers.27.input_layernorm.weight": "pytorch_model-6.bin", "model.layers.27.post_attention_layernorm.weight": "pytorch_model-6.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model-6.bin", "model.layers.28.self_attn.k_proj.weight": "pytorch_model-6.bin", "model.layers.28.self_attn.v_proj.weight": "pytorch_model-6.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model-6.bin", "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-6.bin", "model.layers.15.self_attn.v_proj.weight": "pytorch_model-7.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model-7.bin", "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-7.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model-7.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model-7.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model-7.bin", "model.layers.15.input_layernorm.weight": "pytorch_model-7.bin", "model.layers.15.post_attention_layernorm.weight": "pytorch_model-7.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model-7.bin", "model.layers.16.self_attn.k_proj.weight": "pytorch_model-7.bin", "model.layers.16.self_attn.v_proj.weight": "pytorch_model-7.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model-7.bin", "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-7.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model-7.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model-7.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model-7.bin", "model.layers.16.input_layernorm.weight": "pytorch_model-7.bin", "model.layers.16.post_attention_layernorm.weight": "pytorch_model-7.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model-7.bin", "model.layers.17.self_attn.k_proj.weight": "pytorch_model-7.bin", "model.layers.17.self_attn.v_proj.weight": "pytorch_model-7.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model-7.bin", "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-7.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model-7.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model-7.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model-7.bin", "model.layers.17.input_layernorm.weight": "pytorch_model-7.bin", "model.layers.17.post_attention_layernorm.weight": "pytorch_model-7.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model-7.bin", "model.layers.18.self_attn.k_proj.weight": "pytorch_model-7.bin", "model.layers.18.self_attn.v_proj.weight": "pytorch_model-7.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model-7.bin", "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-7.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model-7.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model-7.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model-7.bin", "model.layers.18.input_layernorm.weight": "pytorch_model-7.bin", "model.layers.18.post_attention_layernorm.weight": "pytorch_model-7.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model-7.bin", "model.layers.19.self_attn.k_proj.weight": "pytorch_model-7.bin", "model.layers.19.self_attn.v_proj.weight": "pytorch_model-7.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model-7.bin", "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-7.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model-7.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model-7.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model-7.bin", "model.layers.19.input_layernorm.weight": "pytorch_model-7.bin", "model.layers.19.post_attention_layernorm.weight": "pytorch_model-7.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model-7.bin", "model.layers.20.self_attn.k_proj.weight": "pytorch_model-7.bin", "model.layers.20.self_attn.v_proj.weight": "pytorch_model-7.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model-7.bin", "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-7.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model-7.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model-7.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model-7.bin", "model.layers.20.input_layernorm.weight": "pytorch_model-7.bin", "model.layers.20.post_attention_layernorm.weight": "pytorch_model-7.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model-7.bin", "model.layers.21.self_attn.k_proj.weight": "pytorch_model-7.bin", "model.layers.21.self_attn.v_proj.weight": "pytorch_model-7.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model-7.bin", "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-7.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model-7.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model-7.bin"}, "metadata": {"total_size": 26031738880}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}