Upload 20 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "./Cybil-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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56a1da1715caafe7d25cffce9e7d9ae26adc252c908eed725a58af7394d96af
+size 2417011552

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb5f3a9c992bfb69db3479f27dc762a54e8d8eb4f707f06ee0f6f5b69bc359a
+size 2044808592

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79e62898e36b655c96f497826b78bb610c73e2aafc637c70f39fd86cab579bc
+size 2060516760

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2b8d015139e5ca8152c84b946c7daec9deb5dc733757993568406578d4a901
+size 1955658944

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e49210778e3ecdad8cded72e5ea90bae651aa5c85fd446f347188b9373ae8d7d
+size 2044787912

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7f29082a07e2ba90d201f07d515a37576eb4538064c03fbc4301de6d46aa613
+size 2044787904

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d70bcd1900d22606b8c8f25b7b35fe3d2ec56378d5a96ca50e1738e416d352
+size 2044808624

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6477067cbcf25a05efc2b641565506dd832a7f17de1a378ae74e862606db8cda
+size 2060516792

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8948ac52923b7ebc41759d060f8f2dfb647083a544185a1ef433fc30d6a2be62
+size 1955658952

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fefd41756da5d6164e359e3d0b86a01c54d87d73bb90b34c6b21aa13312c626
+size 2044787912

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416155888ae66ddaae0971c049cee5860678f8b987af3fd1aaecbebd92d13eca
+size 2044787904

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e933a2577c7904d4495c20dc51a01f647cbd951bb1a45896d92883f1c71ab69a
+size 2044808624

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092403abdc3c57ed1ce23815456d6270706756ae9df4210f645d186868c23bd2
+size 1924190472

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "lm_head.weight": "model-00013-of-00013.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.norm.weight": "model-00013-of-00013.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "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 +1,35 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}