First

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "./vicuna-7b-delta-v1.1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model-0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb9ba2498970aae18bc244761d12a92c15458a03b5845dd48810aa532d05bf0
+size 404770535

pytorch_model-1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c3e630aa8d4e3a8f86b34a9858f825bfd4271d83e17c4a6f1b0ff42f07326f4
+size 404770535

pytorch_model-10.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3abfd2ad685b6cc8271519108324a500f4e06a63da94b0a1e908b4769b742102
+size 404770483

pytorch_model-11.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e4dc7b117a669a0ea79191fbe70fd2f9a7b331d028de5aa89b318fc9d64d418
+size 404770547

pytorch_model-12.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b035edbea69dbc721d9b29edef430779449922847f290f147f366aa2ddfeb184
+size 404770483

pytorch_model-13.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4fc21634d10b76c840e20ecf511c1f46cd6b1c3ffe69e7bb135432f3cc2d67b
+size 404770547

pytorch_model-14.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8f919b0ccd9b989d4fc7a6c9bea3bd5cb63b808819d8f5e081eb872ea2aa1d
+size 404770483

pytorch_model-15.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5034cfe04df38caa65d03bb887e1008478a61846e8616e4c99d1d96dd44a20
+size 404770547

pytorch_model-16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a2023b98e73b05bc532a8e5a546a65c1339d54df81fe55f735b42ad9858006
+size 404770547

pytorch_model-17.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffb2f06eef3dc8c0ef60e3ca325647b501bf2ab99d7fb044a7ea4fa77f005bd2
+size 404770547

pytorch_model-18.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfbc0294154000503bd67fdb1771759a897908ce670a2d4d3eee198e6b068776
+size 404770483

pytorch_model-19.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33271f367ca4b37865640b4ccde45f7455fc96a7aeba06b7697a4431333f52f
+size 404770483

pytorch_model-2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194924ff802416e697afe6b0e20abba2c97b4372870dbac3d51fb8a4d0e2f70a
+size 404770535

pytorch_model-20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffac6519b33825914c787084347f832d93bcb4eef46b6cd4e52e61fd51b1ce7a
+size 404770483

pytorch_model-21.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eddfbe41e7fafd5a8ca8c7fd63107f8a359778a27b3b364de2ecabb9e419b99c
+size 404770547

pytorch_model-22.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f0be83b90283823ced7c0a9217abb585f3ee4e802116772e15318ffce3aeb3
+size 404770547

pytorch_model-23.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0027ebe11bcc4bf0ccefa436d38de95031b30cd9380fedea9c32616fd876f8c9
+size 404770547

pytorch_model-24.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336048fd035e41442a068cccab74a6af91113f6a53d329f9bc1a642839809a10
+size 404770547

pytorch_model-25.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f14f9df4f19600392cb7157acb1fd09fd0c6d4926ecf8fbc57a556ff14f699aa
+size 404770483

pytorch_model-26.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56162fdf1ec9b4d4f17d6b5bd168d2aa05d9a3c61013cdbaf0a1d49f8deaf6c8
+size 404770547

pytorch_model-27.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24866c93134cc8dfaad6b2db4acfd1a7c32788396e6b42d5a20518d679166f35
+size 404770483

pytorch_model-28.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc97c5b3b88fe843f76586fa02d774a67476492b3f35d554f14fc2d42674fcdd
+size 404770483

pytorch_model-29.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f055ba0cf6aed3ad8fbdb55dc650f5aebf1c0fee9511930a3798d10bd66da36
+size 404770483

pytorch_model-3.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df725e4e2a0e0157e1cd8841cf586bf606824c5481499c1be2b6f6449ad2e8df
+size 404770535

pytorch_model-30.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b276ad8fe1ac7d3ba86f2f0c474109449ea8091e09005906c60bc60c395917
+size 404770547

pytorch_model-31.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caeb0a44ff8c04243ac6c741d3f6edc389caa82340a80021ff560ecb026ef5e7
+size 404770547

pytorch_model-32.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6624f749ffc0b2b60cb336bb6ced7dc9ed85db7093cfffa24d0d440285f050d6
+size 404770547

pytorch_model-4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4ce829133d38031b8b207a81bdf8778ff84db60ac4f70a3761a65c14a75770e
+size 524297547

pytorch_model-5.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5dff280ec05517a288d254dc8785bf38dc1af061e3d9eaa9e8f63ed7194fcb
+size 404770535

pytorch_model-6.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291a78fa51aa978b522019365b090cace2b08190648fe72fe0df603907cec0ed
+size 404770535

pytorch_model-7.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26fb4e716ba07c7025f768bdbef4d920f70a4d220f852a1ecc29db605999df7c
+size 404770535

pytorch_model-8.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:053c2e8ebf87fd4e6f752dcb5b73511a7a6b59fc429c62eabfad7ff13cabc699
+size 404770535

pytorch_model-9.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccbea2702b92e39ff9b2088e980d189aeda1803647e36a9386b2a7dc3a5e828d
+size 404770535

pytorch_model.bin.index.json

@@ -0,0 +1 @@
+{"weight_map": {"model.layers.19.self_attn.q_proj.weight": "pytorch_model-0.bin", "model.layers.19.self_attn.k_proj.weight": "pytorch_model-0.bin", "model.layers.19.self_attn.v_proj.weight": "pytorch_model-0.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model-0.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model-0.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model-0.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model-0.bin", "model.layers.19.input_layernorm.weight": "pytorch_model-0.bin", "model.layers.19.post_attention_layernorm.weight": "pytorch_model-0.bin", "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-0.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model-1.bin", "model.layers.24.self_attn.k_proj.weight": "pytorch_model-1.bin", "model.layers.24.self_attn.v_proj.weight": "pytorch_model-1.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model-1.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model-1.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model-1.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model-1.bin", "model.layers.24.input_layernorm.weight": "pytorch_model-1.bin", "model.layers.24.post_attention_layernorm.weight": "pytorch_model-1.bin", "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-1.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model-2.bin", "model.layers.23.self_attn.k_proj.weight": "pytorch_model-2.bin", "model.layers.23.self_attn.v_proj.weight": "pytorch_model-2.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model-2.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model-2.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model-2.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model-2.bin", "model.layers.23.input_layernorm.weight": "pytorch_model-2.bin", "model.layers.23.post_attention_layernorm.weight": "pytorch_model-2.bin", "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-2.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model-3.bin", "model.layers.20.self_attn.k_proj.weight": "pytorch_model-3.bin", "model.layers.20.self_attn.v_proj.weight": "pytorch_model-3.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model-3.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model-3.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model-3.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model-3.bin", "model.layers.20.input_layernorm.weight": "pytorch_model-3.bin", "model.layers.20.post_attention_layernorm.weight": "pytorch_model-3.bin", "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-3.bin", "model.embed_tokens.weight": "pytorch_model-4.bin", "model.norm.weight": "pytorch_model-4.bin", "lm_head.weight": "pytorch_model-4.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model-5.bin", "model.layers.10.self_attn.k_proj.weight": "pytorch_model-5.bin", "model.layers.10.self_attn.v_proj.weight": "pytorch_model-5.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model-5.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model-5.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model-5.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model-5.bin", "model.layers.10.input_layernorm.weight": "pytorch_model-5.bin", "model.layers.10.post_attention_layernorm.weight": "pytorch_model-5.bin", "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-5.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model-6.bin", "model.layers.17.self_attn.k_proj.weight": "pytorch_model-6.bin", "model.layers.17.self_attn.v_proj.weight": "pytorch_model-6.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model-6.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model-6.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model-6.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model-6.bin", "model.layers.17.input_layernorm.weight": "pytorch_model-6.bin", "model.layers.17.post_attention_layernorm.weight": "pytorch_model-6.bin", "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-6.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model-7.bin", "model.layers.15.self_attn.k_proj.weight": "pytorch_model-7.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.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.15.self_attn.rotary_emb.inv_freq": "pytorch_model-7.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model-8.bin", "model.layers.25.self_attn.k_proj.weight": "pytorch_model-8.bin", "model.layers.25.self_attn.v_proj.weight": "pytorch_model-8.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model-8.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model-8.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model-8.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model-8.bin", "model.layers.25.input_layernorm.weight": "pytorch_model-8.bin", "model.layers.25.post_attention_layernorm.weight": "pytorch_model-8.bin", "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-8.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model-9.bin", "model.layers.18.self_attn.k_proj.weight": "pytorch_model-9.bin", "model.layers.18.self_attn.v_proj.weight": "pytorch_model-9.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model-9.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model-9.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model-9.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model-9.bin", "model.layers.18.input_layernorm.weight": "pytorch_model-9.bin", "model.layers.18.post_attention_layernorm.weight": "pytorch_model-9.bin", "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-9.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model-10.bin", "model.layers.9.self_attn.k_proj.weight": "pytorch_model-10.bin", "model.layers.9.self_attn.v_proj.weight": "pytorch_model-10.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model-10.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model-10.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model-10.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model-10.bin", "model.layers.9.input_layernorm.weight": "pytorch_model-10.bin", "model.layers.9.post_attention_layernorm.weight": "pytorch_model-10.bin", "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-10.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model-11.bin", "model.layers.29.self_attn.k_proj.weight": "pytorch_model-11.bin", "model.layers.29.self_attn.v_proj.weight": "pytorch_model-11.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model-11.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model-11.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model-11.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model-11.bin", "model.layers.29.input_layernorm.weight": "pytorch_model-11.bin", "model.layers.29.post_attention_layernorm.weight": "pytorch_model-11.bin", "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-11.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model-12.bin", "model.layers.8.self_attn.k_proj.weight": "pytorch_model-12.bin", "model.layers.8.self_attn.v_proj.weight": "pytorch_model-12.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model-12.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model-12.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model-12.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model-12.bin", "model.layers.8.input_layernorm.weight": "pytorch_model-12.bin", "model.layers.8.post_attention_layernorm.weight": "pytorch_model-12.bin", "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-12.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model-13.bin", "model.layers.13.self_attn.k_proj.weight": "pytorch_model-13.bin", "model.layers.13.self_attn.v_proj.weight": "pytorch_model-13.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model-13.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model-13.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model-13.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model-13.bin", "model.layers.13.input_layernorm.weight": "pytorch_model-13.bin", "model.layers.13.post_attention_layernorm.weight": "pytorch_model-13.bin", "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-13.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model-14.bin", "model.layers.1.self_attn.k_proj.weight": "pytorch_model-14.bin", "model.layers.1.self_attn.v_proj.weight": "pytorch_model-14.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model-14.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model-14.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model-14.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model-14.bin", "model.layers.1.input_layernorm.weight": "pytorch_model-14.bin", "model.layers.1.post_attention_layernorm.weight": "pytorch_model-14.bin", "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-14.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model-15.bin", "model.layers.31.self_attn.k_proj.weight": "pytorch_model-15.bin", "model.layers.31.self_attn.v_proj.weight": "pytorch_model-15.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model-15.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model-15.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model-15.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model-15.bin", "model.layers.31.input_layernorm.weight": "pytorch_model-15.bin", "model.layers.31.post_attention_layernorm.weight": "pytorch_model-15.bin", "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-15.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model-16.bin", "model.layers.14.self_attn.k_proj.weight": "pytorch_model-16.bin", "model.layers.14.self_attn.v_proj.weight": "pytorch_model-16.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model-16.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model-16.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model-16.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model-16.bin", "model.layers.14.input_layernorm.weight": "pytorch_model-16.bin", "model.layers.14.post_attention_layernorm.weight": "pytorch_model-16.bin", "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-16.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model-17.bin", "model.layers.28.self_attn.k_proj.weight": "pytorch_model-17.bin", "model.layers.28.self_attn.v_proj.weight": "pytorch_model-17.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model-17.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model-17.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model-17.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model-17.bin", "model.layers.28.input_layernorm.weight": "pytorch_model-17.bin", "model.layers.28.post_attention_layernorm.weight": "pytorch_model-17.bin", "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-17.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model-18.bin", "model.layers.3.self_attn.k_proj.weight": "pytorch_model-18.bin", "model.layers.3.self_attn.v_proj.weight": "pytorch_model-18.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model-18.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model-18.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model-18.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model-18.bin", "model.layers.3.input_layernorm.weight": "pytorch_model-18.bin", "model.layers.3.post_attention_layernorm.weight": "pytorch_model-18.bin", "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-18.bin", "model.layers.0.self_attn.q_proj.weight": "pytorch_model-19.bin", "model.layers.0.self_attn.k_proj.weight": "pytorch_model-19.bin", "model.layers.0.self_attn.v_proj.weight": "pytorch_model-19.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model-19.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model-19.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model-19.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model-19.bin", "model.layers.0.input_layernorm.weight": "pytorch_model-19.bin", "model.layers.0.post_attention_layernorm.weight": "pytorch_model-19.bin", "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-19.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model-20.bin", "model.layers.4.self_attn.k_proj.weight": "pytorch_model-20.bin", "model.layers.4.self_attn.v_proj.weight": "pytorch_model-20.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model-20.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model-20.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model-20.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model-20.bin", "model.layers.4.input_layernorm.weight": "pytorch_model-20.bin", "model.layers.4.post_attention_layernorm.weight": "pytorch_model-20.bin", "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-20.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model-21.bin", "model.layers.21.self_attn.k_proj.weight": "pytorch_model-21.bin", "model.layers.21.self_attn.v_proj.weight": "pytorch_model-21.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model-21.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model-21.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model-21.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model-21.bin", "model.layers.21.input_layernorm.weight": "pytorch_model-21.bin", "model.layers.21.post_attention_layernorm.weight": "pytorch_model-21.bin", "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-21.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model-22.bin", "model.layers.22.self_attn.k_proj.weight": "pytorch_model-22.bin", "model.layers.22.self_attn.v_proj.weight": "pytorch_model-22.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model-22.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model-22.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model-22.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model-22.bin", "model.layers.22.input_layernorm.weight": "pytorch_model-22.bin", "model.layers.22.post_attention_layernorm.weight": "pytorch_model-22.bin", "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-22.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model-23.bin", "model.layers.12.self_attn.k_proj.weight": "pytorch_model-23.bin", "model.layers.12.self_attn.v_proj.weight": "pytorch_model-23.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model-23.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model-23.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model-23.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model-23.bin", "model.layers.12.input_layernorm.weight": "pytorch_model-23.bin", "model.layers.12.post_attention_layernorm.weight": "pytorch_model-23.bin", "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-23.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model-24.bin", "model.layers.16.self_attn.k_proj.weight": "pytorch_model-24.bin", "model.layers.16.self_attn.v_proj.weight": "pytorch_model-24.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model-24.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model-24.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model-24.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model-24.bin", "model.layers.16.input_layernorm.weight": "pytorch_model-24.bin", "model.layers.16.post_attention_layernorm.weight": "pytorch_model-24.bin", "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-24.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model-25.bin", "model.layers.2.self_attn.k_proj.weight": "pytorch_model-25.bin", "model.layers.2.self_attn.v_proj.weight": "pytorch_model-25.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model-25.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model-25.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model-25.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model-25.bin", "model.layers.2.input_layernorm.weight": "pytorch_model-25.bin", "model.layers.2.post_attention_layernorm.weight": "pytorch_model-25.bin", "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-25.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model-26.bin", "model.layers.27.self_attn.k_proj.weight": "pytorch_model-26.bin", "model.layers.27.self_attn.v_proj.weight": "pytorch_model-26.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model-26.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model-26.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model-26.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model-26.bin", "model.layers.27.input_layernorm.weight": "pytorch_model-26.bin", "model.layers.27.post_attention_layernorm.weight": "pytorch_model-26.bin", "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-26.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model-27.bin", "model.layers.6.self_attn.k_proj.weight": "pytorch_model-27.bin", "model.layers.6.self_attn.v_proj.weight": "pytorch_model-27.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model-27.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model-27.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model-27.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model-27.bin", "model.layers.6.input_layernorm.weight": "pytorch_model-27.bin", "model.layers.6.post_attention_layernorm.weight": "pytorch_model-27.bin", "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-27.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model-28.bin", "model.layers.7.self_attn.k_proj.weight": "pytorch_model-28.bin", "model.layers.7.self_attn.v_proj.weight": "pytorch_model-28.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model-28.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model-28.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model-28.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model-28.bin", "model.layers.7.input_layernorm.weight": "pytorch_model-28.bin", "model.layers.7.post_attention_layernorm.weight": "pytorch_model-28.bin", "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-28.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model-29.bin", "model.layers.5.self_attn.k_proj.weight": "pytorch_model-29.bin", "model.layers.5.self_attn.v_proj.weight": "pytorch_model-29.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model-29.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model-29.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model-29.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model-29.bin", "model.layers.5.input_layernorm.weight": "pytorch_model-29.bin", "model.layers.5.post_attention_layernorm.weight": "pytorch_model-29.bin", "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-29.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model-30.bin", "model.layers.11.self_attn.k_proj.weight": "pytorch_model-30.bin", "model.layers.11.self_attn.v_proj.weight": "pytorch_model-30.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model-30.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model-30.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model-30.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model-30.bin", "model.layers.11.input_layernorm.weight": "pytorch_model-30.bin", "model.layers.11.post_attention_layernorm.weight": "pytorch_model-30.bin", "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-30.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model-31.bin", "model.layers.30.self_attn.k_proj.weight": "pytorch_model-31.bin", "model.layers.30.self_attn.v_proj.weight": "pytorch_model-31.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model-31.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model-31.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model-31.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model-31.bin", "model.layers.30.input_layernorm.weight": "pytorch_model-31.bin", "model.layers.30.post_attention_layernorm.weight": "pytorch_model-31.bin", "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-31.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model-32.bin", "model.layers.26.self_attn.k_proj.weight": "pytorch_model-32.bin", "model.layers.26.self_attn.v_proj.weight": "pytorch_model-32.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model-32.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model-32.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model-32.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model-32.bin", "model.layers.26.input_layernorm.weight": "pytorch_model-32.bin", "model.layers.26.post_attention_layernorm.weight": "pytorch_model-32.bin", "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-32.bin"}, "metadata": {"total_size": 13476839424}}

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": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}