初始化项目，由ModelHub XC社区提供模型

Model: vihangd/smartyplats-7b-v1
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,11 @@
+---
+license: apache-2.0
+---
+<p><h1> SmartyPlats-7b </h1></p>
+An experimental finetune of Mistrel 7b with QLoRA
+
+<h2> Datasets </h2>
+Trained on alpca style datasets
+
+<p><h2> Prompt Template </h2></p>
+Uses alpaca style prompt template

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.0.dev0"
+}

pytorch_model-00001-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8edbc85103b55b0782a1dedc262aa5478f8a4ecd9bd19df92e0975d6e28fc00f
+size 346032713

pytorch_model-00002-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b85609b5c38cfdca156b5e223b1d916c6061caf6a21fe19a4404261fbffa8c6
+size 394284267

pytorch_model-00003-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d554cfbae44c7adb721bb5381f6afdcc207ec73835394726e90990b2fc61b29d
+size 394284267

pytorch_model-00004-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988105c0c0d5a8604c47da9ad79bba4b62fca9501a8da02cf8f356ff6a19f370
+size 318770074

pytorch_model-00005-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a294ebf4f7902a26ff9a015156176ae711a29787fd4c53f377c1b77d90fc28dc
+size 318787068

pytorch_model-00006-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63506e11c3fc663f7d768f8cec7531d2bd4bc8b7fb1b29a4c8125caabe48cc1a
+size 318787068

pytorch_model-00007-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb52c448d772c790f1570eb90ec34cab59e42fc11fa1103aebd74cfaf4aa8af
+size 394284267

pytorch_model-00008-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db010059f6ed533ff3d98fbd66f0b07fbdc4dbdfbcf8a79765d0fdad8b7c6c2e
+size 394284267

pytorch_model-00009-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf688da85933f7da0e3937c65627b19850e89648a8bf7b4e9704ddcdc123150
+size 318770074

pytorch_model-00010-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47d3a8989b5bd1e524263aa4b0dfe66ee7808a8521d11fc02e4a7a03cf237218
+size 318787068

pytorch_model-00011-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a017e14b19dc11606b80284f598cc4733642381a787046d9bf408f87bbd39fcb
+size 318787068

pytorch_model-00012-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b513d5a4037ae9c0c0c916f89ca10fb6167fe3d1528aa087c3cfbdaea3a395
+size 394284267

pytorch_model-00013-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da15eaa3767b9fad47c7900972c6658cebd035aa1729b2e4d648f69e0212e70
+size 394284267

pytorch_model-00014-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0ea40d50ffd062e750073414852d7d070ed45bab82877d30bf2d39f88144da
+size 318770074

pytorch_model-00015-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d949e98c80eb53d0928fc677c0f098be14da619b49249f463944f120dab1777a
+size 318787068

pytorch_model-00016-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf26c83f81b9eee8545b68d07097c06577ccd62ab4eaff1d0303514322a9718f
+size 318787068

pytorch_model-00017-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d098b2369da6dcba69fc274d28bedb093708c4b217dd32067c5d34bc38d80d5
+size 394284267

pytorch_model-00018-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a4d6e1b5049fa8239c2822545bfef82f4b02f9887c276bddaddfb9a1fed91b
+size 394284267

pytorch_model-00019-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81334fca855806d7d277fc0ef03e877abf10b4e84a3e8b6f6a8220d21c8a562
+size 318770074

pytorch_model-00020-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405a3fb7fe56a34f2739d0de19767ee3f56b94d7dd68334c0c79dc2eb7897bbe
+size 318787068

pytorch_model-00021-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b487c643c736d15ee977ca0bfe096d3da42c5906f8d530a47a220c7d60d1eb
+size 318787068

pytorch_model-00022-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d9c02d67822d7ad495e2b270f1eafb4d33d801c027bd24c1bcbdc5358a0bf2
+size 394284267

pytorch_model-00023-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bbc4cd200e5ef294cbe1e9fb2e00d73c1e71ba6244d041439d3d2aa9a3fe4a8
+size 394284267

pytorch_model-00024-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70237cf03992f68eab15244a49e5f4e6047eec9bd8cf77bee271ed0d97de1e99
+size 318770074

pytorch_model-00025-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef4d8066a06f019440a4272ce5d315fbca149988e22a1d3af548268e8b1d611
+size 318787068

pytorch_model-00026-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ba96b41bc1906ecf057b81fb31ac1cc95dc85631e6d3507a198920d607bdda
+size 318787068

pytorch_model-00027-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e000a6d0db66ada575a0a27113525c829335b5ae1d0e49771c63f9f9cec947
+size 394284267

pytorch_model-00028-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c47756a7bc494d8eb86338040b08fde193a8adc141369c34d4f9f5807f525c
+size 394284267

pytorch_model-00029-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b4e14a445d094d091831105828bbf47aa731b03d4ea8676922d49bae8898cf
+size 318770074

pytorch_model-00030-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc40b814770de7804babf4632cc06bc4dd977b6c41ce0763ba56dd2e37510e29
+size 318787068

pytorch_model-00031-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18da0705e940b8f7acccadb96d6ff495118e149ea0957a7f1da6f8de3655d0bd
+size 318787068

pytorch_model-00032-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c15ed0e47dc71e8879ef01efb4db86bda5953fa0f5dcd75a24e230412566bd
+size 394284267

pytorch_model-00033-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1daf27bc05daf026a27bac0e19737cb8f1d64998da8b5d16fcdba3388999b6af
+size 394284267

pytorch_model-00034-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f1ceb9aa75cf62ce96f5c9287050ced0f0c7f98c461d26e993d249e204a427
+size 318770074

pytorch_model-00035-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c1d6f8b417b101342c76e4915364b1e98b561eb08a383da2d968625bd549c4f
+size 318787068

pytorch_model-00036-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5c85ae60c4b17b3cd7461b2c40734bfc4c395fa83bc64c548e1d4551359a33
+size 318787068

pytorch_model-00037-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810a9ff7822a8d9416779c19328805af7732390552544c1e0e2e17d4bb6f1e90
+size 394284267

pytorch_model-00038-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b227145e3281e878f1727a3ef079f6c6e169ea9071501c7e2b13bf409c937d9
+size 394284267

pytorch_model-00039-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa564d675443717388cc8f09d004fec9caf310633effbbbc301e959d63de8210
+size 318770074

pytorch_model-00040-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:987d4af2f6a6732249407301a2388b8288d22ccc7d6a2739ff221f2dacdc0988
+size 318787068

pytorch_model-00041-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3991ce31816cb2d9d0a49789d9a3e49387ba1686c43625c72302dd32b4f67742
+size 234908233

pytorch_model-00042-of-00042.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72fe52df156061bcea5861a655359978f29b406c487b7d039f22f6e1c77dda31
+size 262145413

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00042-of-00042.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00042.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00042.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00042.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00042.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00042.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00042.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00042.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00042.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00042.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00042.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00042.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00042.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00042.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00042.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00042.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00042.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00042.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00042.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00042.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00015-of-00042.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00015-of-00042.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00014-of-00042.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00014-of-00042.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00015-of-00042.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00014-of-00042.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00014-of-00042.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00014-of-00042.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00014-of-00042.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00016-of-00042.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00016-of-00042.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00015-of-00042.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00016-of-00042.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00016-of-00042.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00015-of-00042.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00015-of-00042.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00015-of-00042.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00015-of-00042.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00017-of-00042.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00017-of-00042.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00017-of-00042.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00017-of-00042.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00017-of-00042.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00016-of-00042.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00016-of-00042.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00016-of-00042.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00016-of-00042.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00018-of-00042.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00018-of-00042.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00018-of-00042.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00018-of-00042.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00018-of-00042.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00017-of-00042.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00018-of-00042.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00017-of-00042.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00018-of-00042.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00020-of-00042.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00020-of-00042.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00019-of-00042.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00019-of-00042.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00020-of-00042.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00019-of-00042.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00019-of-00042.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00019-of-00042.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00019-of-00042.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00021-of-00042.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00021-of-00042.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00020-of-00042.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00021-of-00042.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00021-of-00042.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00020-of-00042.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00020-of-00042.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00020-of-00042.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00020-of-00042.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00022-of-00042.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00022-of-00042.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00022-of-00042.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00022-of-00042.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00022-of-00042.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00021-of-00042.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00021-of-00042.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00021-of-00042.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00021-of-00042.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00023-of-00042.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00023-of-00042.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00023-of-00042.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00023-of-00042.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00023-of-00042.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00022-of-00042.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00023-of-00042.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00022-of-00042.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00023-of-00042.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00025-of-00042.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00025-of-00042.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00024-of-00042.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00024-of-00042.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00025-of-00042.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00024-of-00042.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00024-of-00042.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00024-of-00042.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00024-of-00042.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00026-of-00042.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00026-of-00042.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00025-of-00042.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00026-of-00042.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00026-of-00042.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00025-of-00042.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00025-of-00042.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00025-of-00042.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00025-of-00042.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00005-of-00042.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00005-of-00042.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00042.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00042.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00005-of-00042.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00004-of-00042.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00042.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00004-of-00042.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00042.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00027-of-00042.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00027-of-00042.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00027-of-00042.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00027-of-00042.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00027-of-00042.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00026-of-00042.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00026-of-00042.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00026-of-00042.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00026-of-00042.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00028-of-00042.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00028-of-00042.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00028-of-00042.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00028-of-00042.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00028-of-00042.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00027-of-00042.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00028-of-00042.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00027-of-00042.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00028-of-00042.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00030-of-00042.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00030-of-00042.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00029-of-00042.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00029-of-00042.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00030-of-00042.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00029-of-00042.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00029-of-00042.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00029-of-00042.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00029-of-00042.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00031-of-00042.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00031-of-00042.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00030-of-00042.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00031-of-00042.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00031-of-00042.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00030-of-00042.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00030-of-00042.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00030-of-00042.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00030-of-00042.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00032-of-00042.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00032-of-00042.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00032-of-00042.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00032-of-00042.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00032-of-00042.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00031-of-00042.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00031-of-00042.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00031-of-00042.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00031-of-00042.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00033-of-00042.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00033-of-00042.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00033-of-00042.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00033-of-00042.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00033-of-00042.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00032-of-00042.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00033-of-00042.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00032-of-00042.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00033-of-00042.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00035-of-00042.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00035-of-00042.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00034-of-00042.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00034-of-00042.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00035-of-00042.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00034-of-00042.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00034-of-00042.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00034-of-00042.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00034-of-00042.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00036-of-00042.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00036-of-00042.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00035-of-00042.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00036-of-00042.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00036-of-00042.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00035-of-00042.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00035-of-00042.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00035-of-00042.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00035-of-00042.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00037-of-00042.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00037-of-00042.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00037-of-00042.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00037-of-00042.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00037-of-00042.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00036-of-00042.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00036-of-00042.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00036-of-00042.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00036-of-00042.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00038-of-00042.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00038-of-00042.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00038-of-00042.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00038-of-00042.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00038-of-00042.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00037-of-00042.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00038-of-00042.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00037-of-00042.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00038-of-00042.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00006-of-00042.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00006-of-00042.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00042.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00006-of-00042.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00006-of-00042.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00005-of-00042.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00005-of-00042.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00005-of-00042.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00005-of-00042.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00040-of-00042.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00040-of-00042.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00039-of-00042.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00039-of-00042.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00040-of-00042.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00039-of-00042.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00039-of-00042.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00039-of-00042.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00039-of-00042.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00041-of-00042.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00041-of-00042.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00040-of-00042.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00041-of-00042.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00041-of-00042.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00040-of-00042.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00040-of-00042.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00040-of-00042.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00040-of-00042.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00042.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00007-of-00042.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00007-of-00042.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00042.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00042.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00006-of-00042.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00006-of-00042.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00006-of-00042.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00006-of-00042.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00042.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00042.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00008-of-00042.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00042.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00042.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00007-of-00042.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00008-of-00042.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00007-of-00042.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00008-of-00042.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00010-of-00042.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00010-of-00042.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00042.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00042.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00010-of-00042.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00009-of-00042.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00009-of-00042.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00009-of-00042.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00009-of-00042.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00011-of-00042.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00011-of-00042.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00042.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00011-of-00042.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00011-of-00042.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00010-of-00042.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00042.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00010-of-00042.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00010-of-00042.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00012-of-00042.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00012-of-00042.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00012-of-00042.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00012-of-00042.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00012-of-00042.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00011-of-00042.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00042.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00011-of-00042.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00042.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00013-of-00042.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00013-of-00042.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00013-of-00042.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00013-of-00042.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00013-of-00042.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00042.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00013-of-00042.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00012-of-00042.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00013-of-00042.bin",
+    "model.norm.weight": "pytorch_model-00041-of-00042.bin"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}