Initial weights/tokenizer/config upload

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": null,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f2fb318a03001f907e472be94b56fa64913a3fd84f07c03288f0c0db12dcb5
+size 939524800

model-00002-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3545c8bacc3d269a0ad7118d7357b2dd286f1cdf9de15799720510081aa7c33e
+size 872449040

model-00003-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1676f02d7b324e979d7318ddcc860d627bc43d1b8ea68edf2797f61a1dc87f95
+size 872449040

model-00004-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56fde95acfd399efa5780af15092c4cb2e28fa717765248bda16270ea6705584
+size 872449040

model-00005-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:746d141b67195319006ec5ae8d7c754e341a54c338694cdcec9adccd73d9c655
+size 872449040

model-00006-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02eb50df1297d5aa146492dd0de1ac0ed3a0ce6dd32bad10a19cb2f0c3899cb0
+size 872449040

model-00007-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555e61497d778046788c86bbeff946da0a8fd7b835e98a034c7e6d391866447d
+size 872449040

model-00008-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:318f27c662fb2d9479ef455caf04f5e3d0e8fc4bb5cf6c43a337afc638fbfd06
+size 872449040

model-00009-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da718b5c03110026cddc48475bea169dbad9cfabb7b7736157001785d024b8a
+size 872449040

model-00010-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc355fd49f7f2bf8cc39a40720b38f293134ec74fea51573bc5c8a21b9269553
+size 872449040

model-00011-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aa7377074d9c1a02f6b9819ecc97b21e7482657a00b7c935b560c0956f950f3
+size 872449056

model-00012-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363edd8d7812698fdd29b1fa755af925fedfd64c2d5043c75231cd827250feea
+size 872449048

model-00013-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce98887e8691d49ddf534224f37eab8f330dbf38986a338da5c827cb54ceba28
+size 872449048

model-00014-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b7f9eea9b7f98acc6ffc733524d5ea283dfb224d291aad34f61a58c5efa7a5
+size 872449048

model-00015-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b96e6183c1cd31457e302dfd9cda15568926ef98be05244a78e68b2d44a8ff8c
+size 872449048

model-00016-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a760169cb4c6430f4f14d1cba35220dbf0d4daa56f8918d3f8c61fc02db29a0
+size 872449048

model-00017-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a496b6cffd9abfccf6cee213349fea18ad366b9a6b2ece1497747e3f99cca26
+size 872449048

model-00018-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbce0b73c4b2a093f75b2de92119b0f47f55e2c792257fd3fe78c21aabd197f
+size 872449048

model-00019-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d7a046aa2643a471de39e8e3ee18a6bc296b49e4e89146c84d804b03727eaf
+size 872449048

model-00020-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703378e52c37c8f603df89a03accefac2dc98c24bce2ad871102393a83886e6b
+size 872449048

model-00021-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3732174d334c2585d2a0bd8dfdd432185290c67f70c4e9444bc95993071aef74
+size 872449048

model-00022-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b67d56e6caf6ecbad213a04ca445fdce22c9f1f5e8309c30b38e12a9ac36cc
+size 872449048

model-00023-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:894ef8049f8fb5f2764a0e3a25dcf7d13b00b22dd97f65b8e095f8c93c702e58
+size 872449048

model-00024-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfce9da38fbce6d7be8a5df65bcceb6715bdf13212f71d1e93e22c59fb1ee37c
+size 872449048

model-00025-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2d6ebb505add0b429fbb25892ee7c44e185987f75686a88dc36edf35433536
+size 872449048

model-00026-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d489a733957fea5bf1b7ee5d6917d7316a11557b590f4bd2870010ecbcf583
+size 872449048

model-00027-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a13b29d3e1d3b772cbe4a069f5b28c95dcde6bbbd81d1b7086544a3a3f75e1
+size 872449048

model-00028-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a1615fb7a4f8c848ff3a0f47945a45469c45f3dd9a9af1693ecb89e1e8d83b
+size 872449048

model-00029-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92774838708fac74067f5be71597a977dc88a4dc146e868b184ae29e3836cb1
+size 872449048

model-00030-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f7fc03156303d79b16ea3dbb21706b544577fb711ec450955e000e5bc0c87d
+size 872449048

model-00031-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1163334fcc2088e9a0c1388bd7e3ee27ddaf2db050a49b41fbc0fce07bfbf187
+size 872449048

model-00032-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46d8ae687db132b13fcc71008fb1ed916f0174f781a98a380df9d627d26ea285
+size 872449048

model-00033-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105f737d02460261f97b83a022a6308fbebb2c980e294c0ad09b53cae316a283
+size 469811768

model-00034-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdcc3f3446f14da1fe506fe5f1d2e7283d01f28669b2fda3e82ce1d0bea35804
+size 536871040

model.safetensors.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_parameters": 7248023552,
+    "total_size": 28992094208
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00034-of-00034.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00034.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00034.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00034.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00034.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00034.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00034.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00034.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00034.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00034.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00034.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00012-of-00034.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00034.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00013-of-00034.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00034.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00014-of-00034.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00034.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00015-of-00034.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00015-of-00034.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00016-of-00034.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00016-of-00034.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00017-of-00034.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00017-of-00034.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00018-of-00034.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00034.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00019-of-00034.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00034.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00020-of-00034.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00020-of-00034.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00021-of-00034.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00021-of-00034.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00034.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00034.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00022-of-00034.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00022-of-00034.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00023-of-00034.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00034.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00024-of-00034.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00024-of-00034.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00025-of-00034.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00025-of-00034.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00026-of-00034.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00026-of-00034.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00027-of-00034.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00027-of-00034.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00028-of-00034.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00028-of-00034.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00029-of-00034.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00029-of-00034.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00030-of-00034.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00030-of-00034.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00031-of-00034.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00031-of-00034.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00005-of-00034.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00034.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00032-of-00034.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00032-of-00034.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00033-of-00034.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00033-of-00034.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00033-of-00034.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00033-of-00034.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00006-of-00034.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00034.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00007-of-00034.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00034.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00008-of-00034.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00034.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00009-of-00034.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00034.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00010-of-00034.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00010-of-00034.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00010-of-00034.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00034.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00011-of-00034.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00034.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00034.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00034.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00034.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00034.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00034.safetensors",
+    "model.norm.weight": "model-00033-of-00034.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404