Upload folder using huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/raid/viethq5/projects/mergekit/best_model_now",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "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": "4.34.1",
+  "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": "4.34.1"
+}

pytorch_model-00001-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67ff668c6424090bb598a2eba040d9a1c1258e70cf228409bc87395005c9d01
+size 899700344

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6209bf34ff53cd8f8f44c80fe7dc6e101220cac4b5121ff649e07be335f13c
+size 989895552

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d6ae1899f91e9e08b7575bb53c900ad5577e43e45fa1f1f241037f612638b5e
+size 989912548

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43ccc7a9f0c7cb33d2f5d49d4583ca75ace2f7acd61eebbc4c7253ab535879b
+size 956342070

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6cb56b02ed6d41f4c8356576bcc1192456252794450848a504207d4763f88b
+size 989895552

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd695c92a77e44b92f2ce2c3f047f4aa8e54081823c6f3fd8ab397e70033a0ef
+size 989895552

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:262a11867c597ffef196cdf281cd4088d973fdaac806326954c0676fd0f3bac9
+size 989912548

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af9ffe229292e678acab0021644b95f7317b758d7161b6dc914978c0d9230632
+size 956342070

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272d5eb07191246c473a6e6d235019e7ff13d301a7a4661675296f41746df6d1
+size 989895552

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a56d93cc5699aef6f1b00493bc04f261fb42425073d46c4c9178f6a499ebf6
+size 989895552

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80c8ecf7bc15d73bb8763475b1e0f566105d424eda01ba06ee818ce83c88348d
+size 989912548

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f83a772595ca42f86a52e44ac2a75e611a72d16a365b380024671b5a1686f73
+size 956342070

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfcf3f950773a3d37ceebe481185970c334abae38afc628e33f8a7f064927aa2
+size 989895552

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2d5080bd2cb52e355264b27a4c8a17ed292a13dcecc8cceb9bf3909df9ca480
+size 989895552

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e52e3e483d39c55d21c0b736e78f00298581eafdf39f5403d5b889e221e38d3e
+size 815838502

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00015-of-00015.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.norm.weight": "pytorch_model-00015-of-00015.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}