Upload 33 files

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Models/LLAMA2-13B-Holodeck-1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44af05ecb6f155bc4d98286794dbc173e48aa950474dc032d2bd899fb9daaee0
+size 962090112

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bd0550769c4016f37bc6dec4af67056f048ee2207f62ae5864abd572b00a5c
+size 985683528

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b75cf98dd295d24a1958c20c821e6f3a602fdec3f80edf69bda2e575896aa14
+size 969975360

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c4036eb0830cdff3bc9aa14c2b3ee2a6bbf407f4309e2eaaddb2141881d4d24
+size 933254616

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2123d71e013704db0e5518f478f867da2880aed88fb8b52f4c2ef83e6bc45b3b
+size 969975360

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2031f24e3bc1d64874a8bcb7c8d3531ef1d997b435d73cc680f73bb344b078ef
+size 933254616

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16dc349fa72cd06ad0720c8ebda69ad928a2c4551aa069859ced26bb50440bbe
+size 969975368

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2251b0f7535c33ed4e91b73145fcf669c2c06df907d2fedec9bc8d2019496943
+size 933254632

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd298cb2dc119bd77f4790c0e11a8d217b225013e2f299f8bd996debfb163be
+size 969975376

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf46c175710f69978df87c5067fdc5ae8208092ae09d2724fb44acd064e6aa03
+size 933254632

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9233c76d2828abe4d193ce106df567c139adb2220411daff4c34cb661f0e78d6
+size 969975376

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f46b97ab3126ef8d607e5e30bcd5e54822f7cab327d0e57e8b2c24a8a9dd8fb
+size 933254632

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:876164fff861fbc5f3283e73978ccaf79b42378bae86a735934d5bb9ae5d7863
+size 969975376

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9414e2850e0f432325cc9136698f9d8e1e75e3642d77bed78843457b790516d4
+size 933254632

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:884e0ece73bf754d3d0ab8abd0546f89f5481e1b11fb9882a07dde2fbfbf91bd
+size 969975376

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb55676a4d9af61cdf0138848ba3c7e242abe7bf220cbf1138c1df3411469925
+size 933254632

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a0e4c4446c7333bcb137abd101f5d5a05b781eefdd700e0f635cf6e4d5694b
+size 969975376

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:201546f1aca5503f0a812a738d91a7782206b4205cea0f91ed65528709a42c94
+size 933254632

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250829cd25626263a039dcd02909a3c8b1eafd7fdb63e99dca997fd3c5a3f27f
+size 969975376

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f396f873be539fab18cfe5c7e7fc482ff578e80196113804215f94c588363b25
+size 933254632

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d350ee6c1895d7f79ddf27921f95ed517607af46f97b5f9202d1b75ab281f1dd
+size 969975376

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e23f62fdfeb95d77b4b19e2e3ae2de1843ce8ea11637226ee9feec8cbba21799
+size 933254632

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5655cb602f16bdbf478e97f58ce92df67b114c3a33ad367bc051a8097075ade5
+size 969975376

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45e96394c8d1ee905a1bb1ddf7ac64efa4c0d714e0e90bd06cbc17665214032e
+size 933254632

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a514ebe1c04f0b354a98155a40f022effe357df6b71c72e71725fc22c6a7e7b8
+size 969975376

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49faaca1dce3b9e5bb7e2750966607c879b573d6cb60d7fda1d67446e713f723
+size 933254632

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c665b72516e4fc71957cc2ac32c926e6a35a171f9fcfef5f1dee1a32ed54a2c
+size 917556792

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c67541d274660ebc668b42e6644cf986ab1a67294ddebaf011a5be17273caaf
+size 327680128

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 26031728640
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00028-of-00028.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "model.norm.weight": "model-00027-of-00028.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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,36 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}