add model

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "../UltraChat/UltraLM/recover",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "mlp_bias": false,
+  "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-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 32000,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc6e31e676b3908486e3b2bc6a656716e12f63a7b240557fa047d28f7622d38b
+size 1924199568

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00860bfaac22476366b11901e72237f9a41f8cba0ae14ff43b6b15f089d6da9f
+size 1971365464

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f6b1296b18e4339daa5e3589449f3b0c23494194ed9a93e58c9396272ee837
+size 1939949136

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955e4acb5dbca8d3fbd0361e55c169d641d095f817d2644480cdb5152c0d1e83
+size 1866507752

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f228b9f570061dbe8319bf2119aaa809940efcbc8f9001a5017358be0d762d
+size 1939949136

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f9af93894c372afff13d62f314253c979e6adf8f9ba21159f33010cb3c1c4a
+size 1866507752

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97cde3ea32330ef1119dcfb9bada51a75a1a7dbcb1ea885a7d2030e977ba861d
+size 1939949144

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5c6ebebc551b7044db332d88f9cf5bd2b00372279588ae257db959a5622b1d8
+size 1866507760

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9a69626190a4787801ed33966e32b236681e83e68a484bc6a29f76aed5ffbc
+size 1939949152

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f66a8e91f0928f531441bbbf3b7840cc293b9f4e48e243a1818ca3213abe46f
+size 1866507760

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f0ac766844629bac229adb6ba8d10356066e98e2a358583087b191aeb579f7
+size 1939949152

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566e14e6c7375a4bc331822bc858f5f09f46362339a2dc60fd59976c61530b98
+size 1866507760

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1397084348b0f1861980ca0598b75a30d22fc77c729e4bc64e51927bd24380ca
+size 1939949152

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd772064e4aec7201d2f20a8a3d18c530816fdc68651ffcc04c6ac45d73dca1b
+size 1866507760

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94bfb318d511b9387a34793270913684d0bffcd00ad2ab26d9dc40f159f01b1
+size 1939949152

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca3d39c0c243553b6e2ef882dd4e9ffc8c0eb22c8fcc4c4d80f42bc3be6c2ef
+size 1866507760

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6df6913bdf012ea1b3c4f4ca183380b87534d0512c7ec554b9fefe1891f22f5f
+size 1939949152

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a2481638e1cc317a65bccbce97d53aab1895c4db5a4d4fd4b73b9ece9a37c2
+size 1866507760

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c96710f584f3f5ea317a63e3d4ee4ff0c0e22d172eac7b9a713d01dfcac1d02
+size 1939949152

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7295fee169d994780b79213c0065dd16e5b6afa1aa1d3ed79aa8a6a31e2290c1
+size 1866507760

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e269c9d384a640da7a1d4992cda824d400d33fc410aec6264448c053b040bd5c
+size 1939949152

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab5987eeea150f9d84eb5bc81795f9e57c5a766cc8fa95d74d3476ad74d381f
+size 1866507760

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e557584012707b5937ed61472f5e347e72af0b8de429d8a1f480a5c69ffcb47
+size 1939949152

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3feea1ec38216b0969c8510b7c18396b2cf5d433f688c8b6be3d8ce22ab07597
+size 1866507760

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f9f7b8e860060de0ae910b4b35ee29bf425fa24f59974ac5fcdf70f74c2a5d
+size 1939949152

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b4ed537ec3c74e502ef22955eb43d8df0f01df5a66f6d7a1ed8f735e21b3b73
+size 1866507760

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b3a02fc3f441b310b915e00ffc3a99933659e7f9b41143d3d218311f2537b6
+size 1835112008

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa3b3b4e27806c4b6d8d61a88b8284710b7669aaa2017b3fe47194df799e83c
+size 655380608

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 52063498240
+  },
+  "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 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eac72d61bad39200895b6aaf0a0b7f9554e719559b9cdbad3b00fcbd25a8778
+size 3619194

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}