Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/notebooks/35b",
+  "architectures": [
+    "CohereForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_cohere.CohereConfig",
+    "AutoModel": "configuration_cohere.CohereModel",
+    "AutoModelForCausalLM": "modeling_cohere.CohereForCausalLM"
+  },
+  "bos_token_id": 5,
+  "eos_token_id": 6,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22528,
+  "layer_norm_eps": 1e-05,
+  "logit_scale": 0.0625,
+  "max_position_embeddings": 150000,
+  "model_type": "cohere",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 64,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 8000000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "35b",
+  "architectures": [
+    "CohereForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_cohere.CohereConfig",
+    "AutoModel": "configuration_cohere.CohereModel",
+    "AutoModelForCausalLM": "modeling_cohere.CohereForCausalLM"
+  },
+  "bos_token_id": 5,
+  "eos_token_id": 6,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22528,
+  "layer_norm_eps": 1e-05,
+  "logit_scale": 0.0625,
+  "max_position_embeddings": 8192,
+  "model_type": "cohere",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 64,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 8000000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 5,
+  "eos_token_id": 6,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5428fa31fd03765d5c0eb14d3680ba058ee1e0eca4b25140092bb9d669914bbf
+size 4731175520

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d70c9ce69e42faf9616e1bda1448c2766f00fcaa20800d3beda8302cbb8e5c
+size 4932553440

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f1162a4f10ebf07324293635b6b9ee3509a835dc47a409abd87b92203f4d26
+size 4932553440

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d3d16b8c67947bbfbd37c3b235f50337aa4e0b8450a5c1f21d216bb75456e59
+size 4932553440

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120a4429056e6efd04b1d2756b3e625bd829c4b458203d1cbf1e2e8a7b678489
+size 4932553464

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478c89965e4390aa458d52bbef525f95cb69eb277db1f8454ad3b0dbd8b52b7c
+size 4932553464

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d71536b1c2a5c33f27330b19010f7493c1599898207dc57aa1e7e38767a4c2b
+size 4932553464

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57a64b41fcf22f9fd4855f542dac9d99aae242c9ad1245d34d2b71c428fe32aa
+size 4932553464

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad83531189bb6d9456710a903396ec02987be03f6539048b85f1ac25a01dd10
+size 4932553464

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18986af87bed9d98c7b9deff616540b7721c379113668191bf8f848e5a050fc
+size 4932553464

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac15fdc4368f7a3532b7e114938aa5e8e50db07f01962bc3801240b9939d9c1
+size 4932553464

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9ae9ccf809835bfd3c3466c80b1377da957896b34a7090614a508220bd7c1df
+size 4932553464

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b058ba038b230322ef83091c8a91731d384eb6ca11058a9f5df38a7c3da3df83
+size 4932553464

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6db7c3e17ce948ac5202197613ad977a2dd6a8e474e30076f5146571a4a0a4
+size 4932553464

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1fabad5e9533b25b07d107ba37c5f580bc7a8c1871b794baefdae3fa976b76
+size 1107329592

model.safetensors.index.json

@@ -0,0 +1,329 @@
+{
+  "metadata": {
+    "total_size": 69961662464
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.norm.weight": "model-00015-of-00015.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
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec24d1fe80ac960489b2004b7399ea561799de2fae774bd5a9234c13e6a0726
+size 12777306

tokenizer_config.json

@@ -0,0 +1,314 @@
+{
+    "add_bos_token": true,
+    "add_eos_token": false,
+    "added_tokens_decoder": {
+      "0": {
+        "content": "<PAD>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "1": {
+        "content": "<UNK>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "2": {
+        "content": "<CLS>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "3": {
+        "content": "<SEP>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "4": {
+        "content": "<MASK_TOKEN>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "5": {
+        "content": "<s>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "6": {
+        "content": "</s>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "7": {
+        "content": "<EOP_TOKEN>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "255000": {
+        "content": "<|im_start|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255001": {
+        "content": "<|im_end|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255002": {
+        "content": "<|YES_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255003": {
+        "content": "<|NO_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255004": {
+        "content": "<|GOOD_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255005": {
+        "content": "<|BAD_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255006": {
+        "content": "<|USER_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255007": {
+        "content": "<|CHATBOT_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255008": {
+        "content": "<|SYSTEM_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255009": {
+        "content": "<|USER_0_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255010": {
+        "content": "<|USER_1_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255011": {
+        "content": "<|USER_2_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255012": {
+        "content": "<|USER_3_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255013": {
+        "content": "<|USER_4_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255014": {
+        "content": "<|USER_5_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255015": {
+        "content": "<|USER_6_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255016": {
+        "content": "<|USER_7_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255017": {
+        "content": "<|USER_8_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255018": {
+        "content": "<|USER_9_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255019": {
+        "content": "<|EXTRA_0_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255020": {
+        "content": "<|EXTRA_1_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255021": {
+        "content": "<|EXTRA_2_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255022": {
+        "content": "<|EXTRA_3_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255023": {
+        "content": "<|EXTRA_4_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255024": {
+        "content": "<|EXTRA_5_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255025": {
+        "content": "<|EXTRA_6_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255026": {
+        "content": "<|EXTRA_7_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255027": {
+        "content": "<|EXTRA_8_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255028": {
+        "content": "<|EXTRA_9_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      }
+    },
+    "bos_token": "<s>",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "</s>",
+    "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}",
+    "legacy": true,
+    "model_max_length": 1000000000000000019884624838656,
+    "pad_token": "<PAD>",
+    "sp_model_kwargs": {},
+    "spaces_between_special_tokens": false,
+    "tokenizer_class": "LlamaTokenizer",
+    "unk_token": null,
+    "use_default_system_prompt": false
+  }