Upload folder using huggingface_hub

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bigcode/starcoder2-15b",
+  "architectures": [
+    "Starcoder2ForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "embedding_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 6144,
+  "initializer_range": 0.01275,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 16384,
+  "mlp_type": "default",
+  "model_type": "starcoder2",
+  "norm_epsilon": 1e-05,
+  "norm_type": "layer_norm",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 4,
+  "residual_dropout": 0.1,
+  "rope_theta": 100000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.41.1"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a6c8d2ab575c01b48bf9bbb4fc0fe77a991fb1262012261d8173e4ff3ee1e4
+size 4605952488

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a10450dc4df64c0b4f133cf1de12d7e2f97cca7ae0b58b0a56fc5b3508b7a0f
+size 4606174416

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3823c614622b2154e701588db30756580255bbdb6d0034c1096c7f8c8b4301
+size 4606174416

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71b60c4bb2206c450a926f28846ca372f2f9d903b0b253d8642fa38efd76fb6
+size 4606174440

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8383620ce5a9af140308ebedf39ab86685dbc156f93068ce6e517fb95990bcc
+size 4606174464

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7ebc81ebe8aae3afe21488c5ad3cc32ed1671d14841001e532db7ba043a532
+size 4606174464

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d26978d897d1374b3a696f5a8a48c5a3d14defbe97c480db28824cd828e587ed
+size 4606174464

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cedcf14b537cab2c6f6dae029595baeded07b42e609663701d003f5150e8d8f
+size 4606174464

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b96a7da3a0e125a0b6f946a98ae9800fd07071da5b3e8f63b087063eeed27b80
+size 4606174464

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23009bd4f29567a939197511b5598f3665ae53644540351a632326e9c283dd03
+size 4606174464

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cccd9faa850d363274feba0d61dea504208041c3ef363af38fdd80f68ee10c
+size 4606174464

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421e6055b22e3a10256141b34df251ec1e43ecee2b009f23687b96e4fa9afca0
+size 4606174464

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5067908b07ff42dd30c8f8ffa3f5199b6247b2f7c4e15b18e0ac41d6c57af4c5
+size 4606174464

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b1c1091bae5bb6e96b792fca53296f4c9483a51b6e391c09a61dd2f3df2f78
+size 3951582120

model.safetensors.index.json

@@ -0,0 +1,651 @@
+{
+  "metadata": {
+    "total_size": 63831556096
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.c_fc.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.c_fc.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.c_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.c_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.c_fc.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.c_fc.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.c_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.c_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00004-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mlp.c_fc.bias": "model-00004-of-00014.safetensors",
+    "model.layers.10.mlp.c_fc.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mlp.c_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.10.mlp.c_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00005-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.mlp.c_fc.bias": "model-00005-of-00014.safetensors",
+    "model.layers.11.mlp.c_fc.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.mlp.c_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.11.mlp.c_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00005-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mlp.c_fc.bias": "model-00005-of-00014.safetensors",
+    "model.layers.12.mlp.c_fc.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mlp.c_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.12.mlp.c_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00005-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mlp.c_fc.bias": "model-00005-of-00014.safetensors",
+    "model.layers.13.mlp.c_fc.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mlp.c_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.13.mlp.c_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00006-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.mlp.c_fc.bias": "model-00006-of-00014.safetensors",
+    "model.layers.14.mlp.c_fc.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.mlp.c_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.14.mlp.c_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00006-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.mlp.c_fc.bias": "model-00006-of-00014.safetensors",
+    "model.layers.15.mlp.c_fc.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.mlp.c_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.15.mlp.c_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00006-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.mlp.c_fc.bias": "model-00006-of-00014.safetensors",
+    "model.layers.16.mlp.c_fc.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.mlp.c_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.16.mlp.c_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00007-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.mlp.c_fc.bias": "model-00007-of-00014.safetensors",
+    "model.layers.17.mlp.c_fc.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.mlp.c_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.17.mlp.c_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00007-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.mlp.c_fc.bias": "model-00007-of-00014.safetensors",
+    "model.layers.18.mlp.c_fc.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.mlp.c_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.18.mlp.c_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00007-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mlp.c_fc.bias": "model-00007-of-00014.safetensors",
+    "model.layers.19.mlp.c_fc.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mlp.c_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.19.mlp.c_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.c_fc.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.c_fc.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.c_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.c_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00008-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.mlp.c_fc.bias": "model-00008-of-00014.safetensors",
+    "model.layers.20.mlp.c_fc.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.mlp.c_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.20.mlp.c_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00008-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.mlp.c_fc.bias": "model-00008-of-00014.safetensors",
+    "model.layers.21.mlp.c_fc.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.mlp.c_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.21.mlp.c_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00008-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mlp.c_fc.bias": "model-00008-of-00014.safetensors",
+    "model.layers.22.mlp.c_fc.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mlp.c_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.22.mlp.c_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00009-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.mlp.c_fc.bias": "model-00009-of-00014.safetensors",
+    "model.layers.23.mlp.c_fc.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.mlp.c_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.23.mlp.c_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00009-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mlp.c_fc.bias": "model-00009-of-00014.safetensors",
+    "model.layers.24.mlp.c_fc.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mlp.c_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.24.mlp.c_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00009-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.mlp.c_fc.bias": "model-00009-of-00014.safetensors",
+    "model.layers.25.mlp.c_fc.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.mlp.c_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.25.mlp.c_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00010-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.mlp.c_fc.bias": "model-00010-of-00014.safetensors",
+    "model.layers.26.mlp.c_fc.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.mlp.c_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.26.mlp.c_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00010-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mlp.c_fc.bias": "model-00010-of-00014.safetensors",
+    "model.layers.27.mlp.c_fc.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mlp.c_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.27.mlp.c_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00010-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.mlp.c_fc.bias": "model-00010-of-00014.safetensors",
+    "model.layers.28.mlp.c_fc.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.mlp.c_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.28.mlp.c_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00011-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.mlp.c_fc.bias": "model-00011-of-00014.safetensors",
+    "model.layers.29.mlp.c_fc.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.mlp.c_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.29.mlp.c_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.c_fc.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.c_fc.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.c_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.c_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00011-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mlp.c_fc.bias": "model-00011-of-00014.safetensors",
+    "model.layers.30.mlp.c_fc.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mlp.c_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.30.mlp.c_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00011-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.mlp.c_fc.bias": "model-00011-of-00014.safetensors",
+    "model.layers.31.mlp.c_fc.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.mlp.c_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.31.mlp.c_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.input_layernorm.bias": "model-00012-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.mlp.c_fc.bias": "model-00012-of-00014.safetensors",
+    "model.layers.32.mlp.c_fc.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.mlp.c_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.32.mlp.c_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.33.input_layernorm.bias": "model-00012-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.mlp.c_fc.bias": "model-00012-of-00014.safetensors",
+    "model.layers.33.mlp.c_fc.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.mlp.c_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.33.mlp.c_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.input_layernorm.bias": "model-00012-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mlp.c_fc.bias": "model-00012-of-00014.safetensors",
+    "model.layers.34.mlp.c_fc.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mlp.c_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.34.mlp.c_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.input_layernorm.bias": "model-00013-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.mlp.c_fc.bias": "model-00013-of-00014.safetensors",
+    "model.layers.35.mlp.c_fc.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.mlp.c_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.35.mlp.c_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.36.input_layernorm.bias": "model-00013-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.mlp.c_fc.bias": "model-00013-of-00014.safetensors",
+    "model.layers.36.mlp.c_fc.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.mlp.c_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.36.mlp.c_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.input_layernorm.bias": "model-00013-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.mlp.c_fc.bias": "model-00013-of-00014.safetensors",
+    "model.layers.37.mlp.c_fc.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.mlp.c_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.37.mlp.c_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.input_layernorm.bias": "model-00014-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.mlp.c_fc.bias": "model-00014-of-00014.safetensors",
+    "model.layers.38.mlp.c_fc.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.mlp.c_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.38.mlp.c_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.bias": "model-00014-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.39.input_layernorm.bias": "model-00014-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.mlp.c_fc.bias": "model-00014-of-00014.safetensors",
+    "model.layers.39.mlp.c_fc.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.mlp.c_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.39.mlp.c_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.bias": "model-00014-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.c_fc.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.c_fc.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.c_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.c_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00003-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.mlp.c_fc.bias": "model-00003-of-00014.safetensors",
+    "model.layers.5.mlp.c_fc.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.mlp.c_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.5.mlp.c_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00003-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.c_fc.bias": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.c_fc.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.c_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.c_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.c_fc.bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.c_fc.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.c_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.c_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00004-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mlp.c_fc.bias": "model-00004-of-00014.safetensors",
+    "model.layers.8.mlp.c_fc.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mlp.c_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.8.mlp.c_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00004-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.mlp.c_fc.bias": "model-00004-of-00014.safetensors",
+    "model.layers.9.mlp.c_fc.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.mlp.c_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.9.mlp.c_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.norm.bias": "model-00014-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,63 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,356 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}