Upload folder using huggingface_hub

README.md

@@ -1,3 +1,28 @@
 ---
-license: mit
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
 ---
+# SMAUGZILLA-77B
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+ The base model was [Smaug-72](https://huggingface.co/abacusai/Smaug-72B-v0.1).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* /home/ubuntu/nvm/smaug
+* /home/ubuntu/nvm/minismaug
+
+
+
+

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/ubuntu/smaug",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 85,
+  "num_key_value_heads": 64,
+  "pad_token_id": 151643,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "seq_length": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.1",
+  "use_cache": true,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+dtype: float16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 69]
+    model:
+      model:
+        path: /home/ubuntu/nvm/smaug
+- sources:
+  - layer_range: [8, 24]
+    model:
+      model:
+        path: /home/ubuntu/nvm/minismaug

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50bc54a5ffad5ae4a3b796fe1e2fc27409649ad70c14150c002911e5aaeea410
+size 9873494568

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88067c9185b21229d704bddf1e5039ed9d5536011e801fb8830469ba7f9bde16
+size 9873543312

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148aac86f8a8354e3d29fe4b5eec7f190ad41d5eede6c37e311d2f7e42c4065e
+size 9663911808

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb50905041a91b3615b594bd1bf80a20d744753118de045775e0f3c034bd9583
+size 9932281736

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f06e4028759940078661c67f0ea8f9e16ac589fc67a8be8eb9d599f225c3fac
+size 9932314280

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1206c9def63a149b98346d4b0e0583161698dd05605860480aa05bfcb4d1e052
+size 9932281520

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d6af381184f0b4ddb820cf3ae68e8c0473da0ecfe1ad28cb6dcdbc90f3a65a
+size 9798096912

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09feb1f1626cf248d15caae3c6182e32c825326a07c838b9bbbde99a7e42bacb
+size 9663878592

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d5b5e3d832cf1143782c39481b7651d7018c086b5f2e9be7ecc3523738df62
+size 9798064152

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b1990757e2be6545036ebe346a9576f421a47520045496eda507f12bec2cb2
+size 9663878592

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ecbaf89e51eeffab1615d37c211e8dd8cc5f9ea4d8024501a793289f150b89
+size 9932281520

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dea0e34102eaa14d705ec5f97740354fd3651b2abfc2443ff0e3a22d0e7354ad
+size 9798096912

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf55bc3405fbcdbb729d6ffa50785c6e784d87896a77faa1ef028b592e67709
+size 9663878592

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4ed0c555ce9d726a77163cd9da999babb7ae7be4005da2b55f268243c20904
+size 9798064152

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e10fd541679d5983147f41e1a4b10ef66a674c51f393a92b464896f23110d1a
+size 9663878592

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b99bbf50cd5fba097c3a1945c5097bc2878f543e32486463509bb5693574a9
+size 6308368128

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.embed_tokens.weight": "model-00001-of-00016.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.79.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.78.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00016.safetensors", "lm_head.weight": "model-00002-of-00016.safetensors", "model.norm.weight": "model-00002-of-00016.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.84.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.83.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.82.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.81.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.80.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.35.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.40.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.44.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.48.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.46.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.50.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.49.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.53.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.52.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.51.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.56.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.55.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.54.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.59.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.58.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.57.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.62.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.61.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.60.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.64.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.63.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.67.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.66.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.65.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.70.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.69.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.68.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.73.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.72.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.71.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.76.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.75.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.74.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.77.input_layernorm.weight": "model-00016-of-00016.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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 +1,1675 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|extra_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|extra_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|extra_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|extra_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|extra_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|extra_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|extra_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|extra_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|extra_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|extra_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|extra_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<|extra_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151658": {
+      "content": "<|extra_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151659": {
+      "content": "<|extra_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151660": {
+      "content": "<|extra_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151661": {
+      "content": "<|extra_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151662": {
+      "content": "<|extra_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151663": {
+      "content": "<|extra_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151664": {
+      "content": "<|extra_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151665": {
+      "content": "<|extra_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<|extra_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<|extra_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<|extra_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "<|extra_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|extra_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|extra_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<|extra_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<|extra_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<|extra_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<|extra_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151676": {
+      "content": "<|extra_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151677": {
+      "content": "<|extra_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151678": {
+      "content": "<|extra_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151679": {
+      "content": "<|extra_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151680": {
+      "content": "<|extra_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151681": {
+      "content": "<|extra_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151682": {
+      "content": "<|extra_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151683": {
+      "content": "<|extra_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151684": {
+      "content": "<|extra_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151685": {
+      "content": "<|extra_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151686": {
+      "content": "<|extra_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151687": {
+      "content": "<|extra_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151688": {
+      "content": "<|extra_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151689": {
+      "content": "<|extra_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151690": {
+      "content": "<|extra_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151691": {
+      "content": "<|extra_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151692": {
+      "content": "<|extra_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151693": {
+      "content": "<|extra_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151694": {
+      "content": "<|extra_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151695": {
+      "content": "<|extra_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151696": {
+      "content": "<|extra_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151697": {
+      "content": "<|extra_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151698": {
+      "content": "<|extra_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151699": {
+      "content": "<|extra_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151700": {
+      "content": "<|extra_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151701": {
+      "content": "<|extra_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151702": {
+      "content": "<|extra_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151703": {
+      "content": "<|extra_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151704": {
+      "content": "<|extra_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151705": {
+      "content": "<|extra_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151706": {
+      "content": "<|extra_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151707": {
+      "content": "<|extra_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151708": {
+      "content": "<|extra_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151709": {
+      "content": "<|extra_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151710": {
+      "content": "<|extra_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151711": {
+      "content": "<|extra_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151712": {
+      "content": "<|extra_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151713": {
+      "content": "<|extra_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151714": {
+      "content": "<|extra_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151715": {
+      "content": "<|extra_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151716": {
+      "content": "<|extra_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151717": {
+      "content": "<|extra_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151718": {
+      "content": "<|extra_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151719": {
+      "content": "<|extra_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151720": {
+      "content": "<|extra_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151721": {
+      "content": "<|extra_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151722": {
+      "content": "<|extra_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151723": {
+      "content": "<|extra_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151724": {
+      "content": "<|extra_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151725": {
+      "content": "<|extra_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151726": {
+      "content": "<|extra_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151727": {
+      "content": "<|extra_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151728": {
+      "content": "<|extra_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151729": {
+      "content": "<|extra_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151730": {
+      "content": "<|extra_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151731": {
+      "content": "<|extra_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151732": {
+      "content": "<|extra_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151733": {
+      "content": "<|extra_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151734": {
+      "content": "<|extra_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151735": {
+      "content": "<|extra_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151736": {
+      "content": "<|extra_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151737": {
+      "content": "<|extra_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151738": {
+      "content": "<|extra_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151739": {
+      "content": "<|extra_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151740": {
+      "content": "<|extra_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151741": {
+      "content": "<|extra_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151742": {
+      "content": "<|extra_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151743": {
+      "content": "<|extra_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151744": {
+      "content": "<|extra_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151745": {
+      "content": "<|extra_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151746": {
+      "content": "<|extra_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151747": {
+      "content": "<|extra_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151748": {
+      "content": "<|extra_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151749": {
+      "content": "<|extra_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151750": {
+      "content": "<|extra_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151751": {
+      "content": "<|extra_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151752": {
+      "content": "<|extra_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151753": {
+      "content": "<|extra_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151754": {
+      "content": "<|extra_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151755": {
+      "content": "<|extra_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151756": {
+      "content": "<|extra_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151757": {
+      "content": "<|extra_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151758": {
+      "content": "<|extra_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151759": {
+      "content": "<|extra_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151760": {
+      "content": "<|extra_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151761": {
+      "content": "<|extra_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151762": {
+      "content": "<|extra_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151763": {
+      "content": "<|extra_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151764": {
+      "content": "<|extra_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151765": {
+      "content": "<|extra_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151766": {
+      "content": "<|extra_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151767": {
+      "content": "<|extra_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151768": {
+      "content": "<|extra_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151769": {
+      "content": "<|extra_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151770": {
+      "content": "<|extra_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151771": {
+      "content": "<|extra_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151772": {
+      "content": "<|extra_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151773": {
+      "content": "<|extra_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151774": {
+      "content": "<|extra_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151775": {
+      "content": "<|extra_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151776": {
+      "content": "<|extra_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151777": {
+      "content": "<|extra_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151778": {
+      "content": "<|extra_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151779": {
+      "content": "<|extra_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151780": {
+      "content": "<|extra_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151781": {
+      "content": "<|extra_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151782": {
+      "content": "<|extra_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151783": {
+      "content": "<|extra_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151784": {
+      "content": "<|extra_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151785": {
+      "content": "<|extra_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151786": {
+      "content": "<|extra_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151787": {
+      "content": "<|extra_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151788": {
+      "content": "<|extra_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151789": {
+      "content": "<|extra_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151790": {
+      "content": "<|extra_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151791": {
+      "content": "<|extra_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151792": {
+      "content": "<|extra_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151793": {
+      "content": "<|extra_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151794": {
+      "content": "<|extra_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151795": {
+      "content": "<|extra_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151796": {
+      "content": "<|extra_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151797": {
+      "content": "<|extra_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151798": {
+      "content": "<|extra_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151799": {
+      "content": "<|extra_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151800": {
+      "content": "<|extra_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151801": {
+      "content": "<|extra_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151802": {
+      "content": "<|extra_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151803": {
+      "content": "<|extra_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151804": {
+      "content": "<|extra_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151805": {
+      "content": "<|extra_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151806": {
+      "content": "<|extra_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151807": {
+      "content": "<|extra_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151808": {
+      "content": "<|extra_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151809": {
+      "content": "<|extra_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151810": {
+      "content": "<|extra_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151811": {
+      "content": "<|extra_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151812": {
+      "content": "<|extra_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151813": {
+      "content": "<|extra_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151814": {
+      "content": "<|extra_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151815": {
+      "content": "<|extra_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151816": {
+      "content": "<|extra_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151817": {
+      "content": "<|extra_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151818": {
+      "content": "<|extra_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151819": {
+      "content": "<|extra_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151820": {
+      "content": "<|extra_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151821": {
+      "content": "<|extra_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151822": {
+      "content": "<|extra_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151823": {
+      "content": "<|extra_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151824": {
+      "content": "<|extra_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151825": {
+      "content": "<|extra_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151826": {
+      "content": "<|extra_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151827": {
+      "content": "<|extra_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151828": {
+      "content": "<|extra_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151829": {
+      "content": "<|extra_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151830": {
+      "content": "<|extra_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151831": {
+      "content": "<|extra_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151832": {
+      "content": "<|extra_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151833": {
+      "content": "<|extra_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151834": {
+      "content": "<|extra_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151835": {
+      "content": "<|extra_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151836": {
+      "content": "<|extra_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151837": {
+      "content": "<|extra_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151838": {
+      "content": "<|extra_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151839": {
+      "content": "<|extra_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151840": {
+      "content": "<|extra_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151841": {
+      "content": "<|extra_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151842": {
+      "content": "<|extra_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151843": {
+      "content": "<|extra_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151844": {
+      "content": "<|extra_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151845": {
+      "content": "<|extra_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151846": {
+      "content": "<|extra_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151847": {
+      "content": "<|extra_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151848": {
+      "content": "<|extra_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151849": {
+      "content": "<|extra_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151850": {
+      "content": "<|extra_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 4096,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}