upload checkpoint

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "Olmo1124ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "olmo_1124",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 100352
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 100257,
+  "pad_token_id": 100277,
+  "transformers_version": "4.47.0.dev0"
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d98857770936dacb09e4bcfffc98d6eb17d9fb64ead69ccde1c4e4c712978257
+size 4907502536

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8fae969618d33af8174ac76c437906ad9857024db2c143e5c61d739f5c0a94
+size 4970582888

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03c834e34c87a9fa71c4b2c38f7d451b1037dc29f81d93251bb5067eabab8d1
+size 4970582888

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ae8c3a4a7b90f19ae3742a894c85cf14296042f230dfaa943227ad2d646257
+size 4970582928

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefe1d9619d19162177708ad55e462571cba2cc42f9721169f2eb93ba75b0fb7
+size 4792283808

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc566735dedae56caed260f49988cff5c93cc965c554f0168d9837a7b2e11ef
+size 4792325016

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aad6698968645ba46ba258cbd1e336c6f9e986c468a0fdf0d7aa1babc0cb94e
+size 4792325016

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140b9f897f4f68877071b84d4c0cb792f27ed319980420eef16c89ebe67a3410
+size 4970541752

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59cf9c1a7a1b56323eb2b8643605c2d6d635c4a02f642efef36fa251b107e41
+size 4970582928

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6344d8e63d866e783a58694aedc2429463c9c232296b0c432830add37fa953fb
+size 4970582928

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea1c24d5a94d0047769a32bf113ffa067be04b3c580aad5a390df4365e1e3df6
+size 3701743344

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f27e406a792cc69eafa56c98016e4eebdaa4c06c6e3d04e514c3830f8ccaf59
+size 2055209088

model.safetensors.index.json

@@ -0,0 +1,450 @@
+{
+  "metadata": {
+    "total_size": 54864793600
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00012-of-00012.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.norm.weight": "model-00011-of-00012.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,189 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|extra_id_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|extra_id_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100267": {
+      "content": "<|extra_id_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100268": {
+      "content": "<|extra_id_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100269": {
+      "content": "<|extra_id_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100270": {
+      "content": "<|extra_id_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "<|extra_id_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<|extra_id_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "<|extra_id_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<|extra_id_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "<|extra_id_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}