Upload folder using huggingface_hub

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 15,
+  "eos_token_id": 16,
+  "head_dim": null,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.01,
+  "intermediate_size": 8192,
+  "iter": 380000,
+  "max_position_embeddings": 1048576,
+  "model_type": "mixtral",
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "pad_token_id": 14,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 50000000,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 15,
+  "eos_token_id": 16,
+  "pad_token_id": 14,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291f654e9bf140400d40ce47616a3245c0d078c7ceb789c12f561953a0d575df
+size 4968453896

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0abaf85e7ecfd9b9c6f87a50a2c1a1accfea15d75f7954580be31993d22e1c0
+size 4899116256

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd7920a026cf369f8a37068541e4f79f762272b0f2d56f8a89dec4805c64bb3
+size 4966389640

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24703407520800967fc93c00c11411d886a5220edb666c01dce9c61798a50d7f
+size 4899116256

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f599d28288b80ca146773233d20ac006ec9a42d1953b6c66ce95141f03ddeaf
+size 4966389640

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87bd6b0040077e7fd811925f597be575be493eb8748264d64b732367f4fe0a14
+size 4899116256

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3b6aed71d2896c8369e39b16c72babbf0dfce12fad986b5b29b53693602863
+size 4966389648

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a3e3719f5750acf5699f5abdebbfdb9e9dd1a2c8d3252945d422a160589908
+size 4899116304

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be91b0ef921d7ed64a13734745de541e25d464ca945d5d33ffc5724e454c775
+size 1612761024

model.safetensors.index.json

@@ -0,0 +1,382 @@
+{
+  "metadata": {
+    "total_size": 41076801536
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": [
+    "<EOD>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<CLS>",
+  "eos_token": "</s>",
+  "mask_token": "<MASK>",
+  "pad_token": "<PAD>",
+  "sep_token": "<SEP>",
+  "unk_token": "<UNK>"
+}

tokenizer.json

@@ -0,0 +1,163 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 10,
+      "content": "<CLS>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 11,
+      "content": "<SEP>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 12,
+      "content": "<EOD>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 13,
+      "content": "<MASK>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 14,
+      "content": "<PAD>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 15,
+      "content": "<s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 16,
+      "content": "</s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 17,
+      "content": "<UNK>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 0
+        }
+      }
+    ],
+    "special_tokens": {
+      "<CLS>": {
+        "id": "<CLS>",
+        "ids": [
+          10
+        ],
+        "tokens": [
+          "<CLS>"
+        ]
+      },
+      "<SEP>": {
+        "id": "<SEP>",
+        "ids": [
+          11
+        ],
+        "tokens": [
+          "<SEP>"
+        ]
+      }
+    }
+  },
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "<UNK>",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "[PAD]": 0,
+      "[UNK]": 1,
+      "[CLS]": 2,
+      "[SEP]": 3,
+      "[MASK]": 4,
+      "C": 5,
+      "G": 6,
+      "T": 7,
+      "A": 8,
+      "N": 9,
+      "<CLS>": 10,
+      "<SEP>": 11,
+      "<EOD>": 12,
+      "<MASK>": 13,
+      "<PAD>": 14,
+      "<s>": 15,
+      "</s>": 16,
+      "<UNK>": 17
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,82 @@
+{
+  "added_tokens_decoder": {
+    "10": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<EOD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<MASK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<EOD>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<MASK>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sep_token": "<SEP>",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "<UNK>"
+}