Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
+- TomGrc/FusionNet_7Bx2_MoE_14B
+---
+
+# LogoS-7Bx2-MoE-13B-v0.1
+
+LogoS-7Bx2-MoE-13B-v0.1 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B](https://huggingface.co/yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B)
+* [TomGrc/FusionNet_7Bx2_MoE_14B](https://huggingface.co/TomGrc/FusionNet_7Bx2_MoE_14B)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 
+        layer_range: [0, 32]
+      - model: TomGrc/FusionNet_7Bx2_MoE_14B
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 
+        layer_range: [0, 32]
+      - model: TomGrc/FusionNet_7Bx2_MoE_14B
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b72e26d742be0bec0825d28ba015f66c1e9e926dfe2e7a5d6266f73a616d7c
+size 1906338032

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8645e9cfd6e46ff7d724c956193d491afcf7d960e6b3e5bd3661a1fd2ec481
+size 1996515856

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b8fe4b194a297646501685812789dbea75915bc0dae7944aa34068de1f9bc9
+size 1996507568

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb64fb0f04f001a49fc8947a51c0088640040bb6e0c1da26942427d502a2f4d
+size 1996507552

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286a649f679e430758199561dbcbbd161a154c572d33a6a498bd76de2319f3b4
+size 1988437776

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:489664545339a67265d39a69c6859faeda60fe116b94a722aaeb20a92b29383d
+size 1887489240

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:961d1087898f25836cf029f0c40b17d8c7cf04b64ea52eb428c887dd57607f0e
+size 1895928040

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:299fe5f8acf22a475e9f1b7a8d8c4171c076ddb32468c7887055f7b6c3f967b1
+size 1929449016

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f5620deac53c166a011c2c981de629d7480315490b9aa44288eaa46959c212
+size 1971425408

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e04277676a0f89383b1e9ac765b48c4429aa18b5c887cbe72cec4bc25eca62
+size 1971392280

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a27fedc415049dea6d24a4971ca53b529d4e8ec632ac3a866e990ccea3186031
+size 1971425408

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21af2add49e05c525aaa9b126eb7b1f977e5c80025e4ae35696d056e058d520
+size 1971392280

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf695f57254fd8c0a2baf2c096acf6429e5a6c2ba10ee672ffb43817ef0f9b4
+size 1923174232

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f3468c393c4d994299ec37110fe7659cdc50fd254543ba4292a56588edfbf91
+size 352346856

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00005-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00007-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00007-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00007-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00009-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00009-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00009-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00010-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00010-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00011-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00011-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00011-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00012-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00012-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00013-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00013-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "lm_head.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 255,
+  "pad_to_multiple_of": null,
+  "pad_token": "<s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}