Upload 29 files

README.md

@@ -1,35 +1,45 @@
 ---
-license: cc-by-nc-4.0
+base_model: []
+library_name: transformers
 tags:
-- merge
 - mergekit
-- text-generation-inference
-- transformers
+- merge
+
 ---
+# Fimbulvetr-V2-Kuro-Lotus
 
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
-This is a merge of Fimbulvet-V2 and Kuro-Lotus using the following recipe:
+## Merge Details
+### Merge Method
 
-```
+This model was merged using the SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* D:\MK\Models\Fimbulvetr-11B-v2
+* D:\MK\Models\Kuro-Lotus-10.7B
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
 slices:
-- sources:
-- model: saishf/Kuro-Lotus-10.7B
-layer_range: [0, 48]
-- model: Sao10K/Fimbulvetr-11B-v2
-layer_range: [0, 48]
+  - sources:
+    - model: D:\MK\Models\Kuro-Lotus-10.7B
+      layer_range: [0, 48]
+    - model: D:\MK\Models\Fimbulvetr-11B-v2
+      layer_range: [0, 48]
 merge_method: slerp
-base_model: saishf/Kuro-Lotus-10.7B
+base_model: D:\MK\Models\Kuro-Lotus-10.7B
 parameters:
-t:
-- filter: self_attn
-value: [0.6, 0.7, 0.8, 0.9, 1]
-- filter: mlp
-value: [0.4, 0.3, 0.2, 0.1, 0]
-- value: 0.5
+  t:
+    - filter: self_attn
+      value: [0.6, 0.7, 0.8, 0.9, 1]
+    - filter: mlp
+      value: [0.4, 0.3, 0.2, 0.1, 0]
+    - value: 0.5
 dtype: bfloat16
 ```
-Models used:
-
-Fimbulvetr-V2-11B: https://huggingface.co/Sao10K/Fimbulvetr-11B-v2 /n
-
-Kuro-Lotus-10.7B: https://huggingface.co/saishf/Kuro-Lotus-10.7B

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "D:\\MK\\Models\\Kuro-Lotus-10.7B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,16 @@
+slices:
+  - sources:
+    - model: D:\MK\Models\Kuro-Lotus-10.7B
+      layer_range: [0, 48]
+    - model: D:\MK\Models\Fimbulvetr-11B-v2
+      layer_range: [0, 48]
+merge_method: slerp
+base_model: D:\MK\Models\Kuro-Lotus-10.7B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0.6, 0.7, 0.8, 0.9, 1]
+    - filter: mlp
+      value: [0.4, 0.3, 0.2, 0.1, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5f3986fb2b5af1d3bc250c792e1a368fb345236366f53f7903651a7f96d9ba
+size 989882408

model-00002-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca59946948903312d0af2b7b2c51b3c2007195cae431168896700a627c469d2f
+size 908118272

model-00003-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b79cb1d85976fa41b93b8703e835f1e14f85001e3a01cb7234200c76ff2a40c
+size 905995864

model-00004-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b44cf248e9f0534675ba9fa2446b7f864943b0f1bbcd73b4260fd788e90cf15
+size 989899016

model-00005-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:625d3a9ac201fbc53e5204c3d2d4d5874e295afa62cc76b8c78d70c2d46c6143
+size 989890720

model-00006-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d6508ec5462025c2ef7117bfa3ac93360103ae60fab5a79bb2a6ea35cf3a4d
+size 989899016

model-00007-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17482f68ded17e316fd7dff5bc0e3b9dbf3fbd8ead90994ef6940ea05af62049
+size 998287760

model-00008-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77656c053f1a4a5808957ef8e6c7f9b0ec65a10a0a9e3714859a6054fa40dd34
+size 998288216

model-00009-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7216bcc6a7569c109d1935d616b3c80c8038c536d883861c339ffddd480c36
+size 939550416

model-00010-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2756086cc13ba54bcf0a61fdebd7899a51de7a2d6342556648fda50ae28c47b5
+size 989899040

model-00011-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925fdabe52edcc4ed647d9f6449afbc6ae0b08e1eb8534bb65592c4aa8b5fade
+size 998287752

model-00012-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5219999ab950a73292ce25d3201e133d7306fd77ad0922934e23535ef9a5fa89
+size 998288216

model-00013-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2423e91987e0b4ae74c720fefafe991f3fb705197e8358a5a2b8c20f6c03ae
+size 939550416

model-00014-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9bdb77b1d1ece465dc2fbef8e92e19142bd916adcb614207701a30d4ddd0910
+size 989899040

model-00015-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c4c94320c688421a9ec9bb0eb14aed051102f6a86bba32ee1d1f8c16ea6d32
+size 998287752

model-00016-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b640b9e21207ef4da9cc81ee58ca47d319d91670659985afc101312059449dde
+size 998288216

model-00017-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5018779328a599f56ef8519dbe802c44de7c8bb6cbc0e9969871c83599cf0f
+size 939550416

model-00018-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf488272a3b70f6f95adea5f0b77052f512a25801b86e389955aa31e85f5b0b
+size 989899040

model-00019-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d72099c52aa33f9fe2f745633efdea6e8d9c54ba1a012e46fe6090917a9024
+size 989882416

model-00020-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787a5bd83607284e92478b22149eaaeda2a7878366751826da05f880bbdc16a0
+size 998288216

model-00021-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a92ac4fa0d645a401a1b401e05f8b79a0fcc4069f9f205479694cf5cc66f939
+size 966813240

model-00022-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543fc51afd5a8b1eaed6043cd6f6c20941c0cf1838ee7befeba55c271279d462
+size 956353248

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00022.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00022.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00022.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00022.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00022.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00022.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00022.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00022.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00022.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00022.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00022.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00022.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00022.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00022.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00022.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00022.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.embed_tokens.weight": "model-00002-of-00022.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.14.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.13.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.25.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.24.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.23.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.22.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.29.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.28.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.27.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.35.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.34.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.33.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.32.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.31.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.39.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.38.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.37.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.36.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.43.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.42.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.41.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.40.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "lm_head.weight": "model-00021-of-00022.safetensors", "model.norm.weight": "model-00021-of-00022.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.47.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.46.input_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.45.input_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.44.input_layernorm.weight": "model-00022-of-00022.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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 +1,43 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}