Upload folder using huggingface_hub

README.md

@@ -0,0 +1,73 @@
+---
+base_model:
+- FuseAI/FuseChat-7B-VaRM
+- SanjiWatsuki/Kunoichi-DPO-v2-7B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# FUSECHAT-VaRM-Kunoichi-10.7b.v1
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [FuseAI/FuseChat-7B-VaRM](https://huggingface.co/FuseAI/FuseChat-7B-VaRM)
+* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+merge_method: linear # use linear so we can include multiple models, albeit at a zero weight
+parameters:
+  weight: 1.0 # weight everything as 1 unless specified otherwise - linear with one model weighted at 1 is a no-op like passthrough
+slices:
+  - sources:
+      - model: FuseAI/FuseChat-7B-VaRM # embed_tokens comes along with the ride with whatever is the first layer
+        layer_range: [0, 1]
+      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B # add dummy second model with 0 weight so tokenizer-based merge routine is invoked for embed_tokens
+        layer_range: [0, 1]
+        parameters:
+          weight: 0
+  - sources:
+      - model: FuseAI/FuseChat-7B-VaRM
+        layer_range: [1, 5]
+  - sources:
+      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
+        layer_range: [5, 7] # 2 layers
+  - sources:
+      - model: FuseAI/FuseChat-7B-VaRM
+        layer_range: [5, 15]
+  - sources:
+      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
+        layer_range: [15, 27] # 12 layers
+  - sources:
+      - model: FuseAI/FuseChat-7B-VaRM
+        layer_range: [15, 27]
+  - sources:
+      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
+        layer_range: [27, 29] # 2 layers
+  - sources:
+      - model: FuseAI/FuseChat-7B-VaRM
+        layer_range: [27, 31]
+  - sources: # same as above, but for lm_head with the last layer
+      - model: FuseAI/FuseChat-7B-VaRM
+        layer_range: [31, 32]
+      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
+        layer_range: [31, 32]
+        parameters:
+          weight: 0
+dtype: float16
+tokenizer_source: model:FuseAI/FuseChat-7B-VaRM # keep exact tokenizer used by dolphin - or you could use `union` if you add all of the input models to the first/last slice
+
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|end_of_turn|>": 32000,
+  "<|pad_0|>": 32001
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "FuseAI/FuseChat-7B-VaRM",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32002
+}

mergekit_config.yml

@@ -0,0 +1,41 @@
+merge_method: linear # use linear so we can include multiple models, albeit at a zero weight
+parameters:
+  weight: 1.0 # weight everything as 1 unless specified otherwise - linear with one model weighted at 1 is a no-op like passthrough
+slices:
+  - sources:
+      - model: FuseAI/FuseChat-7B-VaRM # embed_tokens comes along with the ride with whatever is the first layer
+        layer_range: [0, 1]
+      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B # add dummy second model with 0 weight so tokenizer-based merge routine is invoked for embed_tokens
+        layer_range: [0, 1]
+        parameters:
+          weight: 0
+  - sources:
+      - model: FuseAI/FuseChat-7B-VaRM
+        layer_range: [1, 5]
+  - sources:
+      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
+        layer_range: [5, 7] # 2 layers
+  - sources:
+      - model: FuseAI/FuseChat-7B-VaRM
+        layer_range: [5, 15]
+  - sources:
+      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
+        layer_range: [15, 27] # 12 layers
+  - sources:
+      - model: FuseAI/FuseChat-7B-VaRM
+        layer_range: [15, 27]
+  - sources:
+      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
+        layer_range: [27, 29] # 2 layers
+  - sources:
+      - model: FuseAI/FuseChat-7B-VaRM
+        layer_range: [27, 31]
+  - sources: # same as above, but for lm_head with the last layer
+      - model: FuseAI/FuseChat-7B-VaRM
+        layer_range: [31, 32]
+      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
+        layer_range: [31, 32]
+        parameters:
+          weight: 0
+dtype: float16
+tokenizer_source: model:FuseAI/FuseChat-7B-VaRM # keep exact tokenizer used by dolphin - or you could use `union` if you add all of the input models to the first/last slice

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87466ce2b2340e331022f1a4b2477f5bf699b345b9132ec7dbd2b5baf215081
+size 1979781432

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62530c29ff8deeb7723074cf09a1f8cbba36b4d7c73e02b34002d47f362011d3
+size 1946243944

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1998ce40233e7249233b85edfc98ff3fbe1a2e3dae13c1987a26914abd5f582a
+size 1979781432

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e388ae89110f9e14e45a66f71a25453c41e77c61724ff3bc026fdc1d66de1e
+size 1946243944

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e365ffc842ab7fe8ca3b9a8f9bb429788561f7484623aebce32361d3f582e5bf
+size 1979781432

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04930d42a5672d02fbff15ae9796514c6bed12e8935907ece7775db44ea8cb9
+size 1946243904

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffd336ebcf508a9ace949e7a5a3f07bed94b6924249b334a70bb03d5f86b742e
+size 1979781368

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b05ce122ae7490df1103dfda2b3e5f84d5990d016e61b9de76c1580783236c9
+size 1973506568

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3bb7f7ee797cf10e1a48cc22afa42904d9e2a3d5cc172e599f0258975a1a97
+size 1979789736

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da5dc68228cf22649bc2007be8bbf5c94455ecab26ea430fa66d0666b5539818
+size 1889619992

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9aae0dd78e74e466b77f81fd36f926e0f59dba8ef62e7a1ab5af731d0cad17f
+size 1862357400

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_turn|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|end_of_turn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|pad_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_turn|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}