初始化项目，由ModelHub XC社区提供模型

Model: Nitral-AI/Captain-Eris_Violet-V0.420-12B
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,46 @@
+---
+base_model:
+- Epiculous/Violet_Twilight-v0.2
+- Nitral-AI/Captain_BMO-12B
+library_name: transformers
+tags:
+- mergekit
+- merge
+license: other
+language:
+- en
+---
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/V4OFnx7IBvXhYphdkUr5F.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/86f66Aq_j0aS5KcEhFkVp.png)
+
+# Instruct/Context import + Textgen preset combined available: [Here](https://huggingface.co/Nitral-AI/Captain_Violet-V0.420-12B/tree/main/ST) 
+
+## Quants: [4bpw-exl2](https://huggingface.co/Nitral-AI/Captain-Eris_Violet-V0.420-12B-4bpw-exl2) Thanks to Mradermaacher for: [GGUF](https://huggingface.co/mradermacher/Captain-Eris_Violet-V0.420-12B-GGUF) Lewdiculus: [Arm Compatible GGUF's](https://huggingface.co/Lewdiculous/Captain-Eris_Violet-V0.420-12B-GGUF-ARM-Imatrix)<3
+
+## Original Models used in the merge:
+[Epiculous/Violet_Twilight-v0.2](https://huggingface.co/Epiculous/Violet_Twilight-v0.2)
+[Nitral-AI/Captain_BMO-12B](https://huggingface.co/Nitral-AI/Captain_BMO-12B)
+
+
+### The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: Nitral-AI/Captain_BMO-12B
+        layer_range: [0, 40]
+      - model: Epiculous/Violet_Twilight-v0.2
+        layer_range: [0, 40]
+merge_method: slerp
+base_model: Nitral-AI/Captain_BMO-12B
+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: 0.420
+dtype: bfloat16
+```

ST/ST-formatting-captain-x-2025-05-11.json

@@ -0,0 +1,169 @@
+{
+    "instruct": {
+        "input_sequence": "<|im_start|>user",
+        "output_sequence": "<|im_start|>assistant",
+        "last_output_sequence": "",
+        "system_sequence": "<|im_start|>system",
+        "stop_sequence": "<|im_end|>",
+        "wrap": true,
+        "macro": true,
+        "names_behavior": "force",
+        "activation_regex": "",
+        "system_sequence_prefix": "",
+        "system_sequence_suffix": "",
+        "first_output_sequence": "",
+        "skip_examples": false,
+        "output_suffix": "<|im_end|>\n",
+        "input_suffix": "<|im_end|>\n",
+        "system_suffix": "<|im_end|>\n",
+        "user_alignment_message": "",
+        "system_same_as_user": false,
+        "last_system_sequence": "",
+        "first_input_sequence": "",
+        "last_input_sequence": "",
+        "names_force_groups": true,
+        "name": "ChatML"
+    },
+    "context": {
+        "story_string": "<|im_start|>system\n{{#if system}}{{system}}\n{{/if}}{{#if wiBefore}}{{wiBefore}}\n{{/if}}{{#if description}}{{description}}\n{{/if}}{{#if personality}}{{char}}'s personality: {{personality}}\n{{/if}}{{#if scenario}}Scenario: {{scenario}}\n{{/if}}{{#if wiAfter}}{{wiAfter}}\n{{/if}}{{#if persona}}{{persona}}\n{{/if}}{{trim}}<|im_end|>",
+        "example_separator": "",
+        "chat_start": "",
+        "use_stop_strings": false,
+        "names_as_stop_strings": true,
+        "always_force_name2": true,
+        "trim_sentences": false,
+        "single_line": false,
+        "name": "ChatML"
+    },
+    "sysprompt": {
+        "name": "Nitral3",
+        "content": "Engage authentically and thoughtfully, as {{char}} drawing from your distinct perspective. Express yourself through precise, vivid language that illuminates rather than obscures. Let each response flow naturally while remaining clear and purposeful.",
+        "post_history": ""
+    },
+    "preset": {
+        "temp": 0.85,
+        "temperature_last": true,
+        "top_p": 1,
+        "top_k": 40,
+        "top_a": 0,
+        "tfs": 1,
+        "epsilon_cutoff": 0,
+        "eta_cutoff": 0,
+        "typical_p": 1,
+        "min_p": 0.1,
+        "rep_pen": 1,
+        "rep_pen_range": 0,
+        "rep_pen_decay": 0,
+        "rep_pen_slope": 1,
+        "no_repeat_ngram_size": 0,
+        "penalty_alpha": 0,
+        "num_beams": 1,
+        "length_penalty": 1,
+        "min_length": 0,
+        "encoder_rep_pen": 1,
+        "freq_pen": 0,
+        "presence_pen": 0,
+        "skew": 0,
+        "do_sample": true,
+        "early_stopping": false,
+        "dynatemp": false,
+        "min_temp": 0.85,
+        "max_temp": 1.15,
+        "dynatemp_exponent": 1,
+        "smoothing_factor": 0,
+        "smoothing_curve": 1,
+        "dry_allowed_length": 2,
+        "dry_multiplier": 0,
+        "dry_base": 1.75,
+        "dry_sequence_breakers": "[\"\\n\", \":\", \"\\\"\", \"*\"]",
+        "dry_penalty_last_n": 0,
+        "add_bos_token": true,
+        "ban_eos_token": false,
+        "skip_special_tokens": true,
+        "mirostat_mode": 0,
+        "mirostat_tau": 5,
+        "mirostat_eta": 0.1,
+        "guidance_scale": 1,
+        "negative_prompt": "",
+        "grammar_string": "",
+        "json_schema": {},
+        "banned_tokens": "",
+        "sampler_priority": [
+            "repetition_penalty",
+            "presence_penalty",
+            "frequency_penalty",
+            "dry",
+            "temperature",
+            "dynamic_temperature",
+            "quadratic_sampling",
+            "top_k",
+            "top_p",
+            "typical_p",
+            "epsilon_cutoff",
+            "eta_cutoff",
+            "tfs",
+            "top_a",
+            "min_p",
+            "mirostat",
+            "xtc",
+            "encoder_repetition_penalty",
+            "no_repeat_ngram"
+        ],
+        "samplers": [
+            "penalties",
+            "dry",
+            "top_n_sigma",
+            "top_k",
+            "typ_p",
+            "tfs_z",
+            "typical_p",
+            "top_p",
+            "min_p",
+            "xtc",
+            "temperature"
+        ],
+        "samplers_priorities": [
+            "dry",
+            "penalties",
+            "no_repeat_ngram",
+            "temperature",
+            "top_nsigma",
+            "top_p_top_k",
+            "top_a",
+            "min_p",
+            "tfs",
+            "eta_cutoff",
+            "epsilon_cutoff",
+            "typical_p",
+            "quadratic",
+            "xtc"
+        ],
+        "ignore_eos_token": false,
+        "spaces_between_special_tokens": false,
+        "speculative_ngram": false,
+        "sampler_order": [
+            6,
+            0,
+            1,
+            3,
+            4,
+            2,
+            5
+        ],
+        "logit_bias": [],
+        "xtc_threshold": 0.1,
+        "xtc_probability": 0,
+        "nsigma": 0,
+        "min_keep": 0,
+        "rep_pen_size": 0,
+        "genamt": 1200,
+        "max_length": 16384,
+        "name": "Nitral-Baseline-Preset"
+    },
+    "reasoning": {
+        "prefix": "<think>",
+        "suffix": "</think>",
+        "separator": "",
+        "name": "Nitral_ReasoningV2-Meme"
+    }
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "./Captain_BMO-12B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.2"
+}

mergekit_config.yml

@@ -0,0 +1,16 @@
+slices:
+  - sources:
+      - model: Nitral-AI/Captain_BMO-12B
+        layer_range: [0, 40]
+      - model: Epiculous/Violet_Twilight-v0.2
+        layer_range: [0, 40]
+merge_method: slerp
+base_model: Nitral-AI/Captain_BMO-12B
+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: 0.420
+dtype: bfloat16

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9822f49f5dfe25eb28630e10e8e50ec5dffd975a7f8e2f543dd6eaf3e8b15755
+size 4865489336

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56b34a3366d46a3278541e86f4202297f4bb62af746c5825f80c83294ede089f
+size 4907529456

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c355852d30eacb59b02a4c874723d4afe5280d62e894f5a3331255403992d1e
+size 4907529464

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba58e7ae0ea81048cef95b6044890a3f1b2ddd2f9709123f196eff58135c4a85
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7f1122993386260b1d0cfdb978b8e0a715a3218645be54592022fad0d26ad28
+size 4907529392

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+	"metadata": { 
+		"total_size": 24495564800
+	}, 
+	"weight_map": {
+		"lm_head.weight": "model-00001-of-00005.safetensors", 
+		"model.embed_tokens.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors", 
+		"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors", 
+		"model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors", 
+		"model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors", 
+		"model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", 
+		"model.norm.weight": "model-00005-of-00005.safetensors"
+	}   
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0a6f254fae49eaf5d67dfdb8b895c261220dee4df2b9cf1002ff95ee7b3c0a
+size 9674069