Upload folder using huggingface_hub

README.md

@@ -8,4 +8,4 @@ pipeline_tag: text-generation
 ---
 # BODHI
 
-Artifact for the BODHI project. This model is a distilled version of Qwen2.5-32B.
+Artifact for the BODHI project. This model is a distilled version of ```Qwen/Qwen2.5-32B```.

chat_template.jinja

@@ -1,54 +1,15 @@
-{%- if tools %}
-    {{- '<|im_start|>system\n' }}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- messages[0]['content'] }}
-    {%- else %}
-        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
-    {%- endif %}
-    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
-{%- else %}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
-    {%- else %}
-        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
-    {%- endif %}
-{%- endif %}
-{%- for message in messages %}
-    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
-        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
-    {%- elif message.role == "assistant" %}
-        {{- '<|im_start|>' + message.role }}
-        {%- if message.content %}
-            {{- '\n' + message.content }}
-        {%- endif %}
-        {%- for tool_call in message.tool_calls %}
-            {%- if tool_call.function is defined %}
-                {%- set tool_call = tool_call.function %}
-            {%- endif %}
-            {{- '\n<tool_call>\n{"name": "' }}
-            {{- tool_call.name }}
-            {{- '", "arguments": ' }}
-            {{- tool_call.arguments | tojson }}
-            {{- '}\n</tool_call>' }}
-        {%- endfor %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- message.content }}
-        {{- '\n</tool_response>' }}
-        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-{%- endif %}
+{%- for message in messages -%}
+    {%- set role = message['role'] -%}
+    {%- set content = message['content'] -%}
+    {%- if role == 'system' -%}
+        {{- '<|im_start|>system\n' + content.strip() + '<|im_end|>\n' -}}
+    {%- elif role == 'user' -%}
+        {{- '<|im_start|>user\n' + content.strip() + '<|im_end|>\n' -}}
+    {%- elif role == 'assistant' -%}
+        {{- '<|im_start|>assistant\n' + content.strip() + '<|im_end|>\n' -}}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {{- '<|im_start|>assistant\n<think>\n' -}}
+{%- endif -%}

config.json

@@ -82,12 +82,15 @@
   "num_attention_heads": 40,
   "num_hidden_layers": 64,
   "num_key_value_heads": 8,
+  "pad_token_id": null,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 1000000.0,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "4.57.3",
+  "transformers_version": "5.8.0",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064

generation_config.json

@@ -1,6 +1,7 @@
 {
   "bos_token_id": 151643,
+  "do_sample": false,
   "eos_token_id": 151643,
   "max_new_tokens": 2048,
-  "transformers_version": "4.57.3"
+  "transformers_version": "5.8.0"
 }

model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbec6e54f2a7cc370aa0ab4dc9e880f5318e65eef2b7d8c0a5cf11254105fcc5
-size 4891730992
+oid sha256:f0b4137f958b715476da41e3088b0637fd0e9bb1cc56dca0430e76b3dc5559ad
+size 4949338472

model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb70664a3da77e34a02f007637d84deaa4b886f3c0d97029896e246873e01ea8
-size 4876059352
+oid sha256:629ea87c47e06711a070093e763e79a82373c42dd6479c877e2be74e3fe8bdd5
+size 4991425920

model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef57fa4b76b0e737525eb4fde96e81d1b725fce34a5aa33d425af5602b22c16b
-size 4876059384
+oid sha256:0cc27c058b8fa4a90cb2ea109a86fa92579df60a56b0ae0660863194a4a4c430
+size 4876059368

model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f13b8ce67eaaf87c59ef3082fc7ae6a6aa585a45ebe4a76cd9ce8294d64ca488
-size 4876059416
+oid sha256:c8d5c022aa5498ddf924b958db0347171764edecd4fa8e973f907361aa95d7a0
+size 4876059408

model-00005-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3beba73280542e05acc260ef1272d7689a405c7d9d802ae3f569754c38f60390
-size 4876059416
+oid sha256:91c75afba0052a2c5f32a95c6b31ed3830efbb1402b9df131c9b0f0bab2382f0
+size 4876059408

model-00006-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cee41b950345833e8e60b1e0201924363774ddda3190f1f750f19cb634985ee5
-size 4876059416
+oid sha256:6f1aaad9f723a50cfcf70decaca3581dd39a28d4b24a4b1427e16bcf53c2f8b9
+size 4876059408

model-00007-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c144f2bd1c73977e7095b499193604e28bf5475f1de1852f5e061c38ba024ad8
-size 4876059416
+oid sha256:ac2ee61b686ebd8929031566faf4497cd20ddc8259f4f24452d4ae8e8c01dfc4
+size 4876059408

model-00008-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a666bfbd59036d2ea08a6aed0b9b31ad6e4a0e435e4ed92308d341894a67b5a
-size 4876059416
+oid sha256:6f652517db8ec1e4d5cf2bb67d29ecf3ff492d1d5fa1d8166d4806631a63a9fb
+size 4876059408

model-00009-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc902a373bc77325dcdff6a268361d210e722c68240c509fad829bd377a9641
-size 4876059416
+oid sha256:4ee5d97b78b8c8e65d14bdfc79542626ee8bef297432367e1b9bd57aa0736add
+size 4876059408

model-00010-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8190dff0a3f375abbaf8f155ef717ecc4ba8423de6c0eff7b8bb0cc7253de712
-size 4876059416
+oid sha256:80c665760636a19bba78cd360117356c13ac9f9cb789f9da5a34de1af6fa8df9
+size 4876059408

model-00011-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d316a8eb9baba5ef02117eee548129f6b4ea9c88ca3bcb6c3483a182e18d866
-size 4876059416
+oid sha256:a7f46032e9b186b6c97de24a786e67821fb185d21ea995290279894a04d9f7d7
+size 4876059408

model-00012-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec241244839e04566c9e299e7f2135d48363c74771c32cc57e4770cd25f125bf
-size 4876059416
+oid sha256:887167ba63a08ad7b73b23313930b62a1a7946ca5b0d47b8804fcb9f1aeb09f4
+size 4876059408

model-00013-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7822309e18a7a42a727f517ad22e87aab81a5adf1f6349779c2adbd68928c9
-size 4876059416
+oid sha256:29d0b4708051047b6eb9f82d8c7fe20a573e795e2e29a1a9533d98cea64ebd2f
+size 4876059408

model-00014-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b45476d03232801659ebf3964e30ccba90dbef73116003a075bd254eb75876
-size 2123397800
+oid sha256:0d6d5fe14f10b330b5f288a632aa4ad0196530f4e172df0cf08087dd098bbc93
+size 1950423752

model.safetensors.index.json

@@ -4,7 +4,7 @@
     "total_size": 65527752704
   },
   "weight_map": {
-    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "lm_head.weight": "model-00001-of-00014.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
@@ -25,11 +25,11 @@
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
     "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
@@ -55,29 +55,29 @@
     "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
     "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
@@ -115,29 +115,29 @@
     "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
@@ -150,18 +150,18 @@
     "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
     "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
@@ -187,29 +187,29 @@
     "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
@@ -247,29 +247,29 @@
     "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
-    "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
-    "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
@@ -284,16 +284,16 @@
     "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
@@ -319,29 +319,29 @@
     "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
     "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
-    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
-    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
     "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
     "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
     "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
     "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
-    "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
-    "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
     "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
     "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
     "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
@@ -379,29 +379,29 @@
     "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
     "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
     "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
-    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
-    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
     "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
     "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
     "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
     "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
-    "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
-    "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
     "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
     "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
     "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
@@ -451,29 +451,29 @@
     "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
     "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
     "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
-    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
-    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
-    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
-    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
-    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
-    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
-    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
-    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
-    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
     "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
     "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
-    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
     "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
     "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
-    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
-    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
-    "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
-    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
-    "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
-    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
     "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
     "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
     "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
@@ -511,29 +511,29 @@
     "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
     "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
     "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
-    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
-    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
-    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
-    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
-    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
-    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
-    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
-    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
-    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
     "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
     "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
-    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
     "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
     "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
-    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
-    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
-    "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
-    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
-    "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
-    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
     "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
     "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
     "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
@@ -583,29 +583,29 @@
     "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
     "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
     "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
-    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
-    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
-    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
-    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
-    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
-    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
-    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
-    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
-    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
     "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
     "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
-    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
     "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
     "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
-    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
-    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
-    "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
-    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
-    "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
-    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
     "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
     "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
     "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
@@ -643,29 +643,29 @@
     "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
     "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
     "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
-    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
-    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
-    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
-    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
-    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
-    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
-    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
-    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
-    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
     "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
     "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
-    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
     "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
     "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
-    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
-    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
-    "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
-    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
-    "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
-    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
     "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
     "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
     "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
@@ -715,53 +715,53 @@
     "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
     "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
     "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
-    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
-    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
-    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
-    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
-    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
-    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
-    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
-    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
-    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
     "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
     "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
-    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
     "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
     "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
-    "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
-    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
-    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
-    "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
-    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
-    "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
-    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -1,185 +1,11 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
     "<|im_start|>",
     "<|im_end|>",
     "<|object_ref_start|>",
@@ -194,11 +20,8 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
+  "is_local": true,
+  "local_files_only": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,