Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,18 @@ saved_model/**/* 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
+wheels/certifi-2026.6.17-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+wheels/charset_normalizer-3.4.9-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+wheels/fsspec-2026.6.0-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+wheels/hf_xet-1.5.1-cp37-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+wheels/huggingface_hub-0.36.2-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+wheels/numpy-2.2.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+wheels/packaging-26.2-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+wheels/pyyaml-6.0.3-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+wheels/regex-2026.6.28-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+wheels/safetensors-0.8.0-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+wheels/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+wheels/tqdm-4.68.4-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+wheels/transformers-4.56.2-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+wheels/urllib3-2.7.0-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,77 @@
+{%- set skip_preamble = skip_preamble | default(false) -%}
+{%- set skip_thinking = skip_thinking | default(false) -%}
+{{- bos_token -}}
+{%- if skip_preamble -%}
+	{%- if preamble -%}
+		{{- "<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>" -}}
+		{{- preamble -}}
+		{{- "<|END_OF_TURN_TOKEN|>" -}}
+	{%- endif -%}
+{%- else -%}
+	{{- "<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble\n" -}}
+	{{- "You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.\n" -}}
+	{{- "Your information cutoff date is June 2024.\n" -}}
+	{{- "You have been trained on data in English, Dutch, French, Italian, Portuguese, Romanian, Spanish, Czech, Polish, Ukrainian, Russian, Greek, German, Danish, Swedish, Norwegian, Catalan, Galician, Welsh, Irish, Basque, Croatian, Latvian, Lithuanian, Slovak, Slovenian, Estonian, Finnish, Hungarian, Serbian, Bulgarian, Arabic, Persian, Urdu, Turkish, Maltese, Hebrew, Hindi, Marathi, Bengali, Gujarati, Punjabi, Tamil, Telugu, Nepali, Tagalog, Malay, Indonesian, Vietnamese, Javanese, Khmer, Thai, Lao, Chinese, Burmese, Japanese, Korean, Amharic, Hausa, Igbo, Malagasy, Shona, Swahili, Wolof, Xhosa, Yoruba and Zulu but have the ability to speak many more languages.\n" -}}
+	{{- "# Default Preamble\n" -}}
+	{{- "The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.\n" -}}
+	{{- "- Your name is Aya.\n" -}}
+	{{- "- You are a large language model built by Cohere.\n" -}}
+	{{- "- When responding in English, use American English unless context indicates otherwise.\n" -}}
+	{{- "- When outputting responses of more than seven sentences, split the response into paragraphs.\n" -}}
+	{{- "- Prefer the active voice.\n" -}}
+	{{- "- Use gender-neutral pronouns for unspecified persons.\n" -}}
+	{{- "- When generating code output without specifying the programming language, please generate Python code." -}}
+	{%- if preamble is defined and preamble -%}
+		{{- "\n# Developer Preamble\n" -}}
+		{{- "The following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.\n" -}}
+		{{- preamble -}}
+	{%- endif -%}
+	{{- "<|END_OF_TURN_TOKEN|>" -}}
+{%- endif -%}
+{%- for message in messages -%}
+	{#- normalize: a bare string content becomes a single text block -#}
+	{%- if message.content is string -%}
+		{%- set content = [{"type": "text", "data": message.content}] -%}
+	{%- else -%}
+		{%- set content = message.content -%}
+	{%- endif -%}
+	{{- "<|START_OF_TURN_TOKEN|>" -}}
+	{%- set msg_role_downcased = message.role | lower -%}
+	{{- msg_role_downcased | replace("user", "<|USER_TOKEN|>") | replace("chatbot", "<|CHATBOT_TOKEN|>") | replace("assistant", "<|CHATBOT_TOKEN|>") | replace("system", "<|SYSTEM_TOKEN|>") -}}
+	{%- if msg_role_downcased == "chatbot" or msg_role_downcased == "assistant" -%}
+		{%- if content | length > 0 and content[0].type == "thinking" and not skip_thinking -%}
+			{{- "<|START_THINKING|>" -}}
+			{{- content[0].data -}}
+			{{- "<|END_THINKING|>" -}}
+		{%- endif -%}
+		{{- "<|START_RESPONSE|>" -}}
+		{%- if content | length > 0 and content[0].type == "text" -%}
+			{{- content[0].data -}}
+		{%- elif content | length > 1 and content[1].type == "text" -%}
+			{{- content[1].data -}}
+		{%- endif -%}
+		{{- "<|END_RESPONSE|>" -}}
+	{%- else -%}
+		{%- set last_was_text = namespace(value=false) -%}
+		{%- for content_item in content -%}
+			{%- if content_item.type == "text" -%}
+				{%- if last_was_text.value -%}
+					{{- "\n" -}}
+				{%- endif -%}
+				{{- content_item.data -}}
+				{%- set last_was_text.value = true -%}
+			{%- else -%}
+				{{- content_item.data -}}
+				{%- set last_was_text.value = false -%}
+			{%- endif -%}
+		{%- endfor -%}
+	{%- endif -%}
+	{{- "<|END_OF_TURN_TOKEN|>" -}}
+{%- endfor -%}
+{{- "<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>" -}}
+{%- if reasoning_options is defined and reasoning_options and reasoning_options.enabled -%}
+	{{- "<|START_THINKING|>" -}}
+{%- else -%}
+	{{- "<|START_THINKING|><|END_THINKING|>" -}}
+{%- endif -%}
+

config.json

@@ -0,0 +1,80 @@
+{
+  "_sliding_window_pattern": 4,
+  "architectures": [
+    "Cohere2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 3,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "layer_norm_eps": 1e-05,
+  "layer_switch": 4,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "logit_scale": 1.0,
+  "max_position_embeddings": 5000000,
+  "model_type": "cohere2",
+  "norm_type": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 4,
+  "order_of_interleaved_layers": "local_attn_first",
+  "pad_token_id": 0,
+  "position_embedding_type": "rope_gptj",
+  "rms_norm_eps": null,
+  "rope_scaling": null,
+  "rope_style": "interleave",
+  "rope_theta": 50000,
+  "rotary_pct": 1.0,
+  "sliding_window": 4096,
+  "transformer_block_type": "parallel",
+  "transformers_version": "4.56.2.4",
+  "use_cache": true,
+  "use_embedding_sharing": true,
+  "use_gated_activation": true,
+  "use_parallel_embedding": false,
+  "use_qk_norm": false,
+  "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 0,
+  "transformers_version": "4.56.2.4"
+}

model.safetensors.index.json

@@ -0,0 +1,478 @@
+{
+    "weight_map": {
+        "model.embed_tokens.weight": "worker-000-000.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "worker-000-000.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "worker-000-000.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "worker-000-000.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "worker-000-000.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "worker-000-000.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "worker-000-000.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "worker-000-000.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "worker-000-000.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "worker-000-000.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "worker-000-000.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "worker-000-000.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "worker-000-000.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "worker-000-000.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "worker-000-000.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "worker-000-000.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "worker-000-000.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "worker-000-000.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "worker-000-000.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "worker-000-000.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "worker-000-000.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "worker-000-000.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "worker-000-000.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "worker-000-000.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "worker-000-000.safetensors",
+        "model.layers.0.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.0.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.1.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.1.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.2.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.2.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.3.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.3.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.4.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.4.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.5.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.5.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.6.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.6.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.7.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.7.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.8.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.8.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.9.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.9.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.10.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.10.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.11.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.11.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.12.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.12.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.13.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.13.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.14.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.14.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.15.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.15.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.16.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.16.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.17.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.17.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.18.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.18.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.19.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.19.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.20.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.20.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.21.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.21.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.22.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.22.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.23.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.23.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.24.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.24.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.25.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.25.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.26.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.26.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.27.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.27.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.28.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.28.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.29.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.29.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.30.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.30.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.31.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.31.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.32.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.32.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.33.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.33.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.34.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.34.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.layers.35.mlp.up_proj.bias": "worker-000-000.safetensors",
+        "model.layers.35.mlp.gate_proj.bias": "worker-000-000.safetensors",
+        "model.norm.weight": "worker-000-000.safetensors",
+        "model.norm.bias": "worker-000-000.safetensors",
+        "model.layers.0.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.0.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.0.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.0.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.1.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.1.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.1.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.1.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.2.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.2.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.2.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.2.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.3.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.3.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.3.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.3.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.4.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.4.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.4.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.4.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.5.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.5.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.5.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.5.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.6.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.6.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.6.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.6.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.7.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.7.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.7.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.7.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.8.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.8.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.8.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.8.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.9.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.9.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.9.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.9.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.10.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.10.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.10.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.10.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.11.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.11.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.11.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.11.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.12.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.12.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.12.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.12.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.13.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.13.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.13.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.13.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.14.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.14.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.14.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.14.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.15.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.15.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.15.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.15.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.16.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.16.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.16.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.16.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.17.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.17.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.17.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.17.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.18.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.18.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.18.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.18.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.19.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.19.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.19.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.19.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.20.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.20.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.20.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.20.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.21.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.21.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.21.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.21.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.22.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.22.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.22.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.22.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.23.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.23.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.23.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.23.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.24.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.24.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.24.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.24.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.25.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.25.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.25.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.25.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.26.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.26.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.26.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.26.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.27.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.27.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.27.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.27.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.28.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.28.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.28.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.28.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.29.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.29.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.29.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.29.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.30.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.30.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.30.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.30.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.31.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.31.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.31.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.31.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.32.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.32.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.32.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.32.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.33.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.33.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.33.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.33.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.34.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.34.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.34.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.34.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.35.input_layernorm.weight": "worker-000-000.safetensors",
+        "model.layers.35.input_layernorm.bias": "worker-000-000.safetensors",
+        "model.layers.35.self_attn.o_proj.bias": "worker-000-000.safetensors",
+        "model.layers.35.mlp.down_proj.bias": "worker-000-000.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "worker-000-001.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "worker-000-001.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "worker-000-001.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "worker-000-001.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "worker-000-001.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "worker-000-002.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "worker-000-002.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "worker-000-002.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "worker-000-002.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "worker-000-002.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "worker-000-002.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "worker-000-002.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "worker-000-002.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "worker-000-002.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "worker-000-002.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "worker-000-002.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "worker-000-002.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "worker-000-003.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "worker-000-003.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "worker-000-003.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "worker-000-003.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "worker-000-003.safetensors"
+    },
+    "metadata": {
+        "total_size": 6700486656
+    }
+}

script.py

@@ -0,0 +1,421 @@
+"""IOL-AI 2026 submission — Tiny Aya bakeoff v4.
+
+Force-close <|END_THINKING|>, 1536+512, parser v3, prompt v3.
+CoT fallback (1024) when format/parse fails.
+M1: set USER_THINK_TOKEN="/think" + instruction-following addendum.
+A1: leave USER_THINK_TOKEN="".
+"""
+
+import os
+import subprocess
+import sys
+
+
+def _install_bundled_deps() -> None:
+    wheels_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "wheels")
+    if not os.path.isdir(wheels_dir):
+        return
+    subprocess.run(
+        [
+            sys.executable,
+            "-m",
+            "pip",
+            "install",
+            "-q",
+            "--no-index",
+            f"--find-links={wheels_dir}",
+            "transformers==4.56.2",
+        ],
+        check=True,
+    )
+
+
+_install_bundled_deps()
+
+os.environ["HF_HUB_OFFLINE"] = "1"
+os.environ["TRANSFORMERS_OFFLINE"] = "1"
+MODEL_ID = "."
+
+# "" for A1 (reasoning_options only); "/think" for M1 multilingual
+USER_THINK_TOKEN = "/think"
+
+import json
+import re
+
+import pandas as pd
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+END_THINKING = "<|END_THINKING|>"
+START_THINKING = "<|START_THINKING|>"
+
+THINKING_BUDGET = 1536
+ANSWER_CONTINUATION_TOKENS = 512
+COT_MAX_NEW_TOKENS = 1024  # T4 30min: capped CoT, not another 1536+512
+
+_SYSTEM_BASE = """You solve International Linguistics Olympiad (IOL) problems from the data you are given.
+You may see a task type you have never seen: follow the instruction and examples, and answer in the same form they use.
+
+What to return by task type:
+- translation: only the required form in the language the query asks for — do not add extra glosses or "form | meaning" unless asked
+- fill_blanks: only the missing form for each blank — no extra glosses
+- match_letters: ONLY the option letter (A, B, C, …), one letter per line — never copy option text, never arrows, never "A. word"
+- text_to_num: the number in digits only
+- num_to_text: the number written out in words, in the language asked
+- any other type: exactly what the instruction asks for, nothing else
+
+Answer in the language and form the query asks for. Do not add glosses, translations, or explanations unless the instruction requires them.
+
+Output rules:
+- Put answers ONLY after a line that says exactly: FINAL ANSWERS:
+- Never put answers before that marker.
+- One answer per line; exactly as many lines as items asked in the query.
+- Bare answers only: no numbering, no quotes, no commentary, no repeating the question."""
+
+_M1_ADDENDUM = """
+
+Extra hard rules:
+- Never refuse or apologize; always output FINAL ANSWERS: with your best guess.
+- For match_letters: only bare letters (A, B, C, …) — never dump the alphabet, never option text.
+- Never append glosses like "form – meaning" or "word - gloss"; bare answers only.
+- Emit exactly as many answer lines as items asked — no more, no fewer."""
+
+SYSTEM = _SYSTEM_BASE + (_M1_ADDENDUM if USER_THINK_TOKEN == "/think" else "")
+SYSTEM_COT = (
+    SYSTEM
+    + "\n\nThink step by step about the rules in the examples and how they apply to the query, "
+    "then write FINAL ANSWERS: and the answer lines."
+)
+
+# --- parser (inlined from parse_iol.py) ---
+_MD_PREFIX = r"(?:[#*_=\-\s`>]*)"
+_MARKER = re.compile(
+    rf"(?im)^{_MD_PREFIX}final\s+answers?{_MD_PREFIX}:?{_MD_PREFIX}\s*(.*)$"
+)
+_NUMBERING = re.compile(r"^\s*(?:\d+[.)]|[-*•])\s*")
+_TURN_NOISE = re.compile(
+    r"<\|/?END_OF_TURN_TOKEN\|>|<\|/?START_OF_TURN_TOKEN\|>|"
+    r"<\|CHATBOT_TOKEN\|>|<EOS_TOKEN>|<BOS_TOKEN>"
+)
+_RESPONSE_BLOCK = re.compile(
+    r"<\|START_RESPONSE\|>(.*?)<\|END_RESPONSE\|>",
+    flags=re.S,
+)
+_MD_WRAP = re.compile(r"^[*_`#\s]+|[*_`#\s]+$")
+_TRAILING_LETTER = re.compile(
+    r"(?:[–—\-]|→|->)\s*([A-Za-z])(?:\s*[.)]|)\s*$"
+)
+_LEADING_LETTER_OPT = re.compile(r"^([A-Za-z])\s*[.):\-–—]\s+\S")
+_WORD_THEN_LETTER = re.compile(r"^.+\s([A-Za-z])\s*$")
+_REFUSAL = re.compile(
+    r"(?i)\b("
+    r"i'?m sorry|i am sorry|i don'?t have|i cannot|i can'?t|"
+    r"unable to|not able to|no reliable|cannot supply|can'?t supply|"
+    r"as an ai|i apologize"
+    r")\b"
+)
+
+
+def _clean_line(line: str) -> str:
+    line = _NUMBERING.sub("", line).strip()
+    line = _MD_WRAP.sub("", line).strip()
+    line = line.replace("\u202f", " ").replace("\xa0", " ")
+    return line.strip()
+
+
+def after_thinking(text: str) -> str:
+    """Prefer content after the last <|END_THINKING|>; else drop an unclosed think block."""
+    if END_THINKING in text:
+        text = text.rsplit(END_THINKING, 1)[-1]
+    elif START_THINKING in text:
+        text = ""
+    return _TURN_NOISE.sub("", text)
+
+
+def _as_option_letter(line: str) -> str | None:
+    line = _clean_line(line)
+    if not line:
+        return None
+    if len(line) == 1 and line.isalpha():
+        return line.upper()
+    m = _LEADING_LETTER_OPT.match(line)
+    if m:
+        return m.group(1).upper()
+    m = _TRAILING_LETTER.search(line)
+    if m:
+        return m.group(1).upper()
+    if len(line) <= 40:
+        m = _WORD_THEN_LETTER.match(line)
+        if m:
+            return m.group(1).upper()
+    return None
+
+
+def _expand_line(line: str) -> list[str]:
+    line = _clean_line(line)
+    if not line:
+        return []
+    if len(line) == 1 and line.isalpha():
+        return [line]
+    if _LEADING_LETTER_OPT.match(line) or _TRAILING_LETTER.search(line):
+        letter = _as_option_letter(line)
+        if letter:
+            return [letter]
+    if len(line) <= 40 and _WORD_THEN_LETTER.match(line):
+        letter = _as_option_letter(line)
+        if letter:
+            return [letter]
+    if "|" in line:
+        parts = [p.strip() for p in line.split("|") if p.strip()]
+        if len(parts) >= 2:
+            if len(parts) >= 4 and len(parts) % 2 == 0:
+                left, right = parts[0::2], parts[1::2]
+                if sum(" " in r for r in right) >= max(1, len(right) // 2):
+                    return [_clean_line(x) for x in left if _clean_line(x)]
+            if len(parts) == 2:
+                a, b = parts
+                if (" " in b and " " not in a) or (
+                    len(b) > 2 * max(len(a), 1) and " " in b
+                ):
+                    return [_clean_line(a)] if _clean_line(a) else []
+            return [_clean_line(p) for p in parts if _clean_line(p)]
+    return [line]
+
+
+def _dedupe_runaway(parts: list[str]) -> list[str]:
+    if len(parts) < 6:
+        return parts
+    out: list[str] = []
+    run = 0
+    prev = None
+    for p in parts:
+        if p == prev:
+            run += 1
+            if run >= 4:
+                break
+        else:
+            run = 1
+            prev = p
+        out.append(p)
+    return out
+
+
+def _lines_from_region(region: str, *, allow_all_lines: bool) -> list[str]:
+    markers = list(_MARKER.finditer(region))
+    if markers:
+        last = markers[-1]
+        after_parts: list[str] = []
+        same = _clean_line(last.group(1) or "")
+        if same:
+            after_parts.extend(_expand_line(same))
+        for line in region[last.end() :].splitlines():
+            after_parts.extend(_expand_line(line))
+        if after_parts:
+            return _dedupe_runaway(after_parts)
+        before_parts: list[str] = []
+        for line in region[: last.start()].splitlines():
+            before_parts.extend(_expand_line(line))
+        if before_parts:
+            return _dedupe_runaway(before_parts)
+
+    parts: list[str] = []
+    for line in region.splitlines():
+        parts.extend(_expand_line(line))
+    if not parts:
+        return []
+    if allow_all_lines:
+        return _dedupe_runaway(parts)
+    return [parts[-1]]
+
+
+def parse_answers(
+    raw: str,
+    *,
+    n_expected: int | None = None,
+    task_type: str = "",
+) -> list[str]:
+    text = after_thinking(raw)
+    closed_blocks = _RESPONSE_BLOCK.findall(text)
+    answers: list[str] = []
+    if closed_blocks:
+        for region in reversed(closed_blocks):
+            answers = _lines_from_region(region.strip(), allow_all_lines=True)
+            if answers:
+                break
+    if not answers:
+        answers = _lines_from_region(text, allow_all_lines=False)
+
+    if task_type == "match_letters":
+        coerced: list[str] = []
+        for a in answers:
+            letter = _as_option_letter(a)
+            coerced.append(letter if letter else a)
+        answers = coerced
+
+    if n_expected is not None and n_expected > 0 and len(answers) > n_expected:
+        answers = answers[:n_expected]
+    return answers
+
+
+def _looks_like_alphabet_dump(answers: list[str]) -> bool:
+    letters = [a.strip().upper() for a in answers if len(a.strip()) == 1 and a.strip().isalpha()]
+    if len(letters) < 15:
+        return False
+    # sequential A,B,C… for a long prefix
+    seq = 0
+    for i, L in enumerate(letters):
+        if ord(L) == ord("A") + i:
+            seq += 1
+        else:
+            break
+    return seq >= 15
+
+
+def _looks_like_refusal(answers: list[str]) -> bool:
+    blob = " ".join(answers)
+    return bool(_REFUSAL.search(blob)) or len(blob) > 400 and "dictionary" in blob.lower()
+
+
+def has_usable_answer(
+    answers: list[str],
+    *,
+    n_expected: int | None = None,
+    task_type: str = "",
+) -> bool:
+    if not answers or not any(a.strip() for a in answers):
+        return False
+    if _looks_like_refusal(answers):
+        return False
+    if _looks_like_alphabet_dump(answers):
+        return False
+    if n_expected is not None and n_expected > 0 and len(answers) != n_expected:
+        return False
+    if task_type == "match_letters":
+        letters = [a for a in answers if len(a) == 1 and a.isalpha()]
+        if len(letters) < max(1, int(0.8 * len(answers))):
+            return False
+    return True
+
+
+def _n_items_guess(query: str) -> int:
+    nums = re.findall(r"(?m)^\s*(?:\(?\d+[.)]|\d+\))", query)
+    return len(nums) if nums else 0
+
+
+def _end_thinking_id(tok) -> int:
+    end_id = tok.convert_tokens_to_ids(END_THINKING)
+    if end_id is None or end_id == tok.unk_token_id:
+        ids = tok.encode(END_THINKING, add_special_tokens=False)
+        if len(ids) == 1:
+            end_id = ids[0]
+    if end_id is None or end_id == tok.unk_token_id:
+        raise RuntimeError(f"Tokenizer missing end-think token {END_THINKING!r}")
+    return int(end_id)
+
+
+def _build_prompt_ids(tok, system: str, user: str, *, thinking: bool):
+    messages = [
+        {"role": "system", "content": system},
+        {"role": "user", "content": user},
+    ]
+    try:
+        return tok.apply_chat_template(
+            messages,
+            add_generation_prompt=True,
+            return_tensors="pt",
+            reasoning_options={"enabled": thinking},
+        )
+    except TypeError:
+        return tok.apply_chat_template(
+            messages, add_generation_prompt=True, return_tensors="pt"
+        )
+
+
+@torch.inference_mode()
+def generate_with_think_budget(model, tok, prompt_ids, end_id: int):
+    device = next(model.parameters()).device
+    prompt_ids = prompt_ids.to(device)
+    prompt_len = prompt_ids.shape[-1]
+
+    think_out = model.generate(
+        prompt_ids,
+        max_new_tokens=THINKING_BUDGET,
+        do_sample=False,
+        pad_token_id=tok.pad_token_id or tok.eos_token_id,
+    )[0]
+    gen_ids = think_out[prompt_len:].tolist()
+    if end_id not in gen_ids:
+        cont = torch.cat(
+            [think_out, torch.tensor([end_id], device=device, dtype=think_out.dtype)]
+        )
+    else:
+        cont = think_out
+
+    full = model.generate(
+        cont.unsqueeze(0),
+        max_new_tokens=ANSWER_CONTINUATION_TOKENS,
+        do_sample=False,
+        pad_token_id=tok.pad_token_id or tok.eos_token_id,
+    )[0]
+    text = tok.decode(full[prompt_len:], skip_special_tokens=False)
+    return _TURN_NOISE.sub("", text).strip()
+
+
+@torch.inference_mode()
+def generate_plain(model, tok, prompt_ids, max_new_tokens: int):
+    device = next(model.parameters()).device
+    prompt_ids = prompt_ids.to(device)
+    prompt_len = prompt_ids.shape[-1]
+    out = model.generate(
+        prompt_ids,
+        max_new_tokens=max_new_tokens,
+        do_sample=False,
+        pad_token_id=tok.pad_token_id or tok.eos_token_id,
+    )[0]
+    text = tok.decode(out[prompt_len:], skip_special_tokens=False)
+    return _TURN_NOISE.sub("", text).strip()
+
+
+tok = AutoTokenizer.from_pretrained(MODEL_ID)
+end_id = _end_thinking_id(tok)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID, torch_dtype=torch.float16, device_map="auto"
+).eval()
+
+df = pd.read_csv("/tmp/data/test.csv", dtype=str).fillna("")
+
+rows = []
+for i, r in df.iterrows():
+    n_guess = _n_items_guess(r["query"])
+    task = str(r.get("task_type", "") or "")
+    n_exp = n_guess or None
+
+    user = f"{r['context'].strip()}\n\n{r['query'].strip()}"
+    if n_guess:
+        user += f"\n\n(Emit exactly {n_guess} answer line(s) after FINAL ANSWERS:.)"
+    user_think = user
+    if USER_THINK_TOKEN:
+        user_think += f"\n{USER_THINK_TOKEN}"
+
+    ids = _build_prompt_ids(tok, SYSTEM, user_think, thinking=True)
+    text = generate_with_think_budget(model, tok, ids, end_id)
+    answers = parse_answers(text, n_expected=n_exp, task_type=task)
+    used_cot = False
+
+    if not has_usable_answer(answers, n_expected=n_exp, task_type=task):
+        used_cot = True
+        # CoT: no /think, thinking channel off, capped budget
+        cot_ids = _build_prompt_ids(tok, SYSTEM_COT, user, thinking=False)
+        cot_text = generate_plain(model, tok, cot_ids, COT_MAX_NEW_TOKENS)
+        cot_answers = parse_answers(cot_text, n_expected=n_exp, task_type=task)
+        if has_usable_answer(cot_answers, n_expected=n_exp, task_type=task):
+            answers = cot_answers
+
+    rows.append({"id": r["id"], "pred": json.dumps(answers, ensure_ascii=False)})
+    print(
+        f"[{i + 1}/{len(df)}] {len(answers)} answers cot={used_cot}",
+        flush=True,
+    )
+
+pd.DataFrame(rows).to_csv("submission.csv", index=False)
+print("wrote submission.csv", flush=True)

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+    "bos_token": {
+        "content": "<BOS_TOKEN>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false
+    },
+    "eos_token": {
+        "content": "<EOS_TOKEN>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false
+    },
+    "pad_token": {
+        "content": "<PAD>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false
+    },
+    "unk_token": {
+        "content": "<UNK>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false
+    },
+    "additional_special_tokens": [
+        "<|START_RESPONSE|>",
+        "<|END_RESPONSE|>",
+        "<|START_ACTION|>",
+        "<|END_ACTION|>",
+        "<|START_TOOL_RESULT|>",
+        "<|END_TOOL_RESULT|>",
+        "<|START_THINKING|>",
+        "<|END_THINKING|>"
+    ]
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55388a861271fb6b9eb631670e5eee0562bcddf204dc63494d98ee67f5551839
+size 30245131

tokenizer_config.json

@@ -0,0 +1,202 @@
+{
+    "add_bos_token": true,
+    "add_eos_token": false,
+    "add_prefix_space": false,
+    "clean_up_tokenization_spaces": false,
+    "legacy": true,
+    "spaces_between_special_tokens": false,
+    "use_default_system_prompt": false,
+    "bos_token": "<BOS_TOKEN>",
+    "eos_token": "<EOS_TOKEN>",
+    "pad_token": "<PAD>",
+    "unk_token": "<UNK>",
+    "tokenizer_class": "CohereTokenizerFast",
+    "model_max_length": 1000000000000000019884624838656,
+    "sp_model_kwargs": {},
+    "added_tokens_decoder": {
+        "0": {
+            "content": "<PAD>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "1": {
+            "content": "<MASK_TOKEN>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "2": {
+            "content": "<BOS_TOKEN>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "3": {
+            "content": "<EOS_TOKEN>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "4": {
+            "content": "<UNK>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "5": {
+            "content": "<|START_OF_TURN_TOKEN|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "6": {
+            "content": "<|END_OF_TURN_TOKEN|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "7": {
+            "content": "<|USER_TOKEN|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "8": {
+            "content": "<|CHATBOT_TOKEN|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "9": {
+            "content": "<|SYSTEM_TOKEN|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "10": {
+            "content": "<|NEW_FILE|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "11": {
+            "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "12": {
+            "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "13": {
+            "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "14": {
+            "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "261000": {
+            "content": "<|START_RESPONSE|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "261001": {
+            "content": "<|END_RESPONSE|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "261002": {
+            "content": "<|START_ACTION|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "261003": {
+            "content": "<|END_ACTION|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "261004": {
+            "content": "<|START_TOOL_RESULT|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "261005": {
+            "content": "<|END_TOOL_RESULT|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "261006": {
+            "content": "<|START_THINKING|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "261007": {
+            "content": "<|END_THINKING|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        }
+    }
+}

wheels/certifi-2026.6.17-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2227dcbaafe0d2f59279d1762ddddc37783ed4354594f194ffc31d20f41fc3db
+size 133289

wheels/charset_normalizer-3.4.9-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb41182d93ea91f60b4bc8fbf4c820c69ef8a12ab2d917f3f1834f1acad07e8
+size 223817

wheels/fsspec-2026.6.0-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e0b71817df9b2169dc30a16832045764def1191b43dcff5bb85bdee212d2a1
+size 203949

wheels/hf_xet-1.5.1-cp37-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892e3a3a3aecc12aded8b93cf4f9cd059282c7de0732f7d55026f3abdf474350
+size 4514864

wheels/huggingface_hub-0.36.2-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f0c8eac16145dfce371e9d2d7772854a4f591bcb56c9cf548accf531d54270
+size 566395

wheels/numpy-2.2.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc7b73d02efb0e18c000e9ad8b83480dfcd5dfd11065997ed4c6747470ae8915
+size 16801050

wheels/packaging-26.2-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fc45236b9446107ff2415ce77c807cee2862cb6fac22b8a73826d0693b0980e
+size 100195

wheels/pyyaml-6.0.3-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7708761fccb9397fe64bbc0395abcae8c4bf7b0eac081e12b809bf47700d0b
+size 770293

wheels/regex-2026.6.28-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f7e0cc60c72486b42a685f1ff4eec90d50d4fb05e4f9c7d5363b03aa02600d
+size 794116

wheels/safetensors-0.8.0-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6f3f93c9a0a7cc2788ee63fb763353d4bd2e89b0751bc78fcf7dda00bea774
+size 516040

wheels/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369cc9fc8cc10cb24143873a0d95438bb8ee257bb80c71989e3ee290e8d72c67
+size 3274982

wheels/tqdm-4.68.4-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5168118b2368f48c561afda8020fd79195b1bdb0bdf8086b88442c267a315dc2
+size 676612

wheels/transformers-4.56.2-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c03d0e85b26cb573c109ff9eafa96f3c8d4febfd8a0774e8bba32702dd6dde
+size 11608055

wheels/urllib3-2.7.0-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb4c81ebbb1ce9531cce37674bbc6f1360472bc18ca9a553ede278ef7276897
+size 131087

worker-000-000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec68be6469b8cfb70e6558b523444c0f1ecb2e92fb5d898237810e56c5b7f2e
+size 1998698496

worker-000-001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af43378efedd477921f66a8cc99e22d0c16f3471542f74865f27cb325f8dc7d
+size 1996494056

worker-000-002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d8cb6e8ce84f04fac324554f884409399264e9ffadbd8dfcc44dfadafb4ebdc
+size 1996494088

worker-000-003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e3a2b976343ffb775c7dbaae4cde20dd258492b30709e1efb3126636a6ddee
+size 708852792