Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1,64 @@
+{{- bos_token -}}
+{%- set keep_past_thinking = keep_past_thinking | default(false) -%}
+{%- set ns = namespace(system_prompt="") -%}
+{%- if messages[0]["role"] == "system" -%}
+    {%- set sys_content = messages[0]["content"] -%}
+    {%- if sys_content is not string -%}
+        {%- for item in sys_content -%}
+            {%- if item["type"] == "text" -%}
+                {%- set ns.system_prompt = ns.system_prompt + item["text"] -%}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {%- set ns.system_prompt = sys_content -%}
+    {%- endif -%}
+    {%- set messages = messages[1:] -%}
+{%- endif -%}
+{%- if tools -%}
+    {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
+    {%- for tool in tools -%}
+        {%- if tool is not string -%}
+            {%- set tool = tool | tojson -%}
+        {%- endif -%}
+        {%- set ns.system_prompt = ns.system_prompt + tool -%}
+        {%- if not loop.last -%}
+            {%- set ns.system_prompt = ns.system_prompt + ", " -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- set ns.system_prompt = ns.system_prompt + "]" -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+    {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- set ns.last_assistant_index = -1 -%}
+{%- for message in messages -%}
+    {%- if message["role"] == "assistant" -%}
+        {%- set ns.last_assistant_index = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- for message in messages -%}
+    {{- "<|im_start|>" + message["role"] + "\n" -}}
+    {%- set content = message["content"] -%}
+    {%- if content is not string -%}
+        {%- set ns.content = "" -%}
+        {%- for item in content -%}
+            {%- if item["type"] == "image" -%}
+                {%- set ns.content = ns.content + "<image>" -%}
+            {%- elif item["type"] == "text" -%}
+                {%- set ns.content = ns.content + item["text"] -%}
+            {%- else -%}
+                {%- set ns.content = ns.content + item | tojson -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- set content = ns.content -%}
+    {%- endif -%}
+    {%- if message["role"] == "assistant" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}
+        {%- if "</think>" in content -%}
+            {%- set content = content.split("</think>")[-1] | trim -%}
+        {%- endif -%}
+    {%- endif -%}
+    {{- content + "<|im_end|>\n" -}}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "<|im_start|>assistant\n" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,127 @@
+{
+  "architectures": [
+    "DatauseEncoder"
+  ],
+  "auto_map": {
+    "AutoModel": "modeling_lfm2_bidirectional.Lfm2BidirectionalModel",
+    "AutoModelForMaskedLM": "modeling_lfm2_bidirectional.Lfm2BidirectionalForMaskedLM"
+  },
+  "block_auto_adjust_ff_dim": false,
+  "block_dim": 1024,
+  "block_ffn_dim_multiplier": 1.0,
+  "block_mlp_init_scale": 1.0,
+  "block_multiple_of": 256,
+  "block_norm_eps": 1e-05,
+  "block_out_init_scale": 1.0,
+  "block_use_swiglu": true,
+  "block_use_xavier_init": true,
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "conv_dim": 1024,
+  "conv_use_xavier_init": true,
+  "dtype": "float32",
+  "eos_token_id": 7,
+  "full_attn_idxs": null,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Agriculture",
+    "1": "Communities and Human Settlements",
+    "2": "Conflict and Development",
+    "3": "Culture and Development",
+    "4": "Education",
+    "5": "Energy",
+    "6": "Environment",
+    "7": "Finance and Financial Sector Development",
+    "8": "Gender",
+    "9": "Governance",
+    "10": "Health",
+    "11": "Industry",
+    "12": "Informatics",
+    "13": "Information and Communication Technologies",
+    "14": "Infrastructure Economics and Finance",
+    "15": "International Economics and Trade",
+    "16": "Law and Development",
+    "17": "Macroeconomics and Economic Growth",
+    "18": "Nutrition and Population",
+    "19": "Poverty Reduction",
+    "20": "Private Sector Development",
+    "21": "Public Sector Development",
+    "22": "Rural Development",
+    "23": "Science and Technology Development",
+    "24": "Social Development",
+    "25": "Social Protections and Labor",
+    "26": "Transport",
+    "27": "Urban Development",
+    "28": "Water Resources",
+    "29": "Water Supply and Sanitation"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "label2id": {
+    "Agriculture": 0,
+    "Communities and Human Settlements": 1,
+    "Conflict and Development": 2,
+    "Culture and Development": 3,
+    "Education": 4,
+    "Energy": 5,
+    "Environment": 6,
+    "Finance and Financial Sector Development": 7,
+    "Gender": 8,
+    "Governance": 9,
+    "Health": 10,
+    "Industry": 11,
+    "Informatics": 12,
+    "Information and Communication Technologies": 13,
+    "Infrastructure Economics and Finance": 14,
+    "International Economics and Trade": 15,
+    "Law and Development": 16,
+    "Macroeconomics and Economic Growth": 17,
+    "Nutrition and Population": 18,
+    "Poverty Reduction": 19,
+    "Private Sector Development": 20,
+    "Public Sector Development": 21,
+    "Rural Development": 22,
+    "Science and Technology Development": 23,
+    "Social Development": 24,
+    "Social Protections and Labor": 25,
+    "Transport": 26,
+    "Urban Development": 27,
+    "Water Resources": 28,
+    "Water Supply and Sanitation": 29
+  },
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv"
+  ],
+  "max_position_embeddings": 128000,
+  "model_type": "lfm2",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 16,
+  "num_heads": 16,
+  "num_hidden_layers": 14,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.13.1",
+  "use_cache": false,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf9c6aaf42ed14dc91037daf9097fb4a3616d2c474222fcefca07a42981a959
+size 918915196

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<|mask|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend"
+}