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 +1,60 @@
+{
+  "architectures": [
+    "Lfm2ForCausalLM"
+  ],
+  "block_auto_adjust_ff_dim": true,
+  "block_dim": 1024,
+  "block_ff_dim": 6656,
+  "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": "bfloat16",
+  "eos_token_id": 7,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 6656,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "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": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "tie_embedding": true,
+  "transformers_version": "5.0.0rc1",
+  "use_cache": true,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 7,
+  "pad_token_id": 0,
+  "transformers_version": "5.0.0rc1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc7e8bbc4aab49d95a57df40629f89518affe9621dd2e3206bd346bb9e3336e
+size 421600080

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020d5723f5cec8ff3299702659a908ad1a1a93bd913b7ddf4d32d89e732d3cdc
+size 287384296

model.safetensors.index.json

@@ -0,0 +1,155 @@
+{
+  "metadata": {
+    "total_size": 708967936
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.embedding_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.conv.conv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.operator_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.conv.conv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.operator_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.operator_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.conv.conv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.operator_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.operator_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.conv.conv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.operator_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.operator_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.conv.conv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.operator_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.operator_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.conv.conv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.conv.in_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.conv.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.operator_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.conv.conv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.conv.in_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.conv.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.operator_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.operator_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.conv.conv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.conv.in_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.conv.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.operator_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.conv.conv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.conv.in_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.conv.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.operator_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.operator_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.conv.conv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.conv.in_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.conv.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.operator_norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": null,
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [],
+  "is_local": true,
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|pad|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}