Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,4 @@ lfm2.5-1.2B-instruct/original/lfm2_5_1_2b_fp16.pte filter=lfs diff=lfs merge=lfs
 lfm2.5-1.2B-instruct/quantized/lfm2_5_1_2b_8da4w.pte filter=lfs diff=lfs merge=lfs -text
 lfm2.5-350M/xnnpack/lfm2_5_350m_xnnpack_8w4da.pte filter=lfs diff=lfs merge=lfs -text
 lfm2.5-350M/xnnpack/lfm2_5_350m_xnnpack_fp16.pte filter=lfs diff=lfs merge=lfs -text
+lfm2.5-VL-1.6B/quantized/lfm2_5_vl_1_6b_8da4w_xnnpack.pte filter=lfs diff=lfs merge=lfs -text

lfm2.5-VL-1.6B/.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+quantized/lfm2_5_vl_1_6b_8da4w_xnnpack.pte filter=lfs diff=lfs merge=lfs -text

lfm2.5-VL-1.6B/README.md

@@ -0,0 +1,29 @@
+---
+license: other
+license_name: lfm1.0
+license_link: https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B/blob/main/LICENSE
+pipeline_tag: image-text-to-text
+tags:
+- liquid
+- lfm2
+- lfm2-vl
+- edge
+- lfm2.5-vl
+- lfm2.5
+---
+
+# Introduction
+
+This repository hosts the **LFM2.5-VL-1.6B** vision-language model for the [React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It includes a **quantized** version in `.pte` format, ready for use in the **ExecuTorch** runtime.
+
+If you'd like to run these models in your own ExecuTorch runtime, refer to the [official documentation](https://pytorch.org/executorch/stable/index.html) for setup instructions.
+
+## Compatibility
+
+If you intend to use this model outside of React Native ExecuTorch, make sure your runtime is compatible with the **ExecuTorch** version used to export the `.pte` files. For more details, see the compatibility note in the [ExecuTorch GitHub repository](https://github.com/pytorch/executorch/blob/11d1742fdeddcf05bc30a6cfac321d2a2e3b6768/runtime/COMPATIBILITY.md?plain=1#L4). If you work with React Native ExecuTorch, the constants from the library will guarantee compatibility with the runtime used behind the scenes.
+
+## Repository Structure
+
+The repository is organized as follows:
+- The `.pte` file should be passed to the `modelSource` parameter.
+- The tokenizer files are available in the repo root: `tokenizer.json` and `tokenizer_config.json` should be passed to `tokenizerSource` and `tokenizerConfigSource` respectively.

lfm2.5-VL-1.6B/quantized/config.json

@@ -0,0 +1,97 @@
+{
+  "architectures": [
+    "Lfm2VlForConditionalGeneration"
+  ],
+  "do_image_splitting": true,
+  "downsample_factor": 2,
+  "dtype": "bfloat16",
+  "encoder_patch_size": 16,
+  "image_token_id": 396,
+  "max_image_tokens": 256,
+  "max_pixels_tolerance": 2.0,
+  "max_tiles": 10,
+  "min_image_tokens": 64,
+  "min_tiles": 2,
+  "model_type": "lfm2_vl",
+  "projector_bias": true,
+  "projector_hidden_act": "gelu",
+  "projector_hidden_size": 2048,
+  "projector_use_layernorm": false,
+  "text_config": {
+    "_name_or_path": "LiquidAI/LFM2-1.2B",
+    "architectures": [
+      "Lfm2ForCausalLM"
+    ],
+    "block_auto_adjust_ff_dim": true,
+    "block_dim": 2048,
+    "block_ff_dim": 12288,
+    "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,
+    "conv_L_cache": 3,
+    "conv_bias": false,
+    "conv_dim": 2048,
+    "conv_dim_out": 2048,
+    "conv_use_xavier_init": true,
+    "dtype": "bfloat16",
+    "eos_token_id": 7,
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "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": 32,
+    "num_heads": 32,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 8,
+    "rope_parameters": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "use_cache": true,
+    "use_pos_enc": true,
+    "vocab_size": 65536
+  },
+  "tile_size": 512,
+  "transformers_version": "5.0.0.dev0",
+  "use_image_special_tokens": true,
+  "use_thumbnail": true,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip2_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "num_patches": 256,
+    "patch_size": 16,
+    "vision_use_head": false
+  }
+}

lfm2.5-VL-1.6B/quantized/lfm2_5_vl_1_6b_8da4w_xnnpack.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f942c856acfe1a4d0b5f8d30bd752b5552bcf20bc6dfa6f3253896b2456d0c4
+size 2427656704

lfm2.5-VL-1.6B/tokenizer_config.json

@@ -0,0 +1,28 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "image_end_token": "<|image_end|>",
+  "image_start_token": "<|image_start|>",
+  "image_thumbnail": "<|img_thumbnail|>",
+  "image_token": "<image>",
+  "is_local": true,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "image_end_token": "<|image_end|>",
+    "image_start_token": "<|image_start|>",
+    "image_thumbnail": "<|img_thumbnail|>",
+    "image_token": "<image>"
+  },
+  "pad_token": "<|pad|>",
+  "processor_class": "Lfm2VlProcessor",
+  "return_token_type_ids": false,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false,
+  "use_fast": true,
+  "chat_template": "{%- 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\" -}}{%- if message[\"content\"] is not string -%}{%- set ns.content = \"\" -%}{%- for item in message[\"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 -%}{%- else -%}{%- set content = message[\"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 -%}"
+}