Upload folder using huggingface_hub

README.md

@@ -0,0 +1,47 @@
+---
+base_model: Qwen/Qwen3-VL-8B-Instruct
+library_name: peft
+license: apache-2.0
+language:
+  - en
+tags:
+  - lora
+  - multimodal
+  - embedding
+  - retrieval
+  - chain-of-thought
+  - qwen3-vl
+pipeline_tag: feature-extraction
+---
+
+# TWN-8B
+
+The 8B version of [Think When Needed (TWN)](https://github.com/winterfell00/Think-When-Needed), a framework for adaptive reasoning-driven multimodal embeddings. TWN introduces a dual-LoRA architecture on top of [Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct) with a learned routing gate that adaptively activates chain-of-thought reasoning.
+
+## Weight Structure
+
+```
+TWN-8B/
+  reasoning/                 # LoRA adapter for CoT generation
+    adapter_config.json
+    adapter_model.safetensors
+  embedding/                 # LoRA adapter for embedding extraction
+    adapter_config.json
+    adapter_model.safetensors
+  gate_mlp.pt                # Routing gate MLP weights
+  queries.pt                 # Learnable query embeddings
+```
+
+## Citation
+
+```bibtex
+@article{zhang2026thinkneeded,
+      title={Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture},
+      author={Longxiang Zhang and Weilong Dai and Guanghao Zhang and Hao Jiang and Pipei Huang},
+      year={2026},
+      eprint={2605.14448},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2605.14448},
+}
+```

embedding/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-VL-8B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual\\.).*(q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)$",
+  "target_parameters": null,
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

embedding/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3396188f161fef48aee411cda276371e5527b4132672386a721e0860cb7248b4
+size 349251816

gate_mlp.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e13ca2f68b931e40aa1d1d80163583364b586df3190debed1e97eae162f587
+size 8428334

queries.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6832f262f597e24cec336ec54c2c74f5a9a286ed3ba0aa7c374a389c3ec0b532
+size 263388

reasoning/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-VL-8B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual\\.).*(q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)$",
+  "target_parameters": null,
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

reasoning/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be8334c679a81741b20e1328dd40b8e79cb923180bcef2914d9fdeddb29d76de
+size 698427288