初始化项目，由ModelHub XC社区提供模型

Model: vysri/SmolLM135M-IT-ConvFill Source: Original Platform
2026-07-27 22:46:32 +08:00
commit e56776becd
9 changed files with 245174 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,56 @@
+---
+license: apache-2.0
+base_model:
+- HuggingFaceTB/SmolLM2-135M-Instruct
+language:
+- en
+pipeline_tag: text-generation
+datasets:
+- zenglhardt/convfill-dataset
+---
+# Model Card for SmolLM135M-IT-ConvFill
+
+This model card implements a finetune of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) for the conversational infill task described in the [ConvFill paper](https://arxiv.org/abs/2511.07397).
+
+## Model Details
+
+This model should be used respecting the original license of the base model, HuggingFaceTB/SmolLM2-135M-Instruct. The dataset that was used to finetune this model can be found [here](https://huggingface.co/datasets/zenglhardt/convfill-dataset).
+
+### Model Description
+Deploying responsive, multi-turn conversational voice agents with large language models poses a critical challenge: cloud-based foundation models utilize reasoning, information retrieval, and tool use for high-value tasks, but introduce latency that disrupts natural conversation. In contrast, small models can respond quickly but lack capabilities needed in real-world tasks. We propose _conversational infill_, a task where a small, local model generates prompt, contextually appropriate dialogue and seamlessly incorporates delayed, external knowledge produced in parallel by a foundation model backend. This finetune trains HuggingFaceTB/SmolLM2-135M-Instruct to perform the conversational infill task.
+
+- **Finetuned from model:** [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct)
+- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
+
+### Model Sources [optional]
+
+- **Repository:** https://github.com/vysri/conversational-infill
+- **Paper:** [Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents](https://arxiv.org/abs/2511.07397)
+- **Demo:** TBD
+
+### Direct Use
+
+This model is intended to be used with the infrastructure in the [ConvFill repository](https://github.com/vysri/conversational-infill).
+
+## Bias, Risks, and Limitations
+
+This model is not explicitly tuned for guardrailed behavior. Please use with caution.
+
+## How to Get Started with the Model
+Use the code in the [ConvFill repository](https://github.com/vysri/conversational-infill) to get started with this model.
+
+### Training Data
+A link to the training data for this model can be found [here](https://huggingface.co/datasets/zenglhardt/convfill-dataset). The dataset generation procedure can be found [here](https://github.com/zenglhardt/convfill-dataset). Information on training procedures can be found in the [ConvFill paper](https://arxiv.org/abs/2511.07397). Training code and scripts can be found in the [ConvFill repository](https://github.com/vysri/conversational-infill). 
+
+## Citation
+```
+@misc{srinivas2026thinkingspeakinginferencetimeknowledge,
+      title={Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents}, 
+      author={Vidya Srinivas and Zachary Englhardt and Shwetak Patel and Vikram Iyer},
+      year={2026},
+      eprint={2511.07397},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2511.07397}, 
+}
+```