初始化项目，由ModelHub XC社区提供模型

Model: vysri/SmolLM135M-IT-ConvFill
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

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}, 
+}
+```

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_parameters": {
+    "rope_theta": 100000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "5.5.4",
+  "use_cache": true,
+  "vocab_size": 49153
+}

config.snapshot.json

@@ -0,0 +1,36 @@
+{
+  "model_name": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "dataset_path": "your_dataset_path_here",
+  "dataset_mode": "full",
+  "platform": "gpu",
+  "wanb_project": "convfill",
+  "training_split_percent": 0.9,
+  "add_special_tokens": true,
+  "special_tokens": {
+    "additional_special_tokens": [
+      "<sil>"
+    ]
+  },
+  "boundary_tokens": {
+    "USER_START": "<|im_start|>user\n",
+    "KNOWLEDGE_START": "<|im_start|>knowledge\n",
+    "ASSN_START": "<|im_start|>assistant\n",
+    "END": "<|im_end|>\n"
+  },
+  "training_config": {
+    "batch_size": 4,
+    "accumulate_grad_batches": 4,
+    "num_epochs": 1,
+    "learning_rate": 0.0001,
+    "weight_decay": 0.01,
+    "warmup_steps": 200,
+    "scheduler": "cosine",
+    "val_check_interval": 0.25
+  },
+  "logging_config": {
+    "log_every_n_steps": 10
+  },
+  "checkpoint_config": {
+    "every_n_train_steps": 50
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "5.5.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e521201b918d98dbc15a0b7d3a594a2027f717f6c61597776ce5a7b85b2ef8fc
+size 269061704

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<sil>"
+  ],
+  "is_local": false,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}