From dc1ec9516c6adc6f3e922d418511f073439f942b Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 29 Aug 2026 22:35:20 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: vysri/Qwen-0.6B-ConvFill Source: Original Platform --- .gitattributes | 36 +++++++++++++++++ README.md | 57 +++++++++++++++++++++++++++ chat_template.jinja | 89 ++++++++++++++++++++++++++++++++++++++++++ config.json | 63 ++++++++++++++++++++++++++++++ config.snapshot.json | 36 +++++++++++++++++ generation_config.json | 13 ++++++ model.safetensors | 3 ++ tokenizer.json | 3 ++ tokenizer_config.json | 17 ++++++++ 9 files changed, 317 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 config.snapshot.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..02a37f6 --- /dev/null +++ b/README.md @@ -0,0 +1,57 @@ +--- +base_model: +- Qwen/Qwen3-0.6B +datasets: +- zenglhardt/convfill-dataset +language: +- en +license: apache-2.0 +pipeline_tag: text-generation +--- + +# Model Card for Qwen-0.6B-ConvFill + +This model card implements a finetune of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) 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, Qwen/Qwen3-0.6B. 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 Qwen/Qwen3-0.6B to perform the conversational infill task. + +- **Finetuned from model:** [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) +- **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 Vikram Iyer and Shwetak Patel}, + year={2026}, + eprint={2511.07397}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2511.07397}, +} +``` \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..01bafff --- /dev/null +++ b/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.5.4", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151670 +} diff --git a/config.snapshot.json b/config.snapshot.json new file mode 100644 index 0000000..7e8eb2f --- /dev/null +++ b/config.snapshot.json @@ -0,0 +1,36 @@ +{ + "model_name": "Qwen/Qwen3-0.6B", + "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": [ + "" + ] + }, + "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 + } +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..3775feb --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.5.4" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..6c292f3 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64006b337a280c802de3cf891f8b3adb1dafc5936e1a1447ed6b5a14e1accbbe +size 1191590328 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..e9f8633 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc4c87889032b5edf8266edcd7d03c8bd66284d3df3fe23c90483b65e14f050 +size 11422832 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9eeec83 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,17 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "" + ], + "is_local": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}