Skip to content
ModelListedExternal
Download

Qwen3 1.7b Voice Light Tool Use Merged

This repository is the standalone BF16 inference checkpoint for the Voice Light conversational model. It merges the Voice Light tool-use LoRA into the original Qwen3-1.7B weights. It does not require PEFT or dynamic...

Sourcehuggingface.co/BertilBraun/qwen3-1.7b-voice-light-tool-use-merged/tree/557314e1a6839183e61a48833911606a23379d15
KindOtherBase modelQwen/Qwen3-1.7BVersionRevision 557314eBgrade

Model source

Kind
Other
File size
3.20 GB
Base model
Qwen/Qwen3-1.7B
Version
vRevision 557314e
Updated
Oct 9, 2026
Downloads
13
Source
Hugging Face

Source description

Voice Light Qwen3 1.7B Tool-Use - Merged

This repository is the standalone BF16 inference checkpoint for the Voice Light conversational model. It merges the Voice Light tool-use LoRA into the original Qwen3-1.7B weights. It does not require PEFT or dynamic LoRA loading at inference time.

Sources

Refer to those repositories for the original model documentation, adapter training information, licenses, and intended-use constraints.

The dataset includes the exact teacher-led v22 generator snapshot, locked environment, tests, teacher-server command, end-to-end reproduction launcher, immutable teacher revision, generation manifests, deterministic scenario seeds, and file hashes under reproducibility/source-8c32f70.

Merge

  • Method: PEFT merge_and_unload(safe_merge=True)
  • Merge device: CPU
  • Weight format: safetensors with a 5GB maximum shard size
  • Weight dtype: BF16
  • Hugging Face Hub: 1.18.0
  • Safetensors: 0.8.0
  • Transformers: 5.14.1
  • PEFT: 0.18.1
  • PyTorch: 2.11.0+cu130

The exact machine-readable source revisions and merge settings are included in merge-provenance.json. The destination repository expected when this artifact was built is BertilBraun/qwen3-1.7b-voice-light-tool-use-merged.

Sources

1 source
Hugging FacePrimaryVersion 557314e1a6839183e61a48833911606a23379d15
huggingface.co/BertilBraun/qwen3-1.7b-voice-light-tool-use-merged/tree/557314e1a6839183e61a48833911606a23379d15

Verified Oct 9

Model artifacts

1 artifact

model.safetensors

safetensors · 3.20 GB · SHA-256 94523b4ce6cd…9322 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeJul 31huggingface.co/BertilBraun/qwen3-1.7b-voice-light-tool-use-merged

--- base_model: Qwen/Qwen3-1.7B library_name: transformers pipeline_tag: text-generation datasets: - BertilBraun/voice-light-tool-use-synthetic tags: - qwen3 - voice-assistant - tool-use - lora - merged --- # Voice Light Qwen3 1.7B Tool-Use - Merged This repository is the standalone BF16 inference checkpoint for the Voice Light conversational model. It merges the Voice Light tool-use LoRA into the original Qwen3-1.7B weights. It does not require PEFT or dynamic LoRA loading at inference time. ## Sources - Base model: [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B/tree/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e) at revision `70d244cc86ccca08cf5af4e1e306ecf908b1ad5e` - LoRA adapter: [BertilBraun/qwen3-1.7b-voice-light-tool-use-lora](https://huggingface.co/BertilBraun/qwen3-1.7b-voice-light-tool-use-lora/tree/5c88c42fe092159e960126823223c3f46056cd7d) at revision `5c88c42fe092159e960126823223c3f46056cd7d` - Training dataset: [BertilBraun/voice-light-tool-use-synthetic](https://huggingface.co/datasets/BertilBraun/voice-light-tool-use-synthetic) Refer to those repositories for the original model documentation, adapter training information, licenses, and intended-use constraints. The dataset includes the exact teacher-led v22 generator snapshot, locked environment, tests, teacher-server command, end-to-end reproduction launcher, immutable teacher revision, generation manifests, deterministic scenario seeds, and file hashes under [`reproducibility/source-8c32f70`](https://huggingface.co/datasets/BertilBraun/voice-light-tool-use-synthetic/tree/9af7e4178f40bf09017cb61f63deaff688b26179/reproducibility/source-8c32f70). ## Merge - Method: PEFT `merge_and_unload(safe_merge=True)` - Merge device: CPU - Weight format: safetensors with a `5GB` maximum shard size - Weight dtype: BF16 - Hugging Face Hub: `1.18.0` - Safetensors: `0.8.0` - Transformers: `5.14.1` - PEFT: `0.18.1` - PyTorch: `2.11.0+cu130` The exact machine-readable source revisions and merge settings are included in `merge-provenance.json`. The destination repository expected when this artifact was built is `BertilBraun/qwen3-1.7b-voice-light-tool-use-merged`.

NoteOct 9huggingface.co/BertilBraun/qwen3-1.7b-voice-light-tool-use-merged

Source context: 13 downloads · 0 likes · Pipeline text-generation · Library transformers · Repo BertilBraun/qwen3-1.7b-voice-light-tool-use-merged

NoteJul 31huggingface.co/BertilBraun/qwen3-1.7b-voice-light-tool-use-merged

Source context: 60 downloads · 0 likes · Pipeline text-generation · Library transformers · Repo BertilBraun/qwen3-1.7b-voice-light-tool-use-merged