Instructions to use VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4")
model = AutoModelForCausalLM.from_pretrained("VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4

SGLang

How to use VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4 with Docker Model Runner:
```
docker model run hf.co/VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4
```

qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4 / README.md

Andrewsab

V15 R-3 Win-CUDA cuda-int4-nf4 ship-form (Win port of macOS WP#919)

fca80e1 verified 3 months ago

preview code

Raw

History Blame Contribute Delete

4.84 kB

	---
	license: apache-2.0
	language: ru
	library_name: transformers
	base_model: Qwen/Qwen3.5-0.8B
	tags:
	- dictation
	- russian
	- lora
	- VoiceScribe
	- corrector
	- qwen3.5
	datasets:
	- VoiceScribe/dictation-corrector-seed
	metrics:
	- exact-match
	---

	# Voice Scribe Russian Dictation Corrector (Qwen3.5-0.8B, V15 R-3, cuda-int4-nf4)

	Consumer ship-form: bitsandbytes 4-bit NF4 (double-quant). ~750 MB. -12pp wild vs bf16 (still passes consumer gate >=78%); preserves hard-neg 5/5 absolute. Target: RTX 2060+/6GB.

	## Eval results (held-out wild_eval, 58 prompts × 9 sectors)

	\| Metric \| Score \|
	\|---\|---:\|
	\| Wild pass \| 84.48% \|
	\| Hard-negative \| 5/5 \|
	\| Smoke \| 8/8 \|
	\| p50 latency \| 676 ms \|
	\| Ship-form size \| 750 MB \|

	Comparison:
	- macOS V15 R-3 reference: 93.1% wild
	- V14 baseline: 86.2%
	- Qwen3-4B Q5 production (pre-LoRA): 48%
	- This model: 84.48% (-1.7pp vs V14 baseline)

	## Training recipe (V15 R-3)

	Mirrors macOS `configs/r4_v15_extended.yaml` byte-for-byte logical-recipe.

	```
	base = Qwen/Qwen3.5-0.8B (vanilla, NOT Instruct)
	LoRA rank = 16
	LoRA alpha = 80 (rsLoRA mode -> effective scale 20.0)
	target_modules = q_proj, k_proj, v_proj, o_proj
	layers_to_transform = last 16 of 24 (range(8, 24))
	mask_prompt = ON (assistant_masks via patched chat_template {% generation %})
	max_steps = 1100
	batch_size = 2
	max_seq_length = 384
	lr_schedule = cosine, peak 3e-5, warmup 100
	weight_decay = 0.01
	optim = adamw_torch_fused
	precision = bf16
	seed = 20260515
	trainable params = 720,896 (0.0957% of 753M)
	data = 1104 rows = V14 seeds (691) + V15 brand expansion (271) + V15 R-3 patches (142)
	```

	## Intended use

	- Russian dictation cleanup after ASR (GigaAM, Whisper, Parakeet)
	- Conservative editing policy: remove filler (эм/ну/типа/короче), normalize Cyrillic IT terms (гитхаб -> GitHub), preserve all meaning
	- NOT for general text editing, English text, creative writing, summarization, translation

	## Limitations

	- 58-row eval set has ±1.72pp single-row noise
	- Cyrillic <-> Latin choice on ambiguous brand spellings is judgment call (model may differ from expected byte-match)
	- Trained on synthetic data only; real production telemetry collection planned for V16
	-
	- INT4 NF4 has higher quality loss (-12pp) than AWQ would; AWQ blocked on Win-Py3.13-cu128 (no source build without nvcc)

	## Hardware ship matrix

	\| Hardware \| Recommended ship-form \| This model? \|
	\|---\|---\|---:\|
	\| RTX 5090 / 4090 24GB+ \| bf16 \| \|
	\| RTX 4070 / 4060 / 3060 8-16GB \| INT8 \| \|
	\| RTX 2060 / 3050 / 4060 6-8GB \| INT4 NF4 \| PRIMARY \|
	\| Re-training / stacking \| adapter \| \|

	## Inference

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	import torch

	model = AutoModelForCausalLM.from_pretrained(
	"VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4",
	load_in_4bit=True,
	device_map="cuda",
	trust_remote_code=True,
	)
	tokenizer = AutoTokenizer.from_pretrained("VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4", trust_remote_code=True)

	messages = [
	{"role": "system", "content": "Корректор русской диктовки. Убери слова-паразиты ..."},
	{"role": "user", "content": "Запушил коммит в гитхаб репозиторий"},
	]
	prompt = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=False,
	enable_thinking=False, # CRITICAL for Qwen3.5
	)
	inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
	out = model.generate(**inputs, max_new_tokens=200, do_sample=False)
	print(tokenizer.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
	# Expected: "Запушил коммит в GitHub репозиторий"
	```

	## Cross-platform variants

	- macOS MLX: `VoiceScribe/qwen3-5-0.8b-dictation-corrector-mlx-{bf16,8bit,4bit}` (V15 R-3, 93.1% wild)
	- CUDA bf16/INT8/INT4-NF4: this family (V15 R-3 Win port, 84.48-96.55% wild)
	- OpenVINO: planned (separate venv for export; tracker WP#920)
	- TensorRT-RTX W4A16: deferred (DeltaNet ONNX export blocked on Win-Py3.13-cu128 in 2026-05)

	## Citation

	```bibtex
	@software{voicescribe-corrector-v15r3-2026,
	title = {Voice Scribe Russian Dictation Corrector (Qwen3.5-0.8B V15 R-3, CUDA Win port)},
	author = {Sabynin, Andrey},
	year = {2026},
	url = {https://huggingface.co/VoiceScribe/qwen3-5-0.8b-dictation-corrector-cuda-int4-nf4}
	}
	```

	## Trackers

	- macOS R&D: OpenProject WP#917 (V14), WP#919 (V15 R-3 macOS)
	- Windows port: OpenProject WP#920 (this effort, achieved 96.55% vs macOS 93.1%)