Translation
Transformers
Safetensors
hunyuan_v1_dense
text-generation
noesis
noesis-dub-lm
dhcf-fno
amaimedia
sft
qlora
bf16
hunyuan
hy-mt2
tencent
dub-lm
live-voice-translate
Instructions to use AMAImedia/NOESIS-Hy-MT2-7.5B-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AMAImedia/NOESIS-Hy-MT2-7.5B-BF16 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="AMAImedia/NOESIS-Hy-MT2-7.5B-BF16")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AMAImedia/NOESIS-Hy-MT2-7.5B-BF16") model = AutoModelForCausalLM.from_pretrained("AMAImedia/NOESIS-Hy-MT2-7.5B-BF16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
docs: model card last updated 2026-08-29
Browse files
README.md
CHANGED
|
@@ -79,7 +79,7 @@ Released as part of the NOESIS Professional Multilingual Dubbing Automation Plat
|
|
| 79 |
> framework: DHCF-FNO — *Deterministic Hybrid Control Framework for Frozen Neural Operators*
|
| 80 |
>
|
| 81 |
> - **Trained:** 2026-06-05/06
|
| 82 |
-
> - **Last updated:** 2026-
|
| 83 |
|
| 84 |
> ⚠️ **License regime — Tencent HY Community License Agreement.** Three license gates apply: (1) Territory — EU excluded; (2) 100M MAU cap (separate Tencent license required above); (3) No-KD: outputs cannot be used to train other AI models. Full text in `LICENSE.md`.
|
| 85 |
|
|
|
|
| 79 |
> framework: DHCF-FNO — *Deterministic Hybrid Control Framework for Frozen Neural Operators*
|
| 80 |
>
|
| 81 |
> - **Trained:** 2026-06-05/06
|
| 82 |
+
> - **Last updated:** 2026-08-29
|
| 83 |
|
| 84 |
> ⚠️ **License regime — Tencent HY Community License Agreement.** Three license gates apply: (1) Territory — EU excluded; (2) 100M MAU cap (separate Tencent license required above); (3) No-KD: outputs cannot be used to train other AI models. Full text in `LICENSE.md`.
|
| 85 |
|