Translation
PEFT
Safetensors
Zulu
English
african-languages
scientific-translation
afriscience-mt
lora
causal-lm
Eval Results (legacy)
Instructions to use dsfsi/tiny_aya_global-lora-r64-zul-eng with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dsfsi/tiny_aya_global-lora-r64-zul-eng with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-global") model = PeftModel.from_pretrained(base_model, "dsfsi/tiny_aya_global-lora-r64-zul-eng") - Notebooks
- Google Colab
- Kaggle
Update example model/adapter paths to dsfsi namespace
Browse files
README.md
CHANGED
|
@@ -30,7 +30,7 @@ model-index:
|
|
| 30 |
|
| 31 |
# tiny_aya_global-lora-r64-zul-eng
|
| 32 |
|
| 33 |
-
[](https://huggingface.co/
|
| 34 |
|
| 35 |
This is a **LoRA adapter** for the AfriScience-MT project, enabling efficient scientific machine translation for African languages.
|
| 36 |
|
|
@@ -89,7 +89,7 @@ base_model = AutoModelForCausalLM.from_pretrained(
|
|
| 89 |
tokenizer = AutoTokenizer.from_pretrained("CohereLabs/tiny-aya-global")
|
| 90 |
|
| 91 |
# Load LoRA adapter
|
| 92 |
-
adapter_name = "
|
| 93 |
model = PeftModel.from_pretrained(base_model, adapter_name)
|
| 94 |
model.eval()
|
| 95 |
|
|
@@ -133,7 +133,7 @@ base_model = AutoModelForCausalLM.from_pretrained(
|
|
| 133 |
device_map="auto",
|
| 134 |
torch_dtype=torch.bfloat16,
|
| 135 |
)
|
| 136 |
-
model = PeftModel.from_pretrained(base_model, "
|
| 137 |
```
|
| 138 |
|
| 139 |
## Training Details
|
|
|
|
| 30 |
|
| 31 |
# tiny_aya_global-lora-r64-zul-eng
|
| 32 |
|
| 33 |
+
[](https://huggingface.co/dsfsi/tiny_aya_global-lora-r64-zul-eng)
|
| 34 |
|
| 35 |
This is a **LoRA adapter** for the AfriScience-MT project, enabling efficient scientific machine translation for African languages.
|
| 36 |
|
|
|
|
| 89 |
tokenizer = AutoTokenizer.from_pretrained("CohereLabs/tiny-aya-global")
|
| 90 |
|
| 91 |
# Load LoRA adapter
|
| 92 |
+
adapter_name = "dsfsi/tiny_aya_global-lora-r64-zul-eng"
|
| 93 |
model = PeftModel.from_pretrained(base_model, adapter_name)
|
| 94 |
model.eval()
|
| 95 |
|
|
|
|
| 133 |
device_map="auto",
|
| 134 |
torch_dtype=torch.bfloat16,
|
| 135 |
)
|
| 136 |
+
model = PeftModel.from_pretrained(base_model, "dsfsi/tiny_aya_global-lora-r64-zul-eng")
|
| 137 |
```
|
| 138 |
|
| 139 |
## Training Details
|