Feature Extraction
sentence-transformers
Safetensors
Transformers
qwen3
text-generation
splade
sparse-encoder
code
custom_code
text-embeddings-inference
Instructions to use naver/splade-code-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use naver/splade-code-8B with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("naver/splade-code-8B", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Transformers
How to use naver/splade-code-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="naver/splade-code-8B", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("naver/splade-code-8B", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("naver/splade-code-8B", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
Update splade.py
Browse files
splade.py
CHANGED
|
@@ -72,10 +72,16 @@ class Splade(PreTrainedModel):
|
|
| 72 |
def from_pretrained(cls, model_name_or_path, *args, **kwargs):
|
| 73 |
config = SpladeConfig.from_pretrained(model_name_or_path)
|
| 74 |
model = cls(config)
|
| 75 |
-
local_dir = snapshot_download(model_name_or_path)
|
| 76 |
-
adapter_path = os.path.join(local_dir, "lora")
|
| 77 |
# model.model.load_adapter(adapter_path)
|
| 78 |
-
model.model = PeftModel.from_pretrained(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
model.reverse_voc = {v: k for k, v in model.tokenizer.vocab.items()}
|
| 80 |
return model
|
| 81 |
|
|
|
|
| 72 |
def from_pretrained(cls, model_name_or_path, *args, **kwargs):
|
| 73 |
config = SpladeConfig.from_pretrained(model_name_or_path)
|
| 74 |
model = cls(config)
|
| 75 |
+
# local_dir = snapshot_download(model_name_or_path)
|
| 76 |
+
# adapter_path = os.path.join(local_dir, "lora")
|
| 77 |
# model.model.load_adapter(adapter_path)
|
| 78 |
+
model.model = PeftModel.from_pretrained(
|
| 79 |
+
model.model,
|
| 80 |
+
model_name_or_path,
|
| 81 |
+
subfolder="lora",
|
| 82 |
+
token=kwargs.get("token", None),
|
| 83 |
+
)
|
| 84 |
+
# model.model = PeftModel.from_pretrained(model.model, adapter_path)
|
| 85 |
model.reverse_voc = {v: k for k, v in model.tokenizer.vocab.items()}
|
| 86 |
return model
|
| 87 |
|