Instructions to use codefuse-ai/F2LLM-v2-330M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codefuse-ai/F2LLM-v2-330M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="codefuse-ai/F2LLM-v2-330M")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("codefuse-ai/F2LLM-v2-330M") model = AutoModel.from_pretrained("codefuse-ai/F2LLM-v2-330M") - sentence-transformers
How to use codefuse-ai/F2LLM-v2-330M with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("codefuse-ai/F2LLM-v2-330M") 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] - Inference
- Notebooks
- Google Colab
- Kaggle
Commit ·
e8ef9a8
1
Parent(s): 33d1c82
Truncate layer_types to match num_hidden_layers (#1)
Browse files- Truncate layer_types to match num_hidden_layers (ac0ca53079b40a3c156fb999ed823700c54f8d89)
Co-authored-by: Alexander Miller <alex-miller-gov@users.noreply.huggingface.co>
- config.json +0 -12
config.json
CHANGED
|
@@ -28,18 +28,6 @@
|
|
| 28 |
"full_attention",
|
| 29 |
"full_attention",
|
| 30 |
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
"full_attention"
|
| 44 |
],
|
| 45 |
"max_position_embeddings": 40960,
|
|
|
|
| 28 |
"full_attention",
|
| 29 |
"full_attention",
|
| 30 |
"full_attention",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
"full_attention"
|
| 32 |
],
|
| 33 |
"max_position_embeddings": 40960,
|