Instructions to use codefuse-ai/F2LLM-v2-80M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codefuse-ai/F2LLM-v2-80M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="codefuse-ai/F2LLM-v2-80M")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("codefuse-ai/F2LLM-v2-80M") model = AutoModel.from_pretrained("codefuse-ai/F2LLM-v2-80M") - sentence-transformers
How to use codefuse-ai/F2LLM-v2-80M with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("codefuse-ai/F2LLM-v2-80M") 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] - Notebooks
- Google Colab
- Kaggle
Truncate layer_types to match num_hidden_layers
Browse filesTruncating layer_types list to length 8, to match num_hidden_layers for this model, per my discussion here: https://huggingface.co/codefuse-ai/F2LLM-v2-80M/discussions/1
- config.json +0 -20
config.json
CHANGED
|
@@ -13,26 +13,6 @@
|
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 2048,
|
| 15 |
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 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",
|
|
|
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 2048,
|
| 15 |
"layer_types": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"full_attention",
|
| 17 |
"full_attention",
|
| 18 |
"full_attention",
|