Sentence Similarity
sentence-transformers
PyTorch
bloom
feature-extraction
mteb
Eval Results (legacy)
Instructions to use bigscience/sgpt-bloom-7b1-msmarco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use bigscience/sgpt-bloom-7b1-msmarco with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("bigscience/sgpt-bloom-7b1-msmarco") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Fix architecture
#1
by lewtun HF Staff - opened
- config.json +2 -2
config.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"_name_or_path": "/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3/bloom-7b1",
|
| 3 |
"apply_residual_connection_post_layernorm": false,
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"attention_softmax_in_fp32": true,
|
|
@@ -30,4 +30,4 @@
|
|
| 30 |
"unk_token_id": 0,
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 250682
|
| 33 |
-
}
|
|
|
|
| 2 |
"_name_or_path": "/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3/bloom-7b1",
|
| 3 |
"apply_residual_connection_post_layernorm": false,
|
| 4 |
"architectures": [
|
| 5 |
+
"BloomForCausalLM"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"attention_softmax_in_fp32": true,
|
|
|
|
| 30 |
"unk_token_id": 0,
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 250682
|
| 33 |
+
}
|