Image-Text-to-Text
Safetensors
ColPali
sentence-transformers
sauerkrautlm-colpali
collfm2
document-retrieval
vision-language-model
multi-vector
late-interaction
visual-retrieval
lfm2
small-model
efficient
curriculum-learning
hierarchical-merge
mteb
vidore
Instructions to use VAGOsolutions/SauerkrautLM-ColLFM2-450M-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ColPali
How to use VAGOsolutions/SauerkrautLM-ColLFM2-450M-v0.1 with ColPali:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- sentence-transformers
How to use VAGOsolutions/SauerkrautLM-ColLFM2-450M-v0.1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("VAGOsolutions/SauerkrautLM-ColLFM2-450M-v0.1") 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
Drop dtype and identity fields from the injected base config
Browse files
sentence_bert_config.json
CHANGED
|
@@ -38,7 +38,6 @@
|
|
| 38 |
"projector_hidden_act": "gelu",
|
| 39 |
"projector_hidden_size": 2560,
|
| 40 |
"text_config": {
|
| 41 |
-
"_name_or_path": "LiquidAI/LFM2-350M",
|
| 42 |
"architectures": [
|
| 43 |
"Lfm2ForCausalLM"
|
| 44 |
],
|
|
@@ -57,7 +56,6 @@
|
|
| 57 |
"conv_dim": 1024,
|
| 58 |
"conv_dim_out": 1024,
|
| 59 |
"conv_use_xavier_init": true,
|
| 60 |
-
"dtype": "bfloat16",
|
| 61 |
"eos_token_id": 7,
|
| 62 |
"hidden_size": 1024,
|
| 63 |
"initializer_range": 0.02,
|
|
@@ -97,7 +95,6 @@
|
|
| 97 |
"use_thumbnail": false,
|
| 98 |
"vision_config": {
|
| 99 |
"attention_dropout": 0.0,
|
| 100 |
-
"dtype": "bfloat16",
|
| 101 |
"hidden_act": "gelu_pytorch_tanh",
|
| 102 |
"hidden_size": 768,
|
| 103 |
"intermediate_size": 3072,
|
|
|
|
| 38 |
"projector_hidden_act": "gelu",
|
| 39 |
"projector_hidden_size": 2560,
|
| 40 |
"text_config": {
|
|
|
|
| 41 |
"architectures": [
|
| 42 |
"Lfm2ForCausalLM"
|
| 43 |
],
|
|
|
|
| 56 |
"conv_dim": 1024,
|
| 57 |
"conv_dim_out": 1024,
|
| 58 |
"conv_use_xavier_init": true,
|
|
|
|
| 59 |
"eos_token_id": 7,
|
| 60 |
"hidden_size": 1024,
|
| 61 |
"initializer_range": 0.02,
|
|
|
|
| 95 |
"use_thumbnail": false,
|
| 96 |
"vision_config": {
|
| 97 |
"attention_dropout": 0.0,
|
|
|
|
| 98 |
"hidden_act": "gelu_pytorch_tanh",
|
| 99 |
"hidden_size": 768,
|
| 100 |
"intermediate_size": 3072,
|