Update readme and config

README.md

@@ -4,8 +4,8 @@ pipeline_tag: feature-extraction
 tags:
 - feature-extraction
 - sentence-similarity
-- mteb
-- sentence-transformers
+- conteb
+- contextual-embeddings
 language:
   - multilingual
 ---
@@ -39,27 +39,6 @@ language:
 
 ## Usage
 
-<details>
-<summary>Via API (Standard Embeddings)</summary>
-
-```bash
-curl -X POST https://api.perplexity.ai/v1/embeddings \
-  -H "Authorization: Bearer YOUR_API_KEY" \
-  -H "Content-Type: application/json" \
-  -d '{
-    "texts": [
-      "Scientists explore the universe driven by curiosity.",
-      "Children learn through curious exploration.",
-      "Historical discoveries began with curious questions.",
-      "Animals use curiosity to adapt and survive.",
-      "Philosophy examines the nature of curiosity.",
-    ],
-    "model": "pplx-embed-1-4B"
-  }'
-```
-
-</details>
-
 <details>
 <summary>Via API (Contextualized Embeddings)</summary>
 
@@ -91,66 +70,8 @@ curl -X POST https://api.perplexity.ai/v1/contextualizedembeddings \
 ```python
 from transformers import AutoModel
 
-model = AutoModel.from_pretrained(
-    "perplexity-ai/pplx-embed-1-0.6B",
-    trust_remote_code=True
-)
-texts = [
-    "Scientists explore the universe driven by curiosity.",
-    "Children learn through curious exploration.",
-    "Historical discoveries began with curious questions.",
-    "Animals use curiosity to adapt and survive.",
-    "Philosophy examines the nature of curiosity.",
-]
-
-embeddings = model.encode(texts) # Shape: (5, 1024)
-
 model_ctx = AutoModel.from_pretrained(
-    "perplexity-ai/pplx-embed-1-context-0.6B",
-    trust_remote_code=True
-)
-
-doc_chunks = [
-    [
-        "Curiosity begins in childhood with endless questions about the world.",
-        "As we grow, curiosity drives us to explore new ideas.",
-        "Scientific breakthroughs often start with a curious question."
-    ],
-    [
-        "The curiosity rover explores Mars searching for ancient life.",
-        "Each discovery on Mars sparks new questions about the universe."
-    ]
-]
-# Returns list of numpy arrays (one per document)
-# embeddings[0].shape = (3, 1024), embeddings[1].shape = (2, 1024)
-embeddings = model_ctx.encode(doc_chunks)
-```
-
-</details>
-
-<details>
-<summary>Using SentenceTransformers</summary>
-
-```python
-from sentence_transformers import SentenceTransformer
-
-model = SentenceTransformer(
-    "perplexity-ai/pplx-embed-1-0.6B",
-    trust_remote_code=True
-)
-
-texts = [
-    "Scientists explore the universe driven by curiosity.",
-    "Children learn through curious exploration.",
-    "Historical discoveries began with curious questions.",
-    "Animals use curiosity to adapt and survive.",
-    "Philosophy examines the nature of curiosity.",
-]
-
-embeddings = model.encode(texts) # Shape: (5, 1024)
-
-model_ctx = SentenceTransformer(
-    "perplexity-ai/pplx-embed-1-context-0.6B",
+    "perplexity-ai/pplx-embed-1-context-4B",
     trust_remote_code=True
 )
 
@@ -172,8 +93,6 @@ embeddings = model_ctx.encode(doc_chunks)
 
 </details>
 
-</details>
-
 ## Technical Details
 
 For comprehensive technical details and evaluation results, see our paper on arXiv.

config.json

@@ -72,5 +72,6 @@
   "use_cache": false,
   "use_sliding_window": false,
   "attn_implementation": "sdpa",
-  "vocab_size": 151936
+  "vocab_size": 151936,
+  "use_bidirectional_attention": true
 }