Upload Zen3 Embedding Small weights

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -1,21 +1,55 @@
 ---
 library_name: transformers
-tags: [zen, embedding, rag, hanzo]
+pipeline_tag: feature-extraction
+tags:
+  - embedding
+  - retrieval
+  - sentence-similarity
+  - zen
+  - zen3
+  - hanzo
 license: apache-2.0
 ---
+
 # Zen3 Embedding Small
 
-Lightweight embedding model for high-throughput, low-cost applications.
+**Zen LM by Hanzo AI** — Compact text embedding model optimized for retrieval and similarity tasks. 33M parameters, 384-dim embeddings.
+
+## Specs
 
-- **Developer**: [Hanzo AI](https://hanzo.ai) × [Zen LM](https://zenlm.org)
-- **Parameters**: 0.6B
-- **Context**: 32K tokens
-- **Endpoint**: `/v1/embeddings`
-- **API**: [api.hanzo.ai](https://cloud.hanzo.ai)
+| Property | Value |
+|----------|-------|
+| Parameters | 33M |
+| Context Length | 512 tokens |
+| Dimensions | 384 |
+| Architecture | Zen MoDE (Mixture of Distilled Experts) |
+| Generation | Zen3 |
 
 ## Usage
+
 ```python
-from hanzo import Hanzo
-client = Hanzo()
-response = client.embeddings.create(model="zen3-embedding-small", input="Your text here")
+from transformers import AutoModel, AutoTokenizer
+
+model = AutoModel.from_pretrained("zenlm/zen3-embedding-small")
+tokenizer = AutoTokenizer.from_pretrained("zenlm/zen3-embedding-small")
+```
+
+## API Access
+
+Available via the Hanzo AI API:
+
+```bash
+curl https://api.hanzo.ai/v1/embeddings \
+  -H "Authorization: Bearer $HANZO_API_KEY" \
+  -d '{"model": "zen3-embedding-small", "input": "Your text here"}'
 ```
+
+Get your API key at [console.hanzo.ai](https://console.hanzo.ai) — $5 free credit on signup.
+
+## License
+
+Apache 2.0
+
+---
+
+*Zen LM is developed by [Hanzo AI](https://hanzo.ai) — Frontier AI infrastructure.*

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/BAAI_bge-small-en/",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.28.1",
+    "pytorch": "1.13.0+cu117"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c9f31665447c8911517620762200d2245a2518d6e7208acc78cd9db317e21ad
+size 133466304

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84868a67d847f7f37d1df745b73a4c20b5bc0a797c87a23b265f8a0131728b88
+size 133508397

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}