Upload folder using huggingface_hub

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "nomic-ai/nomic-embed-text-v1",
+  "activation_function": "swiglu",
+  "architectures": [
+    "NomicBertModel"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "nomic-ai/nomic-embed-text-v1--configuration_hf_nomic_bert.NomicBertConfig",
+    "AutoModel": "nomic-ai/nomic-embed-text-v1--modeling_hf_nomic_bert.NomicBertModel",
+    "AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining"
+  },
+  "bos_token_id": null,
+  "causal": false,
+  "dense_seq_output": true,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "fused_bias_fc": true,
+  "fused_dropout_add_ln": true,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-12,
+  "mlp_fc1_bias": false,
+  "mlp_fc2_bias": false,
+  "model_type": "nomic_bert",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 8192,
+  "pad_vocab_size_multiple": 64,
+  "parallel_block": false,
+  "parallel_block_tied_norm": false,
+  "prenorm": false,
+  "qkv_proj_bias": false,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "rotary_emb_base": 1000,
+  "rotary_emb_fraction": 1.0,
+  "rotary_emb_interleaved": false,
+  "rotary_emb_scale_base": null,
+  "rotary_scaling_factor": null,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.0,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "use_flash_attn": true,
+  "use_rms_norm": false,
+  "use_xentropy": true,
+  "vocab_size": 30528
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347440e93b5ec979fdcf6041b72721aade7b9680c16022e2830db7115ff6fd9f
+size 547552426

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7941066a6529a287e2502ea6cb68ff82006d311eac53627dc88c259cbcbda64
+size 138355983

quantize_config.json

@@ -0,0 +1,39 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Transpose",
+                "ReduceMean",
+                "Sigmoid",
+                "Sub",
+                "Add",
+                "Where",
+                "Gather",
+                "Div",
+                "Unsqueeze",
+                "ConstantOfShape",
+                "Mul",
+                "Pow",
+                "Neg",
+                "Sqrt",
+                "Softmax",
+                "Reshape",
+                "Slice",
+                "Equal",
+                "Constant",
+                "MatMul",
+                "Einsum",
+                "Sin",
+                "Cos",
+                "Concat",
+                "Range",
+                "Cast",
+                "Expand",
+                "Shape"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}