Upload folder using huggingface_hub

.gitattributes

@@ -39,3 +39,5 @@ rknn/model_o1.rknn filter=lfs diff=lfs merge=lfs -text
 rknn/model_o2.rknn filter=lfs diff=lfs merge=lfs -text
 rknn/model_o3.rknn filter=lfs diff=lfs merge=lfs -text
 rknn/model_w8a8.rknn filter=lfs diff=lfs merge=lfs -text
+model_b1_s256.rknn filter=lfs diff=lfs merge=lfs -text
+model_b4_s256.rknn filter=lfs diff=lfs merge=lfs -text

README.md

@@ -13,8 +13,8 @@ tags:
 - rk-transformers
 - rk3588
 pipeline_tag: sentence-similarity
-base_model: sentence-transformers/all-MiniLM-L6-v2
 model_name: all-MiniLM-L6-v2
+base_model: sentence-transformers/all-MiniLM-L6-v2
 ---
 # all-MiniLM-L6-v2 (RKNN2)
 
@@ -34,6 +34,8 @@ model_name: all-MiniLM-L6-v2
 | Model File | Optimization Level | Quantization | File Size |
 | :--------- | :----------------- | :----------- | :-------- |
 | [model.rknn](./model.rknn) | 0 | float16 | 45.7 MB |
+| [model_b1_s256.rknn](./model_b1_s256.rknn) | 0 | float16 | 44.7 MB |
+| [model_b4_s256.rknn](./model_b4_s256.rknn) | 0 | float16 | 48.9 MB |
 | [model_b4_s512.rknn](./model_b4_s512.rknn) | 0 | float16 | 52.5 MB |
 | [rknn/model_o1.rknn](./rknn/model_o1.rknn) | 1 | float16 | 45.7 MB |
 | [rknn/model_o2.rknn](./rknn/model_o2.rknn) | 2 | float16 | 45.7 MB |
@@ -102,7 +104,7 @@ model = RKRTModelForFeatureExtraction.from_pretrained(
 inputs = tokenizer(
     ["Sample text for encoding"],
     padding="max_length",
-    max_length=512,
+    max_length=256,
     truncation=True,
     return_tensors="np"
 )

model_b1_s256.rknn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14315427c644d669134f3620ba1efe97dc6972bb28c53340e7363bf2e08bfc6b
+size 46920212

model_b4_s256.rknn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eae8ea4b3dd8bd2332da540b52a0f8707cf5f890fc31bd91d221ca1d85de64c
+size 51320404

rknn.json

@@ -254,5 +254,89 @@
             "sparse_infer": false,
             "model_pruning": false
         }
+    },
+    "model_b1_s256.rknn": {
+        "model_input_names": [
+            "input_ids",
+            "attention_mask"
+        ],
+        "batch_size": 1,
+        "max_seq_length": 256,
+        "float_dtype": "float16",
+        "target_platform": "rk3588",
+        "single_core_mode": false,
+        "mean_values": null,
+        "std_values": null,
+        "custom_string": null,
+        "inputs_yuv_fmt": null,
+        "dynamic_input": null,
+        "opset": 18,
+        "task": "auto",
+        "quantization": {
+            "do_quantization": false,
+            "dataset_name": null,
+            "dataset_subset": null,
+            "dataset_size": 128,
+            "dataset_split": null,
+            "dataset_columns": null,
+            "quantized_dtype": "w8a8",
+            "quantized_algorithm": "normal",
+            "quantized_method": "channel",
+            "quantized_hybrid_level": 0,
+            "quant_img_RGB2BGR": false,
+            "auto_hybrid_cos_thresh": 0.98,
+            "auto_hybrid_euc_thresh": null
+        },
+        "optimization": {
+            "optimization_level": 0,
+            "enable_flash_attention": true,
+            "remove_weight": false,
+            "compress_weight": false,
+            "remove_reshape": false,
+            "sparse_infer": false,
+            "model_pruning": false
+        }
+    },
+    "model_b4_s256.rknn": {
+        "model_input_names": [
+            "input_ids",
+            "attention_mask"
+        ],
+        "batch_size": 4,
+        "max_seq_length": 256,
+        "float_dtype": "float16",
+        "target_platform": "rk3588",
+        "single_core_mode": false,
+        "mean_values": null,
+        "std_values": null,
+        "custom_string": null,
+        "inputs_yuv_fmt": null,
+        "dynamic_input": null,
+        "opset": 18,
+        "task": "auto",
+        "quantization": {
+            "do_quantization": false,
+            "dataset_name": null,
+            "dataset_subset": null,
+            "dataset_size": 128,
+            "dataset_split": null,
+            "dataset_columns": null,
+            "quantized_dtype": "w8a8",
+            "quantized_algorithm": "normal",
+            "quantized_method": "channel",
+            "quantized_hybrid_level": 0,
+            "quant_img_RGB2BGR": false,
+            "auto_hybrid_cos_thresh": 0.98,
+            "auto_hybrid_euc_thresh": null
+        },
+        "optimization": {
+            "optimization_level": 0,
+            "enable_flash_attention": true,
+            "remove_weight": false,
+            "compress_weight": false,
+            "remove_reshape": false,
+            "sparse_infer": false,
+            "model_pruning": false
+        }
     }
 }