Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/gemma-7b-it",
+  "_name_or_path": "Xenova/tiny-random-GemmaForCausalLM",
   "architectures": [
     "GemmaForCausalLM"
   ],
@@ -9,6 +9,7 @@
   "eos_token_id": 1,
   "head_dim": 2,
   "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 16,
@@ -21,8 +22,7 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "torch_dtype": "float32",
-  "transformers_version": "4.38.1",
+  "transformers_version": "4.42.0.dev0",
   "use_cache": true,
   "vocab_size": 256000
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 2,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.38.1"
+  "transformers_version": "4.42.0.dev0"
 }

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea87779ee6e68454bd7f3cde0c2f8fb891f9529f2f56d511982be2d92e7f5007
-size 75410798
+oid sha256:ba2690dc6dccb2393d7c1d6e456444b4fa0ee0f166dd372e0df06fab250b054f
+size 8304714

onnx/model_bnb4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bce66ef1fd853191e102bad41e1b29dbbb31ea78a5eccdf0d4bf29e0ff59bcdc
-size 75408909
+oid sha256:1ef59b214123dfc30d8a933cece7a73e585a28ea08b32b133ed93b54afd3ad67
+size 8302825

onnx/model_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d21c72a0226346ad38834d26c991dad3d1ea773971b97fc07c22c94f6932ebf
-size 71357852
+oid sha256:6bb98884b766db6f6f30c860a60b77c204eb5348b02ebb3daf1ea49786625f6b
+size 4254070

onnx/model_int8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15ccaf18b573045e6fe591f4f766c5bc0d988735972801d04414c0b25e2cd6dc
-size 69323622
+oid sha256:dec01b08412c43540eb9d96c979828c2295442946a2a6ae3ab04c0a7a2215900
+size 2219842

onnx/model_q4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b2cb87f0dfaba5874151dba68ce9dfc114da33291f65ab7ddb62e6be29154c
-size 75410735
+oid sha256:2844d53f01272ea5db79b0edd6fd50fe64d4f4d01361d16dfa859e142cc9f9df
+size 8304651

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15ccaf18b573045e6fe591f4f766c5bc0d988735972801d04414c0b25e2cd6dc
-size 69323622
+oid sha256:dec01b08412c43540eb9d96c979828c2295442946a2a6ae3ab04c0a7a2215900
+size 2219842

onnx/model_uint8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a80107bb992dcf56fd591e11204c91bac83a3c2a02d54d9da9aad7710bc3f86f
-size 69323621
+oid sha256:0a7ccd538c06cc6b615b30023b45926052696481ebfc0bc020e8d499a65f87dd
+size 2219841

quantize_config.json

@@ -0,0 +1,135 @@
+{
+    "fp16": {},
+    "q8": {
+        "per_model_config": {
+            "model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Cos",
+                    "Div",
+                    "Equal",
+                    "Expand",
+                    "Gather",
+                    "Greater",
+                    "Identity",
+                    "MatMul",
+                    "Mul",
+                    "Neg",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Reshape",
+                    "ScatterND",
+                    "Shape",
+                    "Sin",
+                    "Slice",
+                    "Softmax",
+                    "Sqrt",
+                    "Tanh",
+                    "Transpose",
+                    "Trilu",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QInt8"
+            }
+        },
+        "per_channel": true,
+        "reduce_range": true
+    },
+    "int8": {
+        "per_model_config": {
+            "model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Cos",
+                    "Div",
+                    "Equal",
+                    "Expand",
+                    "Gather",
+                    "Greater",
+                    "Identity",
+                    "MatMul",
+                    "Mul",
+                    "Neg",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Reshape",
+                    "ScatterND",
+                    "Shape",
+                    "Sin",
+                    "Slice",
+                    "Softmax",
+                    "Sqrt",
+                    "Tanh",
+                    "Transpose",
+                    "Trilu",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QInt8"
+            }
+        },
+        "per_channel": true,
+        "reduce_range": true
+    },
+    "uint8": {
+        "per_model_config": {
+            "model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Cos",
+                    "Div",
+                    "Equal",
+                    "Expand",
+                    "Gather",
+                    "Greater",
+                    "Identity",
+                    "MatMul",
+                    "Mul",
+                    "Neg",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Reshape",
+                    "ScatterND",
+                    "Shape",
+                    "Sin",
+                    "Slice",
+                    "Softmax",
+                    "Sqrt",
+                    "Tanh",
+                    "Transpose",
+                    "Trilu",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QUInt8"
+            }
+        },
+        "per_channel": true,
+        "reduce_range": true
+    },
+    "q4": {
+        "block_size": 32,
+        "is_symmetric": true,
+        "accuracy_level": null
+    },
+    "bnb4": {
+        "block_size": 64,
+        "quant_type": 1
+    }
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
-size 17477929
+oid sha256:17a91ce4908a747435938ec27fe0f811551fdc89a64222b539f8de528b7fd81b
+size 17477957