Upload folder using huggingface_hub

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "GerbilLab/Gerbil-A-32m",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_embd": 256,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 8,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 16,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 50400
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.35.2"
+}

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22672ebb312d2642dcd700d99dab373f22f3e25bef3243fcb50294d6a55fd5cd
+size 133242501

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17702e9108f66c406dc40a1f407dd0c079ddd33d56d6a073a7c5c644cc00ef2
+size 37098803

quantize_config.json

@@ -0,0 +1,38 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Concat",
+                "Neg",
+                "Expand",
+                "Slice",
+                "Softmax",
+                "Cast",
+                "Where",
+                "Reshape",
+                "Div",
+                "Mul",
+                "GatherElements",
+                "Add",
+                "Pow",
+                "Tanh",
+                "Shape",
+                "Split",
+                "Constant",
+                "ConstantOfShape",
+                "ReduceMean",
+                "Squeeze",
+                "Sqrt",
+                "Tile",
+                "Unsqueeze",
+                "Transpose",
+                "Sub",
+                "MatMul",
+                "Gather"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "max_length": 1024,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}