Add model files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "SebastianSchramm/Cerebras-GPT-111M-instruction",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "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": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 10,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 50258
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.33.2"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93d8227f7912835cc750f2ef046db5782530865ba159ae62bbaba2ef73581fb
+size 448782103

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1cb546b354e6f524449b84eaa3bfc39d5d611f4c2fbcb3b1c78ecd159fa775
+size 453364666

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946c69dd37b7053134826732c5a16d922bd10e113dcc585a1ada554a784ba74c
+size 120903378

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e51fdebcfb9f841e2562b35898aee9c8818114093a532cb8cf03df18529cfefb
+size 116126827

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f84b6b3a5a73421f07f9e1f3e1426ffd8d7287f13cfab05f3a8f747fb0b1e1
+size 448787916

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8bcce00862035486399b8863725ad92e32cc63a80a5c08cd6badb77cb92ab1
+size 116134566

quantize_config.json

@@ -0,0 +1,97 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "decoder_with_past_model": {
+            "op_types": [
+                "Slice",
+                "ReduceMean",
+                "Constant",
+                "Sqrt",
+                "Sub",
+                "Reshape",
+                "Mul",
+                "Concat",
+                "Shape",
+                "Squeeze",
+                "Pow",
+                "Softmax",
+                "Add",
+                "Split",
+                "Cast",
+                "Gather",
+                "MatMul",
+                "Div",
+                "Erf",
+                "Unsqueeze",
+                "Gemm",
+                "Range",
+                "ConstantOfShape",
+                "Where",
+                "Transpose"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model": {
+            "op_types": [
+                "Slice",
+                "ReduceMean",
+                "Constant",
+                "Sqrt",
+                "Sub",
+                "Reshape",
+                "Mul",
+                "Concat",
+                "Shape",
+                "Squeeze",
+                "Pow",
+                "Softmax",
+                "Add",
+                "Split",
+                "Cast",
+                "Gather",
+                "MatMul",
+                "Div",
+                "Erf",
+                "Unsqueeze",
+                "Gemm",
+                "Range",
+                "ConstantOfShape",
+                "Where",
+                "Transpose"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Slice",
+                "ReduceMean",
+                "Constant",
+                "Sqrt",
+                "Sub",
+                "Reshape",
+                "Mul",
+                "Concat",
+                "Shape",
+                "Squeeze",
+                "Pow",
+                "Softmax",
+                "Add",
+                "Split",
+                "Cast",
+                "Gather",
+                "MatMul",
+                "Div",
+                "Erf",
+                "Unsqueeze",
+                "Gemm",
+                "Range",
+                "ConstantOfShape",
+                "If",
+                "Where",
+                "Transpose"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}