Add model files

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Felladrin/llama2_xs_460M_experimental_evol_instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layernorm_epsilon": 1e-05,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20aa29bd6418d1448f3647974ce2bbba1ad65e83d86c6dcf2b43237c6432ee3
+size 1848291159

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9755c31afabf7c7f52c6b59a5abcaab731f7b180f9a1a2e7d85479f80effff7a
+size 463928831

quantize_config.json

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

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "#",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "\"",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "\"",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "#",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "#",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "\"",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}