Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Constant_2300_attr__value filter=lfs diff=lfs merge=lfs -text
+Constant_2308_attr__value filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text

Constant_2300_attr__value

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d39d994a9f095ab7915db8b999513fda639b1c4c89d08dcd171269b9b8e7d15
+size 2097152

Constant_2308_attr__value

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a41b28fb845ff407014dea375801076b467e204937facf71c3803425ee087b9
+size 2097152

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|end_header_id|>": 32001,
+  "<|eot_id|>": 32002,
+  "<|start_header_id|>": 32000,
+  "[PAD]": 32003
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "premai-io/prem-1B-chat",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 32004
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.33.2"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d27432fc9919d0607f17a87840b231e7c81a8401c33a09962d3fe66416b0287
+size 5254393

onnx/decoder_model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea4bca99d48021a1811539418bcaef2a193461e7cdac61fbc385f69ffe6e49b
+size 13199695872

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c178baa59144e6e1ec46001138a81af9650ff1f7bb73d0ee2d9c953956bb530a
+size 1105728582

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9171b098983a8325152c9ed849be8fdab80fe7c406cb8ed6a980669b076a850d
+size 1016507

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1ca70217cbd70e63fe2ae8272fc7fb91d88ec261c87a6fed83c03c083a2a08
+size 4399898624

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc79f6ca338c88986b6ade19871087cfdd531c80448b959e9001762a43a3809
+size 1101480490

quantize_config.json

@@ -0,0 +1,75 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "decoder_model": {
+            "op_types": [
+                "ConstantOfShape",
+                "Mul",
+                "Transpose",
+                "Expand",
+                "Shape",
+                "Reshape",
+                "Slice",
+                "Cast",
+                "Neg",
+                "Concat",
+                "Unsqueeze",
+                "MatMul",
+                "Div",
+                "Constant",
+                "Gather",
+                "Less",
+                "Sqrt",
+                "Equal",
+                "Sub",
+                "Range",
+                "Sigmoid",
+                "Softmax",
+                "Pow",
+                "Add",
+                "Squeeze",
+                "ReduceMean",
+                "Where",
+                "Identity"
+            ],
+            "weight_type": "QInt8"
+        },
+        "model": {
+            "op_types": [
+                "ConstantOfShape",
+                "Mul",
+                "Transpose",
+                "Greater",
+                "ScatterND",
+                "Expand",
+                "Shape",
+                "Reshape",
+                "Slice",
+                "Cast",
+                "Neg",
+                "Concat",
+                "Unsqueeze",
+                "MatMul",
+                "Div",
+                "Constant",
+                "Cos",
+                "Gather",
+                "Sqrt",
+                "Trilu",
+                "And",
+                "Equal",
+                "Range",
+                "Sigmoid",
+                "Sin",
+                "Softmax",
+                "Pow",
+                "Add",
+                "ReduceMean",
+                "Where",
+                "Identity"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<|start_header_id|>",
+    "<|end_header_id|>",
+    "<|eot_id|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,77 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_header_id|>",
+    "<|end_header_id|>",
+    "<|eot_id|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}