Xenova HF Staff commited on Jul 27, 2023

Commit

c0632e8

1 Parent(s): 4cd0720

Upload folder using huggingface_hub

Browse files

Files changed (18) hide show

.gitattributes +3 -0
Constant_24_attr__value +3 -0
Constant_37_attr__value +3 -0
config.json +38 -0
generation_config.json +6 -0
merges.txt +0 -0
onnx/decoder_model.onnx +3 -0
onnx/decoder_model_merged.onnx +3 -0
onnx/decoder_model_merged.onnx_data +3 -0
onnx/decoder_model_merged_quantized.onnx +3 -0
onnx/decoder_model_quantized.onnx +3 -0
onnx/decoder_with_past_model.onnx +3 -0
onnx/decoder_with_past_model_quantized.onnx +3 -0
quantize_config.json +100 -0
special_tokens_map.json +26 -0
tokenizer.json +0 -0
tokenizer_config.json +31 -0
vocab.json +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,6 @@ 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

 *.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_24_attr__value filter=lfs diff=lfs merge=lfs -text
+Constant_37_attr__value filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text

Constant_24_attr__value ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c3725270cd155782baaa80a9cd636ac8a683d414c53f4722790e24e1ae317dbd
+size 67108864

Constant_37_attr__value ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c3725270cd155782baaa80a9cd636ac8a683d414c53f4722790e24e1ae317dbd
+size 67108864

config.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+  "_name_or_path": "bigcode/starcoderbase-1b",
+  "activation_function": "gelu_pytorch_tanh",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "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": "4.32.0.dev0",
+  "use_cache": true,
+  "validate_runner_input": true,
+  "vocab_size": 49152
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.32.0.dev0"
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

onnx/decoder_model.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dfbe51938a454fb7493cedfc43afbd0046cfe7c722db9216093cc0a3b6e64e82
+size 67546738

onnx/decoder_model_merged.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:70156b0fa12ab9a88b3d8c6c84e68a04f2daaf3809384b71da40b482ee57d05b
+size 135080712

onnx/decoder_model_merged.onnx_data ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6769e4ec8861f12edc9919154f528bf52bdc9be056d268e643efcc87c841228c
+size 4951482368

onnx/decoder_model_merged_quantized.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3d824f8f3448d776ec974775ff68ded9a73b05b26eb3b422c0cbeaa67e1b021d
+size 1377075517

onnx/decoder_model_quantized.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fe76860084f806c05370701a347431f18df17ab49eb67a0a14b42d9a7d6c04b3
+size 1309295033

onnx/decoder_with_past_model.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b9eed4ca2a3763d01f96b6fad2188cf4c8780a919bf1274aabea3faab690f276
+size 67558417

onnx/decoder_with_past_model_quantized.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:84d5609cfbf1787adfa3da0f1910ca833519822ba6b75ee28c3e88193e12d148
+size 1309305555

quantize_config.json ADDED Viewed

	@@ -0,0 +1,100 @@

+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "decoder_with_past_model": {
+            "op_types": [
+                "Gather",
+                "Squeeze",
+                "Mul",
+                "Cast",
+                "Sub",
+                "Constant",
+                "Unsqueeze",
+                "Tanh",
+                "Add",
+                "Softmax",
+                "Sqrt",
+                "Where",
+                "MatMul",
+                "Shape",
+                "Slice",
+                "Concat",
+                "Div",
+                "Pow",
+                "And",
+                "Equal",
+                "Split",
+                "Transpose",
+                "ConstantOfShape",
+                "Reshape",
+                "CumSum",
+                "ReduceMean"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model": {
+            "op_types": [
+                "Gather",
+                "Squeeze",
+                "Mul",
+                "Cast",
+                "Sub",
+                "Constant",
+                "Unsqueeze",
+                "Tanh",
+                "Add",
+                "Softmax",
+                "Sqrt",
+                "Where",
+                "MatMul",
+                "Shape",
+                "Slice",
+                "Concat",
+                "Div",
+                "Pow",
+                "And",
+                "Equal",
+                "Split",
+                "Transpose",
+                "ConstantOfShape",
+                "Reshape",
+                "CumSum",
+                "ReduceMean"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Gather",
+                "Squeeze",
+                "Mul",
+                "Cast",
+                "Sub",
+                "If",
+                "Constant",
+                "Unsqueeze",
+                "Tanh",
+                "Add",
+                "Softmax",
+                "Sqrt",
+                "Where",
+                "MatMul",
+                "Shape",
+                "Slice",
+                "Concat",
+                "Div",
+                "Pow",
+                "And",
+                "Equal",
+                "Split",
+                "Transpose",
+                "ConstantOfShape",
+                "Reshape",
+                "CumSum",
+                "ReduceMean"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff