初始化项目，由ModelHub XC社区提供模型

Model: Xenova/llama2.c-stories42M
Source: Original Platform

.gitattributes

@@ -0,0 +1,68 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_fp16.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_quantized.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_quantized.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model_quantized.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/model.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/model_bnb4.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/model_fp16.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/model_int8.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4f16.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/model_quantized.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/model_uint8.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_bnb4.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_int8.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_bnb4.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_fp16.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_int8.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_q4.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_q4f16.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_uint8.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_q4.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_q4f16.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_uint8.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model_bnb4.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model_fp16.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model_int8.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model_q4.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model_q4f16.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model_uint8.onnx filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,30 @@
+---
+library_name: transformers.js
+tags: 
+- transformers
+---
+
+## Usage (Transformers.js)
+
+If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
+```bash
+npm i @huggingface/transformers
+```
+
+You can then use the model to generate text like this:
+
+```js
+import { pipeline } from "@huggingface/transformers";
+
+// Create a text-generation pipeline
+const generator = await pipeline('text-generation', 'Xenova/llama2.c-stories42M');
+
+const text = 'Once upon a time,';
+const output = await generator(text);
+console.log(output);
+// [{ generated_text: "Once upon a time, there was a little girl named Lily. She loved to play outside in" }]
+
+const output2 = await generator(text, { max_new_tokens: 50 });
+console.log(output2);
+// [{ generated_text: "Once upon a time, there was a little girl named Lily. She loved to play outside in the sunshine. One day, she saw a big, yellow flower in the garden. It was so pretty! She picked it and smelled it. It smelled" }]
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "Xenova/llama2.c-stories42M",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1376,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

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 sha256:9993acfcd14528ac8bcefc4a6a8bdeddc2e6aada567c8d9e0c601dd0ec603562
+size 167566461

onnx/decoder_model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6460c9714d5a2c5efed0e0273a918df433c8a74f7d2aa35b9ea6520491f4de82
+size 80511097

onnx/decoder_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51fe5d3f92fb37eb7572df43033c4ae0ba498a1d086ce4f012cde27ca4f704bc
+size 84020065

onnx/decoder_model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b55e803024137840e4319043678b6d402e1352e5fde1e467d449dedf6966f1
+size 42479003

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4da7ec2fab9370e45b7e8fbcc1a787e19ad6283aff523b08f9373df9b963849
+size 168377675

onnx/decoder_model_merged_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87de4e926833488eaf2e6bea5573cde6ba03046b8e8d02d3e7c432c3320e840f
+size 80751745

onnx/decoder_model_merged_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246c7792e890ba0b1ee197d74a241eb0850e749cec3aa2eadfbc86e029951fdb
+size 84057353

onnx/decoder_model_merged_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27711e76cd880f9708bef25397f3354f42c4e8c049947f73d723965ef8d95652
+size 42771369

onnx/decoder_model_merged_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25cede0887dbe93301c002cbccdaf594e9a102b8e9655a1abef66a10beb23a4e
+size 82331873

onnx/decoder_model_merged_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72355038b15c812a357cae6c0de6ec1d226adc912fa09b31dfc1269b2c1df782
+size 47708900

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d2095b1db3b264342e0aab8779bdaa311fb3117ae9faddd9e2da26ebd943f8
+size 43637900

onnx/decoder_model_merged_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d71562724a47791e36d81c26903fc9f586cb3cd4513f9a8f8ffaf328c6f18a16
+size 42771395

onnx/decoder_model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0227adf9723eb45f29634cd6740063cb9de73d45cdd2ae5c896c82e56d6cfe
+size 82091729

onnx/decoder_model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:358c7544a8efc5a6f653dbdf08c87b364534643677e17a208b292fd970b2ff1a
+size 47464028

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83784ee0b2b115606e5b69d3d5565e99c826d7aa7e1de5437c12b0a964c28c1d
+size 42675859

onnx/decoder_model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f32a68aab637e3faa0e3cf7da6454a5c49d90628499a33002df6e352a9d4a1d
+size 42479029

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d8434248807a07f0a85468cdbdd138171cb2d48c6b25165b99088821346991
+size 167568998

onnx/decoder_with_past_model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bda9c09936b215efcf759c6abe9a5d6c7c7ecbecd7a9520a46310b275c60c6b
+size 80495757

onnx/decoder_with_past_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc6d29592363df9acaf2da2ac3a1dcdbdca33edd900fa2f130837a92ac9849e
+size 83807548

onnx/decoder_with_past_model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2266e9f048125b78e42e47383bf1ab2281d3e00260825d600b1cb1d42e4c3660
+size 42463663

onnx/decoder_with_past_model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a9b1fbdc1abeae29ab75e4436bcf2c974a4b39b2add794bad172e5e34675b2
+size 82076389

onnx/decoder_with_past_model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8b35675e46df3e2a86d349410190b31dc65087166b599c38b51df99b701ec0
+size 47451647

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d5689e151084aa2dbf309f6f54f13fea852af91d00ebc2c4f5d9f7e96a39044
+size 42678372

onnx/decoder_with_past_model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c3592998d93bd7bf66415443825f66a77b5832e30ef4a782662078374b92c8d
+size 42463689

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a99afdeef37423caf04f18802482c7b9f4772e6b3a1fc7b866cafbb9a47a5c69
+size 166951932

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761a3979a2c794281abb91a1165abb3eccf9c0bc1ecbabe3651c004c3bd72ec3
+size 80002615

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a4cbb4b2534e61449d41ca9ded293d44bcd4b7b61ed942485369ae525a526f
+size 83576611

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:683df4e70202e34d0127509af99877b0fffea193416ecd7d812c75342758fd71
+size 41970488

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8234df5931173f7ab2fe6b4905569261bf5f8865f292f15b6d5b173a68ff8953
+size 81583247

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:301522517e8affa2f82d6dfc2b66e4e59e909859695a23a750d5b381b180609b
+size 47220710

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:683df4e70202e34d0127509af99877b0fffea193416ecd7d812c75342758fd71
+size 41970488

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9395fcb3d4abaa99de56f76d3f3c319e37a503cd1f598e115e510bcd877b9398
+size 41970513

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5d73fb5862fe2732b76c4e308ed343b4db2abbaf1fc1d58bd5b4f29d96d096
+size 166781967

quantize_config.json

@@ -0,0 +1,107 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "decoder_with_past_model": {
+            "op_types": [
+                "Unsqueeze",
+                "Transpose",
+                "Neg",
+                "Softmax",
+                "If",
+                "Identity",
+                "Expand",
+                "Where",
+                "Constant",
+                "Mul",
+                "Shape",
+                "Sigmoid",
+                "MatMul",
+                "Div",
+                "Squeeze",
+                "Range",
+                "Sub",
+                "Pow",
+                "Gather",
+                "Concat",
+                "ReduceMean",
+                "ConstantOfShape",
+                "Reshape",
+                "Sqrt",
+                "Cast",
+                "Slice",
+                "Add",
+                "Equal"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model": {
+            "op_types": [
+                "Unsqueeze",
+                "Transpose",
+                "Neg",
+                "Less",
+                "If",
+                "Softmax",
+                "Identity",
+                "Expand",
+                "Where",
+                "Constant",
+                "Mul",
+                "Shape",
+                "Sigmoid",
+                "MatMul",
+                "Div",
+                "Squeeze",
+                "Range",
+                "Sub",
+                "Pow",
+                "Gather",
+                "Concat",
+                "ReduceMean",
+                "ConstantOfShape",
+                "Reshape",
+                "Slice",
+                "Cast",
+                "Sqrt",
+                "Add",
+                "Equal"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Unsqueeze",
+                "Transpose",
+                "Neg",
+                "Less",
+                "If",
+                "Softmax",
+                "Identity",
+                "Expand",
+                "Where",
+                "Constant",
+                "Mul",
+                "Shape",
+                "Sigmoid",
+                "MatMul",
+                "Div",
+                "Squeeze",
+                "Range",
+                "Sub",
+                "Pow",
+                "Gather",
+                "Concat",
+                "ReduceMean",
+                "ConstantOfShape",
+                "Reshape",
+                "Slice",
+                "Cast",
+                "Sqrt",
+                "Add",
+                "Equal"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}