Upload TinyLlama with my changes

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,24 @@
+---
+base_model: Maykeye/TinyLLama-v0
+library_name: transformers.js
+---
+
+https://huggingface.co/Maykeye/TinyLLama-v0 with ONNX weights to be compatible with Transformers.js.
+
+## 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
+```
+
+**Example:** Text generation.
+
+```js
+import { pipeline } from '@huggingface/transformers';
+
+const generator = await pipeline('text-generation', 'Xenova/TinyLLama-v0');
+const output = await generator('Once upon a time, there was', { max_new_tokens: 10 });
+```
+
+Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "Maykeye/TinyLLama-v0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 16,
+  "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": "4.33.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

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": "4.33.0.dev0"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e3763f9f513b9e74e3163c414175648a32ecdd3f2c240dd1be551ade1a5d4e0
+size 18831545

onnx/decoder_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00154ee04aa82dbfe98025f82d858e64294372bfeb17932c2535e52488cbbfa1
+size 9653657

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21fae0af980af7f7e1005f1abc22a1ed9a3bdad62394fbd5dca2776237ca146
+size 19185357

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c613274e7b4ae8030e565a49431e5ad5481fcd3774fca084da707af3b531dbed
+size 5630131

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a72c0a623820aeab2791e41fa280611ef4bff6624bdedcbdb9248e62dcd8ec
+size 5124152

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897f742e4735a8e4216b13f7a028ec3dfbf442b76d638f3672d68194705a1bef
+size 18834082

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc9425c29c3586cfadecc5c8b091b54c02ff42a68b6c5e4805720105101e08ed
+size 5126664

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21fae0af980af7f7e1005f1abc22a1ed9a3bdad62394fbd5dca2776237ca146
+size 19185357

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32cb9bc4df65973b7ed94e0c9b14eb38d1c9b8e56baa16579dcc3c11d1d253cd
+size 10119777

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69f44055e448fdb83c66af5eee2f85b3601ee094b079d88bc36acfef2c929a1
+size 9677453

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b790b1599cafb40f301a015f23bb8bae35a898aa1972d23d7a998b3547823a6f
+size 5206385

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4fbdab6301023bc72cdf278226c6e923f95df5bdf354c04d450e8312674d6d
+size 10279625

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533f26f8a1887f09f4911452ba989b2029b43c11c8bb04b7ea6b9d130aaccb05
+size 5995596

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373025e0a51e00308ffcd4bb45d601fdf7dcfcec22cd2acfb4aa1bb751e194dd
+size 5206415

quantize_config.json

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

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
+size 534194

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}