Upload folder using huggingface_hub

README.md

@@ -7,9 +7,6 @@ tags:
 - tokenizers
 - optimum
 - text-generation
-- int8
-- quantized
-- mobile
 language: en
 pipeline_tag: text-generation
 ---
@@ -20,7 +17,7 @@ This is a version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) t
 - **Base Model:** `Qwen/Qwen3-0.6B`
 - **Task:** `text-generation`
 - **Opset Version:** `17`
-- **Optimization:** `INT8 - Optimized for Mobile (ARM64)`
+- **Optimization:** `FP32 (No Quantization)`
 ## Usage
 ### Installation
 For a lightweight mobile/serverless setup, you only need `onnxruntime` and `tokenizers`.
@@ -58,4 +55,4 @@ print("Output logits shape:", outputs[0].shape)
 ```
 ## About this Export
 This model was exported using [Optimum](https://huggingface.co/docs/optimum/index). 
-It includes the `INT8 - Optimized for Mobile (ARM64)` quantization settings and a pre-compiled `tokenizer.json` for fast loading.
+It includes the `FP32 (No Quantization)` quantization settings and a pre-compiled `tokenizer.json` for fast loading.

model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11cd9918130937ca393d358ed28b488709eff8acc1715461d3032dd32796c35e
-size 754045218
+oid sha256:61a00ac8fcba8de4719e7205a4cc1c4b9b3f01f88c0cf3c4fc90e59cdbce8a20
+size 1403685

tokenizer_config.json

@@ -231,6 +231,7 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "fix_mistral_regex": true,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,