Upload folder using huggingface_hub

README.md

@@ -7,6 +7,23 @@ license: apache-2.0
 library_name: transformers
 pipeline_tag: text-generation
 ---
+<div>
+<p style="margin-top: 0;margin-bottom: 0;">
+    <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
+  </p>
+  <div style="display: flex; gap: 5px; align-items: center; ">
+    <a href="https://github.com/unslothai/unsloth/">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
+    </a>
+    <a href="https://discord.gg/unsloth">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
+    </a>
+    <a href="https://docs.unsloth.ai/">
+      <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
+    </a>
+  </div>
+</div>
+
 # Qwen3-0.6B-Base
 
 ## Qwen3 Highlights
@@ -50,11 +67,13 @@ Detailed evaluation results are reported in this [📑 blog](https://qwenlm.gith
 If you find our work helpful, feel free to give us a cite.
 
 ```
-@misc{qwen3,
-    title  = {Qwen3},
-    url    = {https://qwenlm.github.io/blog/qwen3/},
-    author = {Qwen Team},
-    month  = {April},
-    year   = {2025}
+@misc{qwen3technicalreport,
+      title={Qwen3 Technical Report}, 
+      author={Qwen Team},
+      year={2025},
+      eprint={2505.09388},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2505.09388}, 
 }
 ```

config.json

@@ -10,6 +10,36 @@
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
   "max_position_embeddings": 32768,
   "max_window_layers": 28,
   "model_type": "qwen3",
@@ -27,6 +57,8 @@
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": [
+      "embed_tokens",
+      "embedding",
       "lm_head",
       "multi_modal_projector",
       "merger",
@@ -43,7 +75,7 @@
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.53.2",
   "unsloth_fixed": true,
   "use_cache": true,
   "use_sliding_window": false,

generation_config.json

@@ -4,5 +4,5 @@
   "max_length": 32768,
   "max_new_tokens": 2048,
   "pad_token_id": 151654,
-  "transformers_version": "4.51.3"
+  "transformers_version": "4.53.2"
 }