Upload folder using huggingface_hub

README.md

@@ -6,6 +6,23 @@ base_model:
 license: apache-2.0
 library_name: transformers
 ---
+<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>
+
 # Qwen3-14B-Base
 
 ## Qwen3 Highlights
@@ -49,11 +66,13 @@ 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

@@ -4,12 +4,54 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "eos_token_id": 151645,
+  "eos_token_id": 151643,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 5120,
   "initializer_range": 0.02,
   "intermediate_size": 17408,
+  "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",
+    "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": 40,
   "model_type": "qwen3",
@@ -27,11 +69,12 @@
     "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",
       "modality_projection",
-      "model.layers.19.mlp",
       "model.layers.38.mlp",
       "model.layers.6.mlp"
     ],
@@ -46,7 +89,7 @@
   "sliding_window": null,
   "tie_word_embeddings": false,
   "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

@@ -1,8 +1,8 @@
 {
   "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "eos_token_id": 151643,
   "max_length": 32768,
   "max_new_tokens": 2048,
   "pad_token_id": 151654,
-  "transformers_version": "4.51.3"
+  "transformers_version": "4.53.2"
 }

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a0a244cbba51b90e93c251d1590cd1292de973cc25cefef3bb0761d1d553bad
-size 4589082712
+oid sha256:dd889985d4c47cbd2a950a48036ad1fff7a3f2745cfe345b6faa6045e519855b
+size 4192250759

model.safetensors.index.json

@@ -1,6 +1,7 @@
 {
   "metadata": {
-    "total_size": 11119044927
+    "total_parameters": 14768307200,
+    "total_size": 10722211590
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -513,8 +514,23 @@
     "model.layers.18.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",

special_tokens_map.json

@@ -15,7 +15,7 @@
     "<|video_pad|>"
   ],
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -228,7 +228,7 @@
   ],
   "bos_token": null,
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 32768,