Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+## DFloat11 Compressed Model: `Qwen/Qwen3-14B`
+
+This is a **losslessly compressed** version of [`Qwen/Qwen3-14B`](https://huggingface.co/Qwen/Qwen3-14B) using our custom **DFloat11** format. The outputs of this compressed model are **bit-for-bit identical** to the original BFloat16 model, while reducing GPU memory consumption by approximately **30%**.
+
+### 🔍 How It Works
+
+DFloat11 compresses model weights using **Huffman coding** of BFloat16 exponent bits, combined with **hardware-aware algorithmic designs** that enable efficient on-the-fly decompression directly on the GPU. During inference, the weights remain compressed in GPU memory and are **decompressed just before matrix multiplications**, then **immediately discarded after use** to minimize memory footprint.
+
+Key benefits:
+
+* **No CPU decompression or host-device data transfer** -- all operations are handled entirely on the GPU.
+* **Decompression overhead is constant** per forward pass and **independent of batch size**, making DFloat11 increasingly efficient at larger batch sizes.
+* DFloat11 is **much faster than CPU-offloading approaches**, enabling practical deployment in memory-constrained environments.
+* At **batch size = 1**, inference is approximately **2× slower** than the original BF16 model, but the performance gap **narrows significantly** with larger batches.
+* The compression is **fully lossless**, guaranteeing that the model’s outputs are **bit-for-bit identical** to those of the original model.
+
+### 🔧 How to Use
+
+1. Install the DFloat11 pip package *(installs the CUDA kernel automatically; requires a CUDA-compatible GPU and PyTorch installed)*:
+
+    ```bash
+    pip install dfloat11[cuda12]
+    # or if you have CUDA version 11:
+    # pip install dfloat11[cuda11]
+    ```
+
+2. To use the DFloat11 model, run the following example code in Python:
+
+    ```python
+    import torch
+    from dfloat11 import DFloat11Model
+    from transformers import AutoTokenizer
+
+    model_id = "DFloat11/Qwen3-14B-DF11"
+
+    model = DFloat11Model.from_pretrained(model_id, device_map="auto")
+
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    tokenizer.pad_token = tokenizer.eos_token
+
+    prompt = "Question: What is a binary tree and its applications? Answer:"
+    inputs = tokenizer(prompt, return_tensors="pt", padding=True).to(model.device)
+
+    with torch.no_grad():
+        output = model.generate(
+            **inputs,
+            max_new_tokens=256,
+            do_sample=True,
+        )
+
+    print(tokenizer.batch_decode(output, skip_special_tokens=True))
+    ```
+
+### 📄 Learn More
+
+* **Paper**: [70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float](https://arxiv.org/abs/2504.11651)
+* **GitHub**: [https://github.com/LeanModels/DFloat11](https://github.com/LeanModels/DFloat11)
+* **HuggingFace**: [https://huggingface.co/DFloat11](https://huggingface.co/DFloat11)

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dfloat11_config": {
+    "bytes_per_thread": 8,
+    "pattern_dict": {
+      "lm_head": [],
+      "model.embed_tokens": [],
+      "model.layers.\\d+": [
+        "self_attn.q_proj",
+        "self_attn.k_proj",
+        "self_attn.v_proj",
+        "self_attn.o_proj",
+        "mlp.gate_proj",
+        "mlp.up_proj",
+        "mlp.down_proj"
+      ]
+    },
+    "threads_per_block": [
+      512
+    ],
+    "version": "0.2.0"
+  },
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

lm_head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca4ecce5d1bb4845f60bf93d7e932a43edfc4d8a2592376eae64fd715659a20
+size 1055702884

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:872cea34c9b5d844d71523ff1220c492eb0807afa0acc03cc1ed1e6a64e4e5b6
+size 10360

model_embed_tokens.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b020d1cc3f10bdf1a122260f36660b1c31c710c00ee704e551bc8d397f889e
+size 1057861894

model_layers_0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fef12b7c56f5d52b913ad3951f7ec1f7ea55d02d954b649a5b2bf399134cb6
+size 448335915

model_layers_1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142ccff539212e4ab3eafee16d52750a8ba1fa84b5ab50f8d06adf08423255d6
+size 487779009

model_layers_10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6bf55a70baed8e314f0c66118168cc5e78b429b4cc60fd8c134519eba6537f4
+size 445626062

model_layers_11.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14afe90e2fffedb4017d352345ed1b927991088aa8b993837380c33549fa7fd
+size 445739053

model_layers_12.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e39ae35c3913d19ab4a5f16178b988d41efe2d118783cc77d08540c2430268
+size 446097052

model_layers_13.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77d37d6a1d3fe0ee9aacf216b01070ebfe877ad7fb725d0e6587a3c96bb61af
+size 446478333

model_layers_14.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e02e2773623e878d9b8c66e5e56c909ba15338c69daa90ed2651eb4c54a49273
+size 446577759

model_layers_15.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30dceac03e66b7eed78d034dca0444cb2cd5d48667938b156c3f698bd28ec074
+size 446456854

model_layers_16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c6b01b8be77f11d8ef45a44bfdf8e36268017f4d38cd33b3aba37cbd0ffbd5
+size 446723600

model_layers_17.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef6ba15556076d0eeb95d00478442fc4a421c9ecfe21645651b4cf2dfebd8fd9
+size 446940624

model_layers_18.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f780c1365ae39e3b0e9a8eca419a8ce8e7e87953ea9cf1df172be050c21e52ee
+size 447226980

model_layers_19.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25488e1a3015b6e6cb91eb40a8dc3f604c45847a713947b27dacb9d0cbe62c04
+size 447302715

model_layers_2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3782035adca132d8f3de1e8ff2e6591e84dcb965a31317162f16e6baa0401635
+size 490310356

model_layers_20.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a843ae9e9224d8bba3a054d2a260d2f6a2eca4a30ba9c42e7c8c84439170d796
+size 447516605

model_layers_21.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc434ca668684fc97f20d3412a32f88199a2abdca0aedcfa45131aa7a6c6168
+size 447230016

model_layers_22.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e017e7144603641765a54673ec847e1c2b979bfe91e3ed51df57ddb7f5a85a1d
+size 447107813

model_layers_23.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924355fe80590eb8ce583ce2b0714be15398d7a6435b3e05c80b5b1c3f2734e0
+size 447026146

model_layers_24.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f0e73494c27bdbe341aea4512632fdf45bb20268b00c5c2d0ab626f7aec34bf
+size 446756247

model_layers_25.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1cefd1c8e85c47572fa2406effcfea09c4e530915052dfab122f9774ffacbb7
+size 446673623

model_layers_26.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eaa0efc2cb28badbf185139a73ad57b4d3c389365e3660be70e414d156bd175
+size 446685292

model_layers_27.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:829b76391e8b5304408fbc0da2c87ce5a7a8ee9a84de0f136d83aead9697318c
+size 446674528

model_layers_28.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c1dfc3bc5a521847cbcfbeadd2910c37437984c62c79ee664abeff41c50455
+size 446557884

model_layers_29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5466a2e206b736388a7322fa275190a31276e384bbff032de03891e52c8b6dc3
+size 446392941

model_layers_3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a7faf199a2a2e06750576fd67b9fb7468e773c7df5fe2039ef5d1397c5b5d2
+size 479236809

model_layers_30.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ae434b24b508abd2a23cb24c0852fdf3a9632af933d0296ec9b09d585b8556
+size 446190074

model_layers_31.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46641c1389521711f25df1e74899091ab7c4774c251b435825fafb81df9c22da
+size 446182897

model_layers_32.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0891d17df190e93b09e93df35edecc9627e94ae0d119f974ca3411c95268bef
+size 446078836

model_layers_33.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c2f5cbaaa4cc2240c3ee955de963fd33123a8b8cb88296ce49d08615972e5aa
+size 446071802

model_layers_34.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8356d6e182283fc7d4c8a11a7247f3144dba2da986de2d61f0165165c77fe3c
+size 446124779

model_layers_35.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aef3a26d2a2f30ff71c0a918b469a3a494fb115dd0108a32d33753a5fc8b4a4
+size 446211006

model_layers_36.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f630097733af7af4cff591fb8fd94b0af798e0c570ed35c0c262a7fb1c5e4e1
+size 446160037

model_layers_37.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07214d34285ae0ddc5798e72bc85bd427d4ce194d9731a147c0a999df200b544
+size 446323194

model_layers_38.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130c7966c5bfbbd58701f1b1709000e612df70fb3124150128730a910246b2f5
+size 446456505

model_layers_39.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae40cd2a13ea5927e0f277c5c6fc5a438063ad6cb93e6b448cf99f9c8f941192
+size 447108384

model_layers_4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43a4016ba27fff88b79ae5d63e8f42a8fb4aa9deba46b9acfced0a510022db9
+size 470529813

model_layers_5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eb91a7e0366bd46f6ca1ea9d324d15e16802a7ab42e084b769e0e01e12baabf
+size 458885908

model_layers_6.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bdc71d5578b341e50b76a7bc5f24ba01d6e83555e9c2c7450bb483799877788
+size 449177728

model_layers_7.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fdbca87c5ef10482a356c0346abb72afce65dd0499112fe9cd1fd5f70f59009
+size 447757474

model_layers_8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94770c7685f23790240cb70f6dc63ffc3c06b56cae44c8c184db90272db3926a
+size 446848638

model_layers_9.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ecb871ec586dccc3baefe9d1fe11f60f2dfc725187a4d799700254eff397d35
+size 446095910

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}