chore: squash history to reclaim orphaned LFS objects (HEAD unchanged)

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,100 @@
+---
+license: apache-2.0
+base_model: Jackrong/Qwopus3.5-27B-v3
+language:
+  - en
+  - zh
+  - ko
+  - ja
+tags:
+  - polarquant
+  - quantized
+  - compressed-tensors
+  - int4
+  - marlin
+  - vllm
+pipeline_tag: text-generation
+arxiv: "2603.29078"
+library_name: transformers
+---
+
+# Huihui-Qwopus3.5-27B-abliterated — PolarQuant INT4
+
+**Native vLLM. Marlin kernel. Zero plugin.**
+
+PolarQuant Q5 preprocessing produces **better INT4 weights** than direct quantization — stored in CompressedTensors format for native vLLM inference.
+
+## Quick Start — vLLM (one command)
+
+```bash
+pip install vllm
+vllm serve caiovicentino1/Huihui-Qwopus3.5-27B-v3-abliterated-PolarQuant-Q5 --language-model-only --enforce-eager
+```
+
+That's it. No plugin, no `pip install polarquant`, no custom code.
+
+**Tested results:**
+
+| GPU | tok/s |
+|-----|-------|
+| A100 80GB | **168 tok/s** (9B) |
+| RTX PRO 6000 96GB | **44 tok/s** (9B) / **18 tok/s** (27B) |
+
+## Quick Start — HuggingFace Transformers
+
+```bash
+pip install polarquant
+```
+
+```python
+import polarengine_vllm  # auto-registers with transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("caiovicentino1/Huihui-Qwopus3.5-27B-v3-abliterated-PolarQuant-Q5", device_map="auto", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("caiovicentino1/Huihui-Qwopus3.5-27B-v3-abliterated-PolarQuant-Q5", trust_remote_code=True)
+
+inputs = tokenizer("Hello!", return_tensors="pt").to("cuda")
+out = model.generate(**inputs, max_new_tokens=100)
+print(tokenizer.decode(out[0], skip_special_tokens=True))
+```
+
+
+## Consumer GPU Compatibility
+
+| GPU | VRAM | Works? | Expected tok/s |
+|-----|------|--------|---------------|
+| RTX 4090 | 24 GB | YES (tight) | ~10 |
+| A100 / H100 | 80 GB | YES | ~18-50 |
+| RTX PRO 6000 | 96 GB | YES | ~18 |
+
+## Why PolarQuant INT4 is Better
+
+Standard INT4 (GPTQ/AWQ) quantizes weights directly — outliers cause errors.
+
+PolarQuant adds a **preprocessing step**:
+
+1. **Hadamard rotation** — distributes weight energy uniformly (eliminates outliers)
+2. **Lloyd-Max Q5** — MSE-optimal quantization for the resulting Gaussian distribution
+3. **Dequant → INT4** — the cleaned weights produce better INT4 than direct quantization
+
+| Method | PPL (lower = better) |
+|--------|---------------------|
+| BF16 baseline | 6.37 |
+| **PolarQuant → INT4** | **6.56** |
+| Direct INT4 | 6.68 |
+
+**Same speed as GPTQ/AWQ, better quality.**
+
+## Important Flags
+
+| Flag | Why |
+|------|-----|
+| `--language-model-only` | Qwen3.5 is multimodal — this skips the vision encoder (we only quantized text) |
+| `--enforce-eager` | Required on Blackwell GPUs (cc 12.0). Optional on A100/H100 (faster without it) |
+
+## Links
+
+- Paper: [arxiv.org/abs/2603.29078](https://arxiv.org/abs/2603.29078)
+- GitHub: [github.com/caiovicentino/polarengine-vllm](https://github.com/caiovicentino/polarengine-vllm)
+- PyPI: `pip install polarquant`
+- Base model: [Jackrong/Qwopus3.5-27B-v3](https://huggingface.co/Jackrong/Qwopus3.5-27B-v3)

config.json

@@ -0,0 +1,179 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "bos_token_id": null,
+  "torch_dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "image_token_id": 248056,
+  "model_name": "unsloth/Qwen3.5-27B",
+  "model_type": "qwen3_5",
+  "pad_token_id": 248055,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 17408,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 48,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 24,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "unsloth_fixed": true,
+  "unsloth_version": "2026.3.18",
+  "use_cache": false,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "torch_dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "quantization_config": {
+    "quant_method": "compressed-tensors",
+    "format": "pack-quantized",
+    "quantization_status": "compressed",
+    "global_compression_ratio": 4.0,
+    "config_groups": {
+      "group_0": {
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "num_bits": 4,
+          "type": "int",
+          "symmetric": true,
+          "strategy": "group",
+          "group_size": 128,
+          "dynamic": false,
+          "block_structure": null
+        },
+        "input_activations": null,
+        "output_activations": null
+      }
+    },
+    "ignore": [
+      "lm_head",
+      "embed_tokens",
+      "re:.*in_proj_a$",
+      "re:.*in_proj_b$",
+      "re:visual\\..*",
+      "re:.*vision.*"
+    ]
+  }
+}

model-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74596882a9d73ba395ee3f8a6c5b08243ff7bea06ee711d3bcc127f6e905d9c7
+size 6875108400

model-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8462a3fe9297b49d7d60c5a1d09759af91d40abc387cacab5a2c85702cadb4dd
+size 5010862512

model-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b743210c8c8166865ce158e97dc276691c34deda2a9ee32ce30b94f430d3bf
+size 3247759400

polar_config.json

@@ -0,0 +1,30 @@
+{
+  "method": "PolarQuant",
+  "weight_bits": 5,
+  "kv_cache_bits": 3,
+  "block_size": 128,
+  "head_dim": 128,
+  "num_layers": 64,
+  "quantized_layers": 497,
+  "skipped_layers": 0,
+  "int4_group_size": 128,
+  "vram_gb": 19.1,
+  "base_model": "huihui-ai/Huihui-Qwopus3.5-27B-v3-abliterated",
+  "benchmark": {
+    "FP16": {
+      "tok_s": 21.804779849809538,
+      "peak_gb": 70.363202048,
+      "time": 4.586150407791138
+    },
+    "Q3": {
+      "tok_s": 22.092763850247692,
+      "peak_gb": 19.130801664,
+      "time": 4.526368935902913
+    },
+    "Q2": {
+      "tok_s": 22.038845106697618,
+      "peak_gb": 19.130801664,
+      "time": 4.537442843119304
+    }
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2TokenizerFast",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n<think>\n' }}\n{%- endif %}"
+}