Upload standalone random quantized model

README.md

@@ -0,0 +1,139 @@
+---
+language: en
+license: apache-2.0
+tags:
+- quantization
+- deepseek
+- ocr
+- document-understanding
+- random-quantization
+base_model: deepseek-ai/DeepSeek-OCR
+pipeline_tag: image-to-text
+---
+
+# DeepSeek-OCR Random Quantized Model (Standalone)
+
+This is a **fully standalone randomly quantized** version of [deepseek-ai/DeepSeek-OCR](https://huggingface.co/deepseek-ai/DeepSeek-OCR).
+
+⚠️ **Note**: This model uses random quantization as a baseline for comparison. It is NOT optimized and will have significant quality degradation. This serves as a lower bound for intelligent quantization methods.
+
+## Model Details
+
+### Quantization Statistics
+- **Method**: Random Quantization (Baseline)
+- **Compression Ratio**: 1.90x
+- **Average Bit-Width**: 8.00 bits
+- **Original Size**: 6363.12 MB
+- **Compressed Size**: 3351.56 MB
+- **Size Reduction**: ~47.3%
+
+### Architecture
+Based on DeepSeek-OCR with custom `QuantizedLinear` layers that perform on-the-fly dequantization during inference.
+
+## Usage
+
+### Basic Loading
+
+```python
+from transformers import AutoModel, AutoTokenizer
+import torch
+
+# Load model and tokenizer (no base model needed!)
+model_name = "SamMikaelson/deepseek-ocr-int8-quantized"
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModel.from_pretrained(
+    model_name,
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16
+).to("cuda")
+
+# The model is ready to use!
+```
+
+### For Document OCR
+
+```python
+from transformers import AutoProcessor
+import torch
+from PIL import Image
+
+# Load
+processor = AutoProcessor.from_pretrained("SamMikaelson/deepseek-ocr-int8-quantized", trust_remote_code=True)
+model = AutoModel.from_pretrained(
+    "SamMikaelson/deepseek-ocr-int8-quantized",
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16
+).to("cuda")
+
+# Inference
+image = Image.open("document.jpg")
+prompt = "<image>\n<|grounding|>Convert the document to markdown."
+
+# Process and generate
+inputs = processor(text=prompt, images=image, return_tensors="pt").to("cuda")
+outputs = model.generate(**inputs, max_length=2048)
+result = processor.decode(outputs[0], skip_special_tokens=True)
+
+print(result)
+```
+
+## Performance Characteristics
+
+### Quality Metrics (Expected)
+- **NLS (Normalized Levenshtein Similarity)**: Significantly degraded (~0.01-0.1)
+- **WER (Word Error Rate)**: High error rate (20-50)
+- **Output Generation**: May produce nonsensical outputs due to random quantization
+
+### Speed Metrics
+- **Inference Latency**: Comparable to original (dequantization overhead)
+- **Memory Usage**: ~47.3% reduction
+
+## Limitations
+
+⚠️ **This is a baseline model for research purposes:**
+
+1. **Quality Degradation**: Random quantization severely impacts model quality
+2. **Not Production-Ready**: This model is for comparison/research only
+3. **Baseline Purpose**: Demonstrates the lower bound of quantization quality
+
+### Why This Model Exists
+
+This model serves as a **sanity check** and **lower bound** for intelligent quantization methods:
+- Shows what happens with no quantization intelligence
+- Provides a baseline to compare against optimized methods
+- Validates that your evaluation metrics can detect poor quantization
+
+## Better Alternatives
+
+For production use, consider:
+- **Sensitivity-aware quantization**: Quantize less important layers more aggressively
+- **Mixed-precision methods**: Use different bit-widths per layer based on importance
+- **Quantization-aware training**: Fine-tune after quantization
+- **GPTQ/AWQ**: State-of-the-art quantization methods
+
+## Files Included
+
+- `model.safetensors` or `pytorch_model.bin`: Complete model with quantized weights
+- `config.json`: Model configuration
+- `tokenizer.json`, `tokenizer_config.json`: Tokenizer files
+- `layer_configs.json`: Per-layer quantization settings
+- `quantization_info.json`: Quantization metadata
+- `compression_stats.json`: Compression statistics
+
+## Citation
+
+```bibtex
+@misc{deepseek-ocr-random-quantized,
+  title={DeepSeek-OCR Random Quantized Model},
+  author={SamMikaelson},
+  year={2024},
+  publisher={Hugging Face},
+  howpublished={\url{https://huggingface.co/SamMikaelson/deepseek-ocr-int8-quantized}}
+}
+```
+
+Original DeepSeek-OCR model: [deepseek-ai/DeepSeek-OCR](https://huggingface.co/deepseek-ai/DeepSeek-OCR)
+
+## License
+
+Apache 2.0 (same as base model)

compression_stats.json

@@ -0,0 +1,13 @@
+{
+  "original_params": 3336106240,
+  "quantized_layers": 2342,
+  "uniform_bits": 8,
+  "avg_bit_width": 8.0,
+  "original_size_mb": 6363.11767578125,
+  "compressed_size_mb": 3351.557418823242,
+  "compression_ratio": 1.898555471568018,
+  "vision_layers_quantized": 96,
+  "language_layers_quantized": 2197,
+  "actual_size_reduction": true,
+  "method": "uniform"
+}

config.json

@@ -0,0 +1,135 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-OCR",
+  "architectures": [
+    "DeepseekOCRForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "deepseek-ai/DeepSeek-OCR--modeling_deepseekocr.DeepseekOCRConfig",
+    "AutoModel": "deepseek-ai/DeepSeek-OCR--modeling_deepseekocr.DeepseekOCRForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 0,
+  "candidate_resolutions": [
+    [
+      1024,
+      1024
+    ]
+  ],
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 1,
+  "global_view_pos": "head",
+  "hidden_act": "silu",
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 6848,
+  "kv_lora_rank": null,
+  "language_config": {
+    "architectures": [
+      "DeepseekV2ForCausalLM"
+    ],
+    "auto_map": {
+      "AutoConfig": "configuration_deepseekv2.DeepseekV2Config",
+      "AutoModel": "modeling_deepseek.DeepseekV2Model",
+      "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
+    },
+    "bos_token_id": 0,
+    "eos_token_id": 1,
+    "first_k_dense_replace": 1,
+    "hidden_size": 1280,
+    "intermediate_size": 6848,
+    "kv_lora_rank": null,
+    "lm_head": true,
+    "max_position_embeddings": 8192,
+    "moe_intermediate_size": 896,
+    "n_group": 1,
+    "n_routed_experts": 64,
+    "n_shared_experts": 2,
+    "num_attention_heads": 10,
+    "num_experts_per_tok": 6,
+    "num_hidden_layers": 12,
+    "num_key_value_heads": 10,
+    "q_lora_rank": null,
+    "qk_nope_head_dim": 0,
+    "qk_rope_head_dim": 0,
+    "rm_head": false,
+    "topk_group": 1,
+    "topk_method": "greedy",
+    "torch_dtype": "bfloat16",
+    "use_mla": false,
+    "v_head_dim": 0,
+    "vocab_size": 129280
+  },
+  "lm_head": true,
+  "max_position_embeddings": 8192,
+  "model_type": "DeepseekOCR",
+  "moe_intermediate_size": 896,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 2,
+  "norm_topk_prob": false,
+  "num_attention_heads": 10,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 10,
+  "pretraining_tp": 1,
+  "projector_config": {
+    "input_dim": 2048,
+    "model_type": "mlp_projector",
+    "n_embed": 1280,
+    "projector_type": "linear"
+  },
+  "q_lora_rank": null,
+  "qk_nope_head_dim": 0,
+  "qk_rope_head_dim": 0,
+  "rm_head": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "routed_scaling_factor": 1.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "tile_tag": "2D",
+  "topk_group": 1,
+  "topk_method": "greedy",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "use_mla": false,
+  "v_head_dim": 0,
+  "vision_config": {
+    "image_size": 1024,
+    "mlp_ratio": 3.7362,
+    "model_name": "deeplip_b_l",
+    "model_type": "vision",
+    "width": {
+      "clip-l-14-224": {
+        "heads": 16,
+        "image_size": 224,
+        "layers": 24,
+        "patch_size": 14,
+        "width": 1024
+      },
+      "sam_vit_b": {
+        "downsample_channels": [
+          512,
+          1024
+        ],
+        "global_attn_indexes": [
+          2,
+          5,
+          8,
+          11
+        ],
+        "heads": 12,
+        "layers": 12,
+        "width": 768
+      }
+    }
+  },
+  "vocab_size": 129280
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66cfd58eaa2d4a6418f7573a9691f9c24515c7a147b26bbc443c0387d7f3c2f2
+size 3515210600

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|User|>",
+    "<|Assistant|>"
+  ],
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜▁pad▁｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}