Upload DeepseekOCRForCausalLM

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

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-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3791b38410fcd609af63c2ca6c5ddbe8ed5554bfe5e49ed4580c53ba706e72
+size 5000038048

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e727af0c7177a56e3c99c123248069c3102185fe86fb8197462dd4ebaf518e
+size 869704152