Upload model

README.md

@@ -0,0 +1,198 @@
+---
+library_name: diffusers
+---
+
+# 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 🧨 diffusers 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 +1,123 @@
+{
+  "_class_name": "SanaTransformer2DModel",
+  "_diffusers_version": "0.34.0.dev0",
+  "_name_or_path": "Efficient-Large-Model/Sana_600M_1024px_diffusers",
+  "attention_bias": false,
+  "attention_head_dim": 32,
+  "caption_channels": 2304,
+  "cross_attention_dim": 1152,
+  "cross_attention_head_dim": 72,
+  "dropout": 0.0,
+  "guidance_embeds": false,
+  "guidance_embeds_scale": 0.1,
+  "in_channels": 32,
+  "interpolation_scale": null,
+  "mlp_ratio": 2.5,
+  "norm_elementwise_affine": false,
+  "norm_eps": 1e-06,
+  "num_attention_heads": 36,
+  "num_cross_attention_heads": 16,
+  "num_layers": 28,
+  "out_channels": 32,
+  "patch_size": 1,
+  "qk_norm": null,
+  "quantization_config": {
+    "algorithm": "max",
+    "block_quantize": null,
+    "channel_quantize": null,
+    "modelopt_config": {
+      "algorithm": "max",
+      "quant_cfg": {
+        "*block_sparse_moe.gate*": {
+          "enable": false
+        },
+        "*input_quantizer": {
+          "enable": false
+        },
+        "*k_bmm_quantizer": {
+          "enable": false
+        },
+        "*lm_head*": {
+          "enable": false
+        },
+        "*mlp.gate.*": {
+          "enable": false
+        },
+        "*mlp.shared_expert_gate.*": {
+          "enable": false
+        },
+        "*output_layer*": {
+          "enable": false
+        },
+        "*output_quantizer": {
+          "enable": false
+        },
+        "*proj_out.*": {
+          "enable": false
+        },
+        "*q_bmm_quantizer": {
+          "enable": false
+        },
+        "*router*": {
+          "enable": false
+        },
+        "*softmax_quantizer": {
+          "enable": false
+        },
+        "*v_bmm_quantizer": {
+          "enable": false
+        },
+        "*weight_quantizer": {
+          "fake_quant": false,
+          "num_bits": [
+            4,
+            3
+          ]
+        },
+        "default": {
+          "enable": false
+        },
+        "nn.BatchNorm1d": {
+          "*": {
+            "enable": false
+          }
+        },
+        "nn.BatchNorm2d": {
+          "*": {
+            "enable": false
+          }
+        },
+        "nn.BatchNorm3d": {
+          "*": {
+            "enable": false
+          }
+        },
+        "nn.LeakyReLU": {
+          "*": {
+            "enable": false
+          }
+        },
+        "output.*": {
+          "enable": false
+        }
+      }
+    },
+    "modules_to_not_convert": null,
+    "quant_method": "modelopt",
+    "quant_type": "FP8",
+    "type_bit_map": {
+      "FP8": [
+        4,
+        3
+      ],
+      "INT4": 4,
+      "NVFP4": [
+        2,
+        1
+      ]
+    },
+    "weight_only": true
+  },
+  "sample_size": 32,
+  "timestep_scale": 1.0
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab2efee5cd4429de2a0265281c871b108facdf72c89c58430b0f7ae5cac27b9
+size 592617144

modelopt_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ceba166545307f1be1a6e4a7b4bea6a1df42889f18b8b730cd8270642a6111
+size 150076