Upload folder using huggingface_hub

README.md

@@ -0,0 +1,201 @@
+---
+library_name: peft
+---
+
+# 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. -->
+
+
+
+- **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]
+### Framework versions
+
+- PEFT 0.17.1.dev0

adapter_config.json

@@ -0,0 +1,370 @@
+{
+  "_module_configs": {
+    ".*vlm_with_expert.(?P<layer_name>lm_expert.layers.(?P<layer_id>(0|2|4|6|8|10|12|14)).self_attn.(k_proj|v_proj))": {
+      "add_zero_init_conv_layer": false,
+      "batch_first": true,
+      "discriminator_cfg": {
+        "batch_first": true,
+        "feature_dim": 720,
+        "feature_fusion": false,
+        "fused_feature_dim": null,
+        "hidden_dim": 128,
+        "max_batches_tracked": 2000,
+        "momentum": 0.1,
+        "num_tokens": 16,
+        "type": "autoencoder_small",
+        "use_momentum": true
+      },
+      "feature_dim": 720,
+      "func_adapter_cfg": {
+        "hidden_dim": null,
+        "lora_alpha": 32,
+        "lora_rank": 32,
+        "use_lora": true
+      },
+      "out_feature_dim": 320,
+      "pattern": ".*vlm_with_expert.(?P<layer_name>lm_expert.layers.(?P<layer_id>(0|2|4|6|8|10|12|14)).self_attn.(k_proj|v_proj))",
+      "use_trainable_copy": false
+    },
+    ".*vlm_with_expert.(?P<layer_name>lm_expert.layers.(?P<layer_id>(1|3|5|7|9|11|13|15)).self_attn.(k_proj|v_proj))": {
+      "add_zero_init_conv_layer": false,
+      "batch_first": true,
+      "discriminator_cfg": {
+        "batch_first": true,
+        "feature_dim": 320,
+        "feature_fusion": false,
+        "fused_feature_dim": null,
+        "hidden_dim": 64,
+        "max_batches_tracked": 2000,
+        "momentum": 0.1,
+        "num_tokens": 16,
+        "type": "autoencoder_small",
+        "use_momentum": true
+      },
+      "feature_dim": 320,
+      "func_adapter_cfg": {
+        "hidden_dim": null,
+        "lora_alpha": 32,
+        "lora_rank": 32,
+        "use_lora": true
+      },
+      "out_feature_dim": 320,
+      "pattern": ".*vlm_with_expert.(?P<layer_name>lm_expert.layers.(?P<layer_id>(1|3|5|7|9|11|13|15)).self_attn.(k_proj|v_proj))",
+      "use_trainable_copy": false
+    },
+    ".*vlm_with_expert.(?P<layer_name>lm_expert.layers.(?P<layer_id>\\d+).self_attn.q_proj)": {
+      "add_zero_init_conv_layer": false,
+      "batch_first": true,
+      "discriminator_cfg": {
+        "batch_first": true,
+        "feature_dim": 720,
+        "feature_fusion": false,
+        "fused_feature_dim": null,
+        "hidden_dim": 128,
+        "max_batches_tracked": 2000,
+        "momentum": 0.1,
+        "num_tokens": 16,
+        "type": "autoencoder_small",
+        "use_momentum": true
+      },
+      "feature_dim": 720,
+      "func_adapter_cfg": {
+        "hidden_dim": null,
+        "lora_alpha": 32,
+        "lora_rank": 32,
+        "use_lora": true
+      },
+      "out_feature_dim": 960,
+      "pattern": ".*vlm_with_expert.(?P<layer_name>lm_expert.layers.(?P<layer_id>\\d+).self_attn.q_proj)",
+      "use_trainable_copy": false
+    }
+  },
+  "add_zero_init_conv_layer": false,
+  "auto_mapping": {
+    "base_model_class": "PeftWrapperPolicy",
+    "parent_library": "__main__"
+  },
+  "base_model_name_or_path": null,
+  "batch_first": true,
+  "discriminator_cfg": null,
+  "feature_dim": null,
+  "func_adapter_cfg": null,
+  "inference_mode": true,
+  "num_learned_task": 1,
+  "out_feature_dim": null,
+  "peft_type": "CLARE",
+  "revision": null,
+  "structure": {
+    "lm_expert.layers.0.self_attn.k_proj.0": [
+      1,
+      1
+    ],
+    "lm_expert.layers.0.self_attn.q_proj.0": [
+      1,
+      1
+    ],
+    "lm_expert.layers.0.self_attn.v_proj.0": [
+      1,
+      1
+    ],
+    "lm_expert.layers.1.self_attn.k_proj.1": [
+      1,
+      1
+    ],
+    "lm_expert.layers.1.self_attn.q_proj.1": [
+      1,
+      1
+    ],
+    "lm_expert.layers.1.self_attn.v_proj.1": [
+      1,
+      1
+    ],
+    "lm_expert.layers.10.self_attn.k_proj.10": [
+      1,
+      1
+    ],
+    "lm_expert.layers.10.self_attn.q_proj.10": [
+      1,
+      1
+    ],
+    "lm_expert.layers.10.self_attn.v_proj.10": [
+      1,
+      1
+    ],
+    "lm_expert.layers.11.self_attn.k_proj.11": [
+      1,
+      1
+    ],
+    "lm_expert.layers.11.self_attn.q_proj.11": [
+      1,
+      1
+    ],
+    "lm_expert.layers.11.self_attn.v_proj.11": [
+      1,
+      1
+    ],
+    "lm_expert.layers.12.self_attn.k_proj.12": [
+      1,
+      1
+    ],
+    "lm_expert.layers.12.self_attn.q_proj.12": [
+      1,
+      1
+    ],
+    "lm_expert.layers.12.self_attn.v_proj.12": [
+      1,
+      1
+    ],
+    "lm_expert.layers.13.self_attn.k_proj.13": [
+      1,
+      1
+    ],
+    "lm_expert.layers.13.self_attn.q_proj.13": [
+      1,
+      1
+    ],
+    "lm_expert.layers.13.self_attn.v_proj.13": [
+      1,
+      1
+    ],
+    "lm_expert.layers.14.self_attn.k_proj.14": [
+      1,
+      1
+    ],
+    "lm_expert.layers.14.self_attn.q_proj.14": [
+      1,
+      1
+    ],
+    "lm_expert.layers.14.self_attn.v_proj.14": [
+      1,
+      1
+    ],
+    "lm_expert.layers.15.self_attn.k_proj.15": [
+      1,
+      1
+    ],
+    "lm_expert.layers.15.self_attn.q_proj.15": [
+      1,
+      1
+    ],
+    "lm_expert.layers.15.self_attn.v_proj.15": [
+      1,
+      1
+    ],
+    "lm_expert.layers.2.self_attn.k_proj.2": [
+      1,
+      1
+    ],
+    "lm_expert.layers.2.self_attn.q_proj.2": [
+      1,
+      1
+    ],
+    "lm_expert.layers.2.self_attn.v_proj.2": [
+      1,
+      1
+    ],
+    "lm_expert.layers.3.self_attn.k_proj.3": [
+      1,
+      1
+    ],
+    "lm_expert.layers.3.self_attn.q_proj.3": [
+      1,
+      1
+    ],
+    "lm_expert.layers.3.self_attn.v_proj.3": [
+      1,
+      1
+    ],
+    "lm_expert.layers.4.self_attn.k_proj.4": [
+      1,
+      1
+    ],
+    "lm_expert.layers.4.self_attn.q_proj.4": [
+      1,
+      1
+    ],
+    "lm_expert.layers.4.self_attn.v_proj.4": [
+      1,
+      1
+    ],
+    "lm_expert.layers.5.self_attn.k_proj.5": [
+      1,
+      1
+    ],
+    "lm_expert.layers.5.self_attn.q_proj.5": [
+      1,
+      1
+    ],
+    "lm_expert.layers.5.self_attn.v_proj.5": [
+      1,
+      1
+    ],
+    "lm_expert.layers.6.self_attn.k_proj.6": [
+      1,
+      1
+    ],
+    "lm_expert.layers.6.self_attn.q_proj.6": [
+      1,
+      1
+    ],
+    "lm_expert.layers.6.self_attn.v_proj.6": [
+      1,
+      1
+    ],
+    "lm_expert.layers.7.self_attn.k_proj.7": [
+      1,
+      1
+    ],
+    "lm_expert.layers.7.self_attn.q_proj.7": [
+      1,
+      1
+    ],
+    "lm_expert.layers.7.self_attn.v_proj.7": [
+      1,
+      1
+    ],
+    "lm_expert.layers.8.self_attn.k_proj.8": [
+      1,
+      1
+    ],
+    "lm_expert.layers.8.self_attn.q_proj.8": [
+      1,
+      1
+    ],
+    "lm_expert.layers.8.self_attn.v_proj.8": [
+      1,
+      1
+    ],
+    "lm_expert.layers.9.self_attn.k_proj.9": [
+      1,
+      1
+    ],
+    "lm_expert.layers.9.self_attn.q_proj.9": [
+      1,
+      1
+    ],
+    "lm_expert.layers.9.self_attn.v_proj.9": [
+      1,
+      1
+    ]
+  },
+  "target_modules": {
+    ".*vlm_with_expert.(?P<layer_name>lm_expert.layers.(?P<layer_id>(0|2|4|6|8|10|12|14)).self_attn.(k_proj|v_proj))": {
+      "add_zero_init_conv_layer": false,
+      "batch_first": true,
+      "discriminator_cfg": {
+        "batch_first": true,
+        "feature_dim": 720,
+        "feature_fusion": false,
+        "fused_feature_dim": null,
+        "hidden_dim": 128,
+        "max_batches_tracked": 2000,
+        "momentum": 0.1,
+        "num_tokens": 16,
+        "type": "autoencoder_small",
+        "use_momentum": true
+      },
+      "feature_dim": 720,
+      "func_adapter_cfg": {
+        "hidden_dim": null,
+        "lora_alpha": 32,
+        "lora_rank": 32,
+        "use_lora": true
+      },
+      "out_feature_dim": 320,
+      "use_trainable_copy": false
+    },
+    ".*vlm_with_expert.(?P<layer_name>lm_expert.layers.(?P<layer_id>(1|3|5|7|9|11|13|15)).self_attn.(k_proj|v_proj))": {
+      "add_zero_init_conv_layer": false,
+      "batch_first": true,
+      "discriminator_cfg": {
+        "batch_first": true,
+        "feature_dim": 320,
+        "feature_fusion": false,
+        "fused_feature_dim": null,
+        "hidden_dim": 64,
+        "max_batches_tracked": 2000,
+        "momentum": 0.1,
+        "num_tokens": 16,
+        "type": "autoencoder_small",
+        "use_momentum": true
+      },
+      "feature_dim": 320,
+      "func_adapter_cfg": {
+        "hidden_dim": null,
+        "lora_alpha": 32,
+        "lora_rank": 32,
+        "use_lora": true
+      },
+      "out_feature_dim": 320,
+      "use_trainable_copy": false
+    },
+    ".*vlm_with_expert.(?P<layer_name>lm_expert.layers.(?P<layer_id>\\d+).self_attn.q_proj)": {
+      "add_zero_init_conv_layer": false,
+      "batch_first": true,
+      "discriminator_cfg": {
+        "batch_first": true,
+        "feature_dim": 720,
+        "feature_fusion": false,
+        "fused_feature_dim": null,
+        "hidden_dim": 128,
+        "max_batches_tracked": 2000,
+        "momentum": 0.1,
+        "num_tokens": 16,
+        "type": "autoencoder_small",
+        "use_momentum": true
+      },
+      "feature_dim": 720,
+      "func_adapter_cfg": {
+        "hidden_dim": null,
+        "lora_alpha": 32,
+        "lora_rank": 32,
+        "use_lora": true
+      },
+      "out_feature_dim": 960,
+      "use_trainable_copy": false
+    }
+  },
+  "task_type": null,
+  "use_trainable_copy": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c34437d162b7ae597b22ee3fd6c991cf1d72ed93891355c0d89a99411f8bed
+size 18711872