Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: a8cheng/SpatialRGPT-VILA1.5-8B
+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 0.9.0

adapter_config.json

@@ -0,0 +1,252 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "llm.model.layers.2.self_attn.k_proj",
+    "llm.model.layers.22.mlp.up_proj",
+    "llm.model.layers.9.self_attn.v_proj",
+    "llm.model.layers.17.self_attn.o_proj",
+    "llm.model.layers.21.self_attn.q_proj",
+    "llm.model.layers.17.self_attn.k_proj",
+    "llm.model.layers.15.mlp.up_proj",
+    "llm.model.layers.21.self_attn.o_proj",
+    "llm.model.layers.24.self_attn.o_proj",
+    "llm.model.layers.30.mlp.gate_proj",
+    "llm.model.layers.2.self_attn.o_proj",
+    "llm.model.layers.7.self_attn.v_proj",
+    "llm.model.layers.8.self_attn.k_proj",
+    "llm.model.layers.23.self_attn.o_proj",
+    "llm.model.layers.11.self_attn.q_proj",
+    "llm.model.layers.18.mlp.down_proj",
+    "llm.model.layers.1.self_attn.k_proj",
+    "llm.model.layers.26.self_attn.k_proj",
+    "llm.model.layers.19.mlp.up_proj",
+    "llm.model.layers.16.self_attn.v_proj",
+    "llm.model.layers.20.mlp.gate_proj",
+    "llm.model.layers.22.self_attn.o_proj",
+    "llm.model.layers.14.mlp.down_proj",
+    "llm.model.layers.0.self_attn.v_proj",
+    "llm.model.layers.18.self_attn.k_proj",
+    "llm.model.layers.6.self_attn.v_proj",
+    "llm.model.layers.12.mlp.gate_proj",
+    "llm.model.layers.5.self_attn.o_proj",
+    "llm.model.layers.0.mlp.down_proj",
+    "llm.model.layers.20.mlp.up_proj",
+    "llm.model.layers.31.mlp.up_proj",
+    "llm.model.layers.6.self_attn.k_proj",
+    "llm.model.layers.11.self_attn.k_proj",
+    "llm.model.layers.26.mlp.up_proj",
+    "llm.model.layers.0.self_attn.q_proj",
+    "llm.model.layers.9.self_attn.o_proj",
+    "llm.model.layers.3.mlp.up_proj",
+    "llm.model.layers.27.mlp.up_proj",
+    "llm.model.layers.18.self_attn.v_proj",
+    "llm.model.layers.28.self_attn.q_proj",
+    "llm.model.layers.4.mlp.gate_proj",
+    "llm.model.layers.1.self_attn.q_proj",
+    "llm.model.layers.17.mlp.gate_proj",
+    "llm.model.layers.31.self_attn.v_proj",
+    "llm.model.layers.18.self_attn.o_proj",
+    "llm.model.layers.20.self_attn.k_proj",
+    "llm.model.layers.10.mlp.down_proj",
+    "llm.model.layers.23.mlp.gate_proj",
+    "llm.model.layers.4.self_attn.o_proj",
+    "llm.model.layers.9.mlp.up_proj",
+    "llm.model.layers.17.mlp.up_proj",
+    "llm.model.layers.22.self_attn.v_proj",
+    "llm.model.layers.13.mlp.down_proj",
+    "llm.model.layers.31.mlp.gate_proj",
+    "llm.model.layers.21.self_attn.v_proj",
+    "llm.model.layers.12.self_attn.o_proj",
+    "llm.model.layers.9.self_attn.q_proj",
+    "llm.model.layers.15.self_attn.o_proj",
+    "llm.model.layers.25.mlp.up_proj",
+    "llm.model.layers.2.mlp.gate_proj",
+    "llm.model.layers.13.self_attn.o_proj",
+    "llm.model.layers.25.mlp.gate_proj",
+    "llm.model.layers.19.mlp.down_proj",
+    "llm.model.layers.20.self_attn.v_proj",
+    "llm.model.layers.31.self_attn.q_proj",
+    "llm.model.layers.19.self_attn.o_proj",
+    "llm.model.layers.10.self_attn.k_proj",
+    "llm.model.layers.23.self_attn.v_proj",
+    "llm.model.layers.6.self_attn.o_proj",
+    "llm.model.layers.27.mlp.down_proj",
+    "llm.model.layers.26.mlp.down_proj",
+    "llm.model.layers.4.self_attn.q_proj",
+    "llm.model.layers.5.self_attn.q_proj",
+    "llm.model.layers.10.mlp.up_proj",
+    "llm.model.layers.22.self_attn.k_proj",
+    "llm.model.layers.13.mlp.gate_proj",
+    "llm.model.layers.28.mlp.down_proj",
+    "llm.model.layers.29.mlp.down_proj",
+    "llm.model.layers.29.self_attn.o_proj",
+    "llm.model.layers.8.self_attn.o_proj",
+    "llm.model.layers.7.self_attn.q_proj",
+    "llm.model.layers.19.self_attn.q_proj",
+    "llm.model.layers.12.self_attn.k_proj",
+    "llm.model.layers.3.mlp.gate_proj",
+    "llm.model.layers.16.self_attn.k_proj",
+    "llm.model.layers.13.self_attn.v_proj",
+    "llm.model.layers.1.mlp.up_proj",
+    "llm.model.layers.27.self_attn.o_proj",
+    "llm.model.layers.4.mlp.down_proj",
+    "llm.model.layers.25.mlp.down_proj",
+    "llm.model.layers.5.mlp.down_proj",
+    "llm.model.layers.3.self_attn.k_proj",
+    "llm.model.layers.4.self_attn.k_proj",
+    "llm.model.layers.14.self_attn.o_proj",
+    "llm.model.layers.23.self_attn.k_proj",
+    "llm.model.layers.7.self_attn.k_proj",
+    "llm.model.layers.6.mlp.gate_proj",
+    "llm.model.layers.19.self_attn.k_proj",
+    "llm.model.layers.12.self_attn.q_proj",
+    "llm.model.layers.21.mlp.down_proj",
+    "llm.model.layers.28.self_attn.v_proj",
+    "llm.model.layers.27.self_attn.v_proj",
+    "llm.model.layers.11.mlp.down_proj",
+    "region_extractor.rgb_projector",
+    "llm.model.layers.30.self_attn.q_proj",
+    "llm.model.layers.21.mlp.up_proj",
+    "llm.model.layers.7.self_attn.o_proj",
+    "llm.model.layers.29.self_attn.k_proj",
+    "llm.model.layers.8.self_attn.q_proj",
+    "llm.model.layers.28.self_attn.o_proj",
+    "llm.model.layers.27.self_attn.q_proj",
+    "llm.model.layers.22.mlp.gate_proj",
+    "llm.model.layers.22.self_attn.q_proj",
+    "llm.model.layers.14.mlp.gate_proj",
+    "llm.model.layers.25.self_attn.k_proj",
+    "llm.model.layers.28.mlp.gate_proj",
+    "llm.model.layers.15.self_attn.k_proj",
+    "llm.model.layers.2.mlp.down_proj",
+    "llm.model.layers.28.mlp.up_proj",
+    "llm.model.layers.8.mlp.gate_proj",
+    "llm.model.layers.7.mlp.down_proj",
+    "llm.model.layers.1.mlp.gate_proj",
+    "llm.model.layers.0.self_attn.o_proj",
+    "region_extractor.depth_projector",
+    "llm.model.layers.6.mlp.up_proj",
+    "llm.model.layers.5.self_attn.k_proj",
+    "llm.model.layers.17.self_attn.q_proj",
+    "llm.model.layers.27.self_attn.k_proj",
+    "llm.model.layers.31.mlp.down_proj",
+    "llm.model.layers.1.mlp.down_proj",
+    "llm.model.layers.4.mlp.up_proj",
+    "llm.model.layers.26.self_attn.q_proj",
+    "llm.model.layers.0.mlp.gate_proj",
+    "llm.model.layers.30.self_attn.v_proj",
+    "llm.model.layers.15.self_attn.q_proj",
+    "llm.model.layers.16.mlp.up_proj",
+    "llm.model.layers.14.self_attn.k_proj",
+    "llm.model.layers.16.self_attn.o_proj",
+    "llm.model.layers.0.mlp.up_proj",
+    "llm.model.layers.24.mlp.gate_proj",
+    "llm.model.layers.29.self_attn.q_proj",
+    "llm.model.layers.2.mlp.up_proj",
+    "llm.model.layers.21.self_attn.k_proj",
+    "llm.model.layers.4.self_attn.v_proj",
+    "llm.model.layers.28.self_attn.k_proj",
+    "llm.model.layers.18.mlp.up_proj",
+    "llm.model.layers.9.mlp.down_proj",
+    "llm.model.layers.16.mlp.gate_proj",
+    "llm.model.layers.23.mlp.up_proj",
+    "llm.model.layers.25.self_attn.q_proj",
+    "llm.model.layers.30.self_attn.k_proj",
+    "llm.model.layers.26.mlp.gate_proj",
+    "llm.model.layers.19.self_attn.v_proj",
+    "llm.model.layers.21.mlp.gate_proj",
+    "llm.model.layers.3.self_attn.o_proj",
+    "llm.model.layers.3.self_attn.v_proj",
+    "llm.model.layers.3.self_attn.q_proj",
+    "llm.model.layers.12.self_attn.v_proj",
+    "llm.model.layers.24.mlp.down_proj",
+    "llm.model.layers.1.self_attn.v_proj",
+    "llm.model.layers.9.mlp.gate_proj",
+    "llm.model.layers.17.self_attn.v_proj",
+    "llm.model.layers.14.mlp.up_proj",
+    "llm.model.layers.15.self_attn.v_proj",
+    "llm.model.layers.24.self_attn.q_proj",
+    "llm.model.layers.3.mlp.down_proj",
+    "llm.model.layers.2.self_attn.v_proj",
+    "llm.model.layers.16.mlp.down_proj",
+    "llm.model.layers.8.mlp.down_proj",
+    "llm.model.layers.5.self_attn.v_proj",
+    "llm.model.layers.10.self_attn.o_proj",
+    "llm.model.layers.29.mlp.gate_proj",
+    "llm.model.layers.24.mlp.up_proj",
+    "llm.model.layers.6.mlp.down_proj",
+    "llm.model.layers.9.self_attn.k_proj",
+    "llm.model.layers.0.self_attn.k_proj",
+    "llm.model.layers.13.self_attn.q_proj",
+    "llm.model.layers.25.self_attn.v_proj",
+    "llm.model.layers.20.mlp.down_proj",
+    "llm.model.layers.2.self_attn.q_proj",
+    "llm.model.layers.29.mlp.up_proj",
+    "llm.model.layers.16.self_attn.q_proj",
+    "llm.model.layers.10.self_attn.q_proj",
+    "llm.model.layers.1.self_attn.o_proj",
+    "llm.model.layers.8.self_attn.v_proj",
+    "llm.model.layers.20.self_attn.o_proj",
+    "llm.model.layers.11.self_attn.v_proj",
+    "llm.model.layers.7.mlp.gate_proj",
+    "llm.model.layers.15.mlp.down_proj",
+    "llm.model.layers.30.mlp.up_proj",
+    "llm.model.layers.24.self_attn.v_proj",
+    "llm.model.layers.26.self_attn.o_proj",
+    "llm.model.layers.14.self_attn.q_proj",
+    "llm.model.layers.11.self_attn.o_proj",
+    "llm.model.layers.29.self_attn.v_proj",
+    "llm.model.layers.10.self_attn.v_proj",
+    "llm.model.layers.18.mlp.gate_proj",
+    "llm.model.layers.8.mlp.up_proj",
+    "llm.model.layers.23.self_attn.q_proj",
+    "llm.model.layers.23.mlp.down_proj",
+    "llm.model.layers.31.self_attn.o_proj",
+    "llm.model.layers.13.mlp.up_proj",
+    "llm.model.layers.11.mlp.up_proj",
+    "llm.model.layers.7.mlp.up_proj",
+    "llm.model.layers.31.self_attn.k_proj",
+    "llm.model.layers.15.mlp.gate_proj",
+    "llm.model.layers.27.mlp.gate_proj",
+    "llm.model.layers.12.mlp.down_proj",
+    "llm.model.layers.6.self_attn.q_proj",
+    "llm.model.layers.25.self_attn.o_proj",
+    "llm.model.layers.11.mlp.gate_proj",
+    "llm.model.layers.24.self_attn.k_proj",
+    "llm.model.layers.19.mlp.gate_proj",
+    "llm.model.layers.5.mlp.gate_proj",
+    "llm.model.layers.22.mlp.down_proj",
+    "llm.model.layers.12.mlp.up_proj",
+    "llm.model.layers.18.self_attn.q_proj",
+    "llm.model.layers.5.mlp.up_proj",
+    "llm.model.layers.14.self_attn.v_proj",
+    "llm.model.layers.20.self_attn.q_proj",
+    "llm.model.layers.30.self_attn.o_proj",
+    "llm.model.layers.17.mlp.down_proj",
+    "llm.model.layers.10.mlp.gate_proj",
+    "llm.model.layers.30.mlp.down_proj",
+    "llm.model.layers.26.self_attn.v_proj",
+    "llm.model.layers.13.self_attn.k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881fd87ea2efbc494730285fd9f041504f1e768472a75afd4cbc1835a4d52f7c
+size 168506768

checkpoint-14985/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ''
+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 0.9.0

checkpoint-14985/adapter_config.json

@@ -0,0 +1,252 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "llm.model.layers.2.self_attn.k_proj",
+    "llm.model.layers.22.mlp.up_proj",
+    "llm.model.layers.9.self_attn.v_proj",
+    "llm.model.layers.17.self_attn.o_proj",
+    "llm.model.layers.21.self_attn.q_proj",
+    "llm.model.layers.17.self_attn.k_proj",
+    "llm.model.layers.15.mlp.up_proj",
+    "llm.model.layers.21.self_attn.o_proj",
+    "llm.model.layers.24.self_attn.o_proj",
+    "llm.model.layers.30.mlp.gate_proj",
+    "llm.model.layers.2.self_attn.o_proj",
+    "llm.model.layers.7.self_attn.v_proj",
+    "llm.model.layers.8.self_attn.k_proj",
+    "llm.model.layers.23.self_attn.o_proj",
+    "llm.model.layers.11.self_attn.q_proj",
+    "llm.model.layers.18.mlp.down_proj",
+    "llm.model.layers.1.self_attn.k_proj",
+    "llm.model.layers.26.self_attn.k_proj",
+    "llm.model.layers.19.mlp.up_proj",
+    "llm.model.layers.16.self_attn.v_proj",
+    "llm.model.layers.20.mlp.gate_proj",
+    "llm.model.layers.22.self_attn.o_proj",
+    "llm.model.layers.14.mlp.down_proj",
+    "llm.model.layers.0.self_attn.v_proj",
+    "llm.model.layers.18.self_attn.k_proj",
+    "llm.model.layers.6.self_attn.v_proj",
+    "llm.model.layers.12.mlp.gate_proj",
+    "llm.model.layers.5.self_attn.o_proj",
+    "llm.model.layers.0.mlp.down_proj",
+    "llm.model.layers.20.mlp.up_proj",
+    "llm.model.layers.31.mlp.up_proj",
+    "llm.model.layers.6.self_attn.k_proj",
+    "llm.model.layers.11.self_attn.k_proj",
+    "llm.model.layers.26.mlp.up_proj",
+    "llm.model.layers.0.self_attn.q_proj",
+    "llm.model.layers.9.self_attn.o_proj",
+    "llm.model.layers.3.mlp.up_proj",
+    "llm.model.layers.27.mlp.up_proj",
+    "llm.model.layers.18.self_attn.v_proj",
+    "llm.model.layers.28.self_attn.q_proj",
+    "llm.model.layers.4.mlp.gate_proj",
+    "llm.model.layers.1.self_attn.q_proj",
+    "llm.model.layers.17.mlp.gate_proj",
+    "llm.model.layers.31.self_attn.v_proj",
+    "llm.model.layers.18.self_attn.o_proj",
+    "llm.model.layers.20.self_attn.k_proj",
+    "llm.model.layers.10.mlp.down_proj",
+    "llm.model.layers.23.mlp.gate_proj",
+    "llm.model.layers.4.self_attn.o_proj",
+    "llm.model.layers.9.mlp.up_proj",
+    "llm.model.layers.17.mlp.up_proj",
+    "llm.model.layers.22.self_attn.v_proj",
+    "llm.model.layers.13.mlp.down_proj",
+    "llm.model.layers.31.mlp.gate_proj",
+    "llm.model.layers.21.self_attn.v_proj",
+    "llm.model.layers.12.self_attn.o_proj",
+    "llm.model.layers.9.self_attn.q_proj",
+    "llm.model.layers.15.self_attn.o_proj",
+    "llm.model.layers.25.mlp.up_proj",
+    "llm.model.layers.2.mlp.gate_proj",
+    "llm.model.layers.13.self_attn.o_proj",
+    "llm.model.layers.25.mlp.gate_proj",
+    "llm.model.layers.19.mlp.down_proj",
+    "llm.model.layers.20.self_attn.v_proj",
+    "llm.model.layers.31.self_attn.q_proj",
+    "llm.model.layers.19.self_attn.o_proj",
+    "llm.model.layers.10.self_attn.k_proj",
+    "llm.model.layers.23.self_attn.v_proj",
+    "llm.model.layers.6.self_attn.o_proj",
+    "llm.model.layers.27.mlp.down_proj",
+    "llm.model.layers.26.mlp.down_proj",
+    "llm.model.layers.4.self_attn.q_proj",
+    "llm.model.layers.5.self_attn.q_proj",
+    "llm.model.layers.10.mlp.up_proj",
+    "llm.model.layers.22.self_attn.k_proj",
+    "llm.model.layers.13.mlp.gate_proj",
+    "llm.model.layers.28.mlp.down_proj",
+    "llm.model.layers.29.mlp.down_proj",
+    "llm.model.layers.29.self_attn.o_proj",
+    "llm.model.layers.8.self_attn.o_proj",
+    "llm.model.layers.7.self_attn.q_proj",
+    "llm.model.layers.19.self_attn.q_proj",
+    "llm.model.layers.12.self_attn.k_proj",
+    "llm.model.layers.3.mlp.gate_proj",
+    "llm.model.layers.16.self_attn.k_proj",
+    "llm.model.layers.13.self_attn.v_proj",
+    "llm.model.layers.1.mlp.up_proj",
+    "llm.model.layers.27.self_attn.o_proj",
+    "llm.model.layers.4.mlp.down_proj",
+    "llm.model.layers.25.mlp.down_proj",
+    "llm.model.layers.5.mlp.down_proj",
+    "llm.model.layers.3.self_attn.k_proj",
+    "llm.model.layers.4.self_attn.k_proj",
+    "llm.model.layers.14.self_attn.o_proj",
+    "llm.model.layers.23.self_attn.k_proj",
+    "llm.model.layers.7.self_attn.k_proj",
+    "llm.model.layers.6.mlp.gate_proj",
+    "llm.model.layers.19.self_attn.k_proj",
+    "llm.model.layers.12.self_attn.q_proj",
+    "llm.model.layers.21.mlp.down_proj",
+    "llm.model.layers.28.self_attn.v_proj",
+    "llm.model.layers.27.self_attn.v_proj",
+    "llm.model.layers.11.mlp.down_proj",
+    "region_extractor.rgb_projector",
+    "llm.model.layers.30.self_attn.q_proj",
+    "llm.model.layers.21.mlp.up_proj",
+    "llm.model.layers.7.self_attn.o_proj",
+    "llm.model.layers.29.self_attn.k_proj",
+    "llm.model.layers.8.self_attn.q_proj",
+    "llm.model.layers.28.self_attn.o_proj",
+    "llm.model.layers.27.self_attn.q_proj",
+    "llm.model.layers.22.mlp.gate_proj",
+    "llm.model.layers.22.self_attn.q_proj",
+    "llm.model.layers.14.mlp.gate_proj",
+    "llm.model.layers.25.self_attn.k_proj",
+    "llm.model.layers.28.mlp.gate_proj",
+    "llm.model.layers.15.self_attn.k_proj",
+    "llm.model.layers.2.mlp.down_proj",
+    "llm.model.layers.28.mlp.up_proj",
+    "llm.model.layers.8.mlp.gate_proj",
+    "llm.model.layers.7.mlp.down_proj",
+    "llm.model.layers.1.mlp.gate_proj",
+    "llm.model.layers.0.self_attn.o_proj",
+    "region_extractor.depth_projector",
+    "llm.model.layers.6.mlp.up_proj",
+    "llm.model.layers.5.self_attn.k_proj",
+    "llm.model.layers.17.self_attn.q_proj",
+    "llm.model.layers.27.self_attn.k_proj",
+    "llm.model.layers.31.mlp.down_proj",
+    "llm.model.layers.1.mlp.down_proj",
+    "llm.model.layers.4.mlp.up_proj",
+    "llm.model.layers.26.self_attn.q_proj",
+    "llm.model.layers.0.mlp.gate_proj",
+    "llm.model.layers.30.self_attn.v_proj",
+    "llm.model.layers.15.self_attn.q_proj",
+    "llm.model.layers.16.mlp.up_proj",
+    "llm.model.layers.14.self_attn.k_proj",
+    "llm.model.layers.16.self_attn.o_proj",
+    "llm.model.layers.0.mlp.up_proj",
+    "llm.model.layers.24.mlp.gate_proj",
+    "llm.model.layers.29.self_attn.q_proj",
+    "llm.model.layers.2.mlp.up_proj",
+    "llm.model.layers.21.self_attn.k_proj",
+    "llm.model.layers.4.self_attn.v_proj",
+    "llm.model.layers.28.self_attn.k_proj",
+    "llm.model.layers.18.mlp.up_proj",
+    "llm.model.layers.9.mlp.down_proj",
+    "llm.model.layers.16.mlp.gate_proj",
+    "llm.model.layers.23.mlp.up_proj",
+    "llm.model.layers.25.self_attn.q_proj",
+    "llm.model.layers.30.self_attn.k_proj",
+    "llm.model.layers.26.mlp.gate_proj",
+    "llm.model.layers.19.self_attn.v_proj",
+    "llm.model.layers.21.mlp.gate_proj",
+    "llm.model.layers.3.self_attn.o_proj",
+    "llm.model.layers.3.self_attn.v_proj",
+    "llm.model.layers.3.self_attn.q_proj",
+    "llm.model.layers.12.self_attn.v_proj",
+    "llm.model.layers.24.mlp.down_proj",
+    "llm.model.layers.1.self_attn.v_proj",
+    "llm.model.layers.9.mlp.gate_proj",
+    "llm.model.layers.17.self_attn.v_proj",
+    "llm.model.layers.14.mlp.up_proj",
+    "llm.model.layers.15.self_attn.v_proj",
+    "llm.model.layers.24.self_attn.q_proj",
+    "llm.model.layers.3.mlp.down_proj",
+    "llm.model.layers.2.self_attn.v_proj",
+    "llm.model.layers.16.mlp.down_proj",
+    "llm.model.layers.8.mlp.down_proj",
+    "llm.model.layers.5.self_attn.v_proj",
+    "llm.model.layers.10.self_attn.o_proj",
+    "llm.model.layers.29.mlp.gate_proj",
+    "llm.model.layers.24.mlp.up_proj",
+    "llm.model.layers.6.mlp.down_proj",
+    "llm.model.layers.9.self_attn.k_proj",
+    "llm.model.layers.0.self_attn.k_proj",
+    "llm.model.layers.13.self_attn.q_proj",
+    "llm.model.layers.25.self_attn.v_proj",
+    "llm.model.layers.20.mlp.down_proj",
+    "llm.model.layers.2.self_attn.q_proj",
+    "llm.model.layers.29.mlp.up_proj",
+    "llm.model.layers.16.self_attn.q_proj",
+    "llm.model.layers.10.self_attn.q_proj",
+    "llm.model.layers.1.self_attn.o_proj",
+    "llm.model.layers.8.self_attn.v_proj",
+    "llm.model.layers.20.self_attn.o_proj",
+    "llm.model.layers.11.self_attn.v_proj",
+    "llm.model.layers.7.mlp.gate_proj",
+    "llm.model.layers.15.mlp.down_proj",
+    "llm.model.layers.30.mlp.up_proj",
+    "llm.model.layers.24.self_attn.v_proj",
+    "llm.model.layers.26.self_attn.o_proj",
+    "llm.model.layers.14.self_attn.q_proj",
+    "llm.model.layers.11.self_attn.o_proj",
+    "llm.model.layers.29.self_attn.v_proj",
+    "llm.model.layers.10.self_attn.v_proj",
+    "llm.model.layers.18.mlp.gate_proj",
+    "llm.model.layers.8.mlp.up_proj",
+    "llm.model.layers.23.self_attn.q_proj",
+    "llm.model.layers.23.mlp.down_proj",
+    "llm.model.layers.31.self_attn.o_proj",
+    "llm.model.layers.13.mlp.up_proj",
+    "llm.model.layers.11.mlp.up_proj",
+    "llm.model.layers.7.mlp.up_proj",
+    "llm.model.layers.31.self_attn.k_proj",
+    "llm.model.layers.15.mlp.gate_proj",
+    "llm.model.layers.27.mlp.gate_proj",
+    "llm.model.layers.12.mlp.down_proj",
+    "llm.model.layers.6.self_attn.q_proj",
+    "llm.model.layers.25.self_attn.o_proj",
+    "llm.model.layers.11.mlp.gate_proj",
+    "llm.model.layers.24.self_attn.k_proj",
+    "llm.model.layers.19.mlp.gate_proj",
+    "llm.model.layers.5.mlp.gate_proj",
+    "llm.model.layers.22.mlp.down_proj",
+    "llm.model.layers.12.mlp.up_proj",
+    "llm.model.layers.18.self_attn.q_proj",
+    "llm.model.layers.5.mlp.up_proj",
+    "llm.model.layers.14.self_attn.v_proj",
+    "llm.model.layers.20.self_attn.q_proj",
+    "llm.model.layers.30.self_attn.o_proj",
+    "llm.model.layers.17.mlp.down_proj",
+    "llm.model.layers.10.mlp.gate_proj",
+    "llm.model.layers.30.mlp.down_proj",
+    "llm.model.layers.26.self_attn.v_proj",
+    "llm.model.layers.13.self_attn.k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-14985/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1aef50c2ad42c863339a84e0298b5563b0204308a01209cdf2feb5fc4c840a
+size 168506768

checkpoint-14985/global_step14985/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f058a9ba6ed7c3bc0fbebbc9e0921332ef62d8861cea8ed8cdee9b39591aa8c6
+size 1438748336

checkpoint-14985/global_step14985/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:687127868baffafeb2e6f11b2eac86bd9686801238c6a4fb1b31db40632c5711
+size 13217124518

checkpoint-14985/latest

@@ -0,0 +1 @@
+global_step14985

checkpoint-14985/non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1cd99dd954a185936134534dbed8b9d6c1897e80ffd62097ba78bfda2aadc0
+size 71340800

checkpoint-14985/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243afa74317471681b96048372def099149905a5ee634b86dca7aa9c9e78becb
+size 14244

checkpoint-14985/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc0b6bc2b0a2d06697575b3dc0b1fc981eac40da760fc92c1ac8632729acfbfa
+size 1064

checkpoint-14985/zero_to_fp32.py

@@ -0,0 +1,578 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage == 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dicts.append(torch.load(f, map_location=device))
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage == 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage == 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage == 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file)

config.json

@@ -0,0 +1,325 @@
+{
+  "_name_or_path": "./checkpoints/SpatialRGPT-VILA1.5-8B-SFT-SpatialWarehouse",
+  "architectures": [
+    "LlavaLlamaModel"
+  ],
+  "drop_path_rate": 0.0,
+  "enable_depth": true,
+  "enable_region": true,
+  "fps": 0.0,
+  "hidden_size": 4096,
+  "image_aspect_ratio": "resize",
+  "interpolate_mode": "linear",
+  "llm_cfg": {
+    "_name_or_path": "./checkpoints/SpatialRGPT-VILA1.5-8B/llm",
+    "add_cross_attention": false,
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 128000,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 128009,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 8192,
+    "min_length": 0,
+    "model_max_length": 4096,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 500000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "tokenizer_model_max_length": 4096,
+    "tokenizer_padding_side": "right",
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 128259
+  },
+  "mm_hidden_size": 1152,
+  "mm_projector_cfg": {
+    "_name_or_path": "./checkpoints/SpatialRGPT-VILA1.5-8B/mm_projector",
+    "add_cross_attention": false,
+    "architectures": [
+      "MultimodalProjector"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mm_projector_type": "mlp_downsample",
+    "model_type": "v2l_projector",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "mm_projector_lr": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "cls_patch",
+  "mm_vision_select_layer": -2,
+  "model_dtype": "torch.bfloat16",
+  "model_type": "llava_llama",
+  "num_video_frames": 8,
+  "region_extractor_cfg": {
+    "_name_or_path": "./checkpoints/SpatialRGPT-VILA1.5-8B/region_extractor",
+    "add_cross_attention": false,
+    "architectures": [
+      "RegionExtractor"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "region_extractor",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "region_extractor_type": "regiongpt",
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "resume_path": "./checkpoints/SpatialRGPT-VILA1.5-8B-SFT-SpatialWarehouse",
+  "s2": false,
+  "s2_max_split_size": 336,
+  "s2_scales": "336,672,1008",
+  "transformers_version": "4.37.2",
+  "tune_language_model": false,
+  "tune_mm_projector": true,
+  "tune_region_extractor": true,
+  "tune_vision_tower": false,
+  "vision_resolution": -1,
+  "vision_tower_cfg": {
+    "_name_or_path": "./checkpoints/SpatialRGPT-VILA1.5-8B/vision_tower",
+    "add_cross_attention": false,
+    "architectures": [
+      "SiglipVisionModel"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 384,
+    "intermediate_size": 4304,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "llm_depth_token_id": 128258,
+    "llm_mask_token_id": 128257,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "siglip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135dd02104f0989ebcea265bef6786dd5c6f441f0d153a7686adee132ec2f69e
+size 71340800