Upload CambrianQwenForCausalLM

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 +1,81 @@
+{
+  "_name_or_path": "/data/cambrian-u/ckpt/20251009_instruction-tune_60k_128_1_5b_diffloss_1_dit0_5b_cfg0_1_context1024_ep64_bs64_lr5_66e-5-last",
+  "architectures": [
+    "CambrianQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "aux_regression": false,
+  "aux_regression_coef": 1.0,
+  "bos_token_id": 151643,
+  "connector_only": true,
+  "ddt_encoder_depth": 2,
+  "diff_head_lr": 0.000566,
+  "diffusion_base_dim": null,
+  "diffusion_class_dropout_prob": 0.1,
+  "diffusion_model_channels": 1152,
+  "diffusion_model_depth": 16,
+  "diffusion_model_heads": 32,
+  "diffusion_model_hidden_size": 1280,
+  "diffusion_model_z_channels": 1280,
+  "diffusion_norm_stats_path": null,
+  "diffusion_split_per_token": 256,
+  "diffusion_timesteps_per_sample": 1,
+  "eos_token_id": 151645,
+  "freeze_mm_mlp_adapter": false,
+  "generation_alignment_tower": null,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_aspect_ratio": "square",
+  "image_position": 35,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "miv_token_len": 0,
+  "mm_hidden_size": 1152,
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": true,
+  "mm_vision_sampler_lr": null,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
+  "mm_vision_tower_aux_list": [
+    "google/siglip2-so400m-patch14-224"
+  ],
+  "mm_vision_tower_aux_token_len_list": [
+    256
+  ],
+  "mm_vision_tower_lr": 2e-06,
+  "model_type": "cambrian_qwen",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "patch_size": 2,
+  "pretrain_adapter_and_vision_head": null,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "si_token_len": 729,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 1024,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0",
+  "tune_adapter_and_vision_head": false,
+  "tune_mm_mlp_adapter": false,
+  "tune_vision_head": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_sliding_window": false,
+  "vision_coef": 2.0,
+  "vision_hidden_size": 1152,
+  "vision_loss": "diffusion-loss",
+  "vision_loss_mode": "query",
+  "vision_tower_aux_token_len_list": [
+    256
+  ],
+  "vocab_size": 151667
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.37.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc22943cb322cda5d2a702f9bad7d98cc128494a0ba27d7941312d62c824470
+size 4061876056