Upload 6 files

README.md

@@ -1,3 +1,202 @@
----
-license: cc-by-4.0
----
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.6-mistral-7b
+---
+
+# 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 0.10.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.6-mistral-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_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 sha256:0a835791b30e5094a12dfc29ea44d3337de72194e2ee6dafd789cddae4cdc3a9
+size 708923528

config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "liuhaotian/llava-v1.6-mistral-7b",
+  "architectures": [
+    "LlavaMistralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "image_crop_resolution": 224,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_split_resolution": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "mm_vision_tower_lr": 2e-06,
+  "model_type": "llava_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": true,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60fb82c3660319e6d0b239950b20c28181e97f1ade117dc0660b40e2ad94a89b
+size 912

trainer_state.json

@@ -0,0 +1,504 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 79,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.563,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3043,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2e-05,
+      "loss": 1.2638,
+      "step": 3
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.999145758387301e-05,
+      "loss": 1.3178,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.99658449300667e-05,
+      "loss": 0.9881,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.992320579737045e-05,
+      "loss": 0.9734,
+      "step": 6
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9863613034027224e-05,
+      "loss": 1.0088,
+      "step": 7
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9787168453273546e-05,
+      "loss": 0.996,
+      "step": 8
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9694002659393306e-05,
+      "loss": 0.8973,
+      "step": 9
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.958427482458253e-05,
+      "loss": 0.9568,
+      "step": 10
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9458172417006347e-05,
+      "loss": 0.9458,
+      "step": 11
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9315910880512792e-05,
+      "loss": 0.9379,
+      "step": 12
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9157733266550577e-05,
+      "loss": 0.9296,
+      "step": 13
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.898390981891979e-05,
+      "loss": 0.8659,
+      "step": 14
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.879473751206489e-05,
+      "loss": 0.876,
+      "step": 15
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8590539543698852e-05,
+      "loss": 0.8748,
+      "step": 16
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8371664782625287e-05,
+      "loss": 0.9528,
+      "step": 17
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.813848717270195e-05,
+      "loss": 0.9572,
+      "step": 18
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.789140509396394e-05,
+      "loss": 0.903,
+      "step": 19
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7630840681998068e-05,
+      "loss": 0.8989,
+      "step": 20
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.735723910673132e-05,
+      "loss": 0.8918,
+      "step": 21
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.8911,
+      "step": 22
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6772815716257414e-05,
+      "loss": 0.9015,
+      "step": 23
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.646299237860941e-05,
+      "loss": 0.8788,
+      "step": 24
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6142127126896682e-05,
+      "loss": 0.8929,
+      "step": 25
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5810768154019386e-05,
+      "loss": 0.9049,
+      "step": 26
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5469481581224274e-05,
+      "loss": 0.8985,
+      "step": 27
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5118850490896012e-05,
+      "loss": 0.9353,
+      "step": 28
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4759473930370738e-05,
+      "loss": 0.8249,
+      "step": 29
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4391965888473705e-05,
+      "loss": 0.8426,
+      "step": 30
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4016954246529697e-05,
+      "loss": 0.8492,
+      "step": 31
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3635079705638298e-05,
+      "loss": 0.8952,
+      "step": 32
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3246994692046837e-05,
+      "loss": 0.8821,
+      "step": 33
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2853362242491054e-05,
+      "loss": 0.8758,
+      "step": 34
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2454854871407993e-05,
+      "loss": 0.8224,
+      "step": 35
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.2052153421956343e-05,
+      "loss": 0.8758,
+      "step": 36
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.164594590280734e-05,
+      "loss": 0.8689,
+      "step": 37
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.123692631269348e-05,
+      "loss": 0.7884,
+      "step": 38
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0825793454723325e-05,
+      "loss": 0.8356,
+      "step": 39
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0413249742488132e-05,
+      "loss": 0.8492,
+      "step": 40
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.9018,
+      "step": 41
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.586750257511868e-06,
+      "loss": 0.8776,
+      "step": 42
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.174206545276678e-06,
+      "loss": 0.8249,
+      "step": 43
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.763073687306523e-06,
+      "loss": 0.9175,
+      "step": 44
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.35405409719266e-06,
+      "loss": 0.8375,
+      "step": 45
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.947846578043658e-06,
+      "loss": 0.9021,
+      "step": 46
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.545145128592009e-06,
+      "loss": 0.8291,
+      "step": 47
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.14663775750895e-06,
+      "loss": 0.8727,
+      "step": 48
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.7530053079531664e-06,
+      "loss": 0.8673,
+      "step": 49
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.364920294361701e-06,
+      "loss": 0.8716,
+      "step": 50
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.983045753470308e-06,
+      "loss": 0.8658,
+      "step": 51
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.608034111526298e-06,
+      "loss": 0.8199,
+      "step": 52
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.240526069629265e-06,
+      "loss": 0.9193,
+      "step": 53
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.881149509103993e-06,
+      "loss": 0.7906,
+      "step": 54
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.530518418775734e-06,
+      "loss": 0.8785,
+      "step": 55
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.189231845980618e-06,
+      "loss": 0.8281,
+      "step": 56
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.857872873103322e-06,
+      "loss": 0.8772,
+      "step": 57
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5370076213905904e-06,
+      "loss": 0.8723,
+      "step": 58
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.2271842837425917e-06,
+      "loss": 0.8242,
+      "step": 59
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.8723,
+      "step": 60
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.642760893268684e-06,
+      "loss": 0.8294,
+      "step": 61
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.369159318001937e-06,
+      "loss": 0.8132,
+      "step": 62
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.1085949060360654e-06,
+      "loss": 0.9158,
+      "step": 63
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.861512827298051e-06,
+      "loss": 0.8152,
+      "step": 64
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6283352173747148e-06,
+      "loss": 0.8172,
+      "step": 65
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.409460456301147e-06,
+      "loss": 0.8718,
+      "step": 66
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2052624879351105e-06,
+      "loss": 0.8251,
+      "step": 67
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0160901810802114e-06,
+      "loss": 0.8401,
+      "step": 68
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.42266733449425e-07,
+      "loss": 0.8318,
+      "step": 69
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.840891194872112e-07,
+      "loss": 0.8563,
+      "step": 70
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.418275829936537e-07,
+      "loss": 0.87,
+      "step": 71
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.1572517541747294e-07,
+      "loss": 0.8736,
+      "step": 72
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.059973406066963e-07,
+      "loss": 0.837,
+      "step": 73
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.1283154672645522e-07,
+      "loss": 0.8477,
+      "step": 74
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3638696597277678e-07,
+      "loss": 0.8302,
+      "step": 75
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.679420262954984e-08,
+      "loss": 0.8606,
+      "step": 76
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.4155069933301535e-08,
+      "loss": 0.904,
+      "step": 77
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 8.542416126989805e-09,
+      "loss": 0.8027,
+      "step": 78
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.8881,
+      "step": 79
+    },
+    {
+      "epoch": 1.0,
+      "step": 79,
+      "total_flos": 2.0832241753627034e+17,
+      "train_loss": 0.9012186353719687,
+      "train_runtime": 1256.0083,
+      "train_samples_per_second": 3.981,
+      "train_steps_per_second": 0.063
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 79,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 2.0832241753627034e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}