Upload model checkpoint

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+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 0.13.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+ "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": 16,
+ "lora_dropout": 0.05,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 8,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "v_proj",
+ "q_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 sha256:4d247b49b26539fe582c67ff09004815a571a464eb5fd2bb00e7e11c4ccc763a
+size 10107280

added_tokens.json

@@ -0,0 +1,16 @@
+{
+ "<|box_end|>": 151649,
+ "<|box_start|>": 151648,
+ "<|endoftext|>": 151643,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644,
+ "<|image_pad|>": 151655,
+ "<|object_ref_end|>": 151647,
+ "<|object_ref_start|>": 151646,
+ "<|quad_end|>": 151651,
+ "<|quad_start|>": 151650,
+ "<|video_pad|>": 151656,
+ "<|vision_end|>": 151653,
+ "<|vision_pad|>": 151654,
+ "<|vision_start|>": 151652
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7151715c23fe43b913ce051c875676177b7ccfe84e9ddb0cd52d0ad3845b2175
+size 20280890

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e056b4799a47fcb03d95e8e1d42330f35016f0006ac726dcfd45e2e3ea6eb23c
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d829a2c582255f48447ae34872c1e125d881beba555f88fc957c4c789c4b7e5
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151646": {
+ "content": "<|object_ref_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|object_ref_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151648": {
+ "content": "<|box_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151649": {
+ "content": "<|box_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>",
+ "<|object_ref_start|>",
+ "<|object_ref_end|>",
+ "<|box_start|>",
+ "<|box_end|>",
+ "<|quad_start|>",
+ "<|quad_end|>",
+ "<|vision_start|>",
+ "<|vision_end|>",
+ "<|vision_pad|>",
+ "<|image_pad|>",
+ "<|video_pad|>"
+ ],
+ "bos_token": null,
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "model_max_length": 32768,
+ "pad_token": "<|endoftext|>",
+ "padding_side": "left",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,208 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 2.991097922848665,
+ "eval_steps": 500,
+ "global_step": 126,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.11869436201780416,
+ "grad_norm": 0.6501234173774719,
+ "learning_rate": 0.0002,
+ "loss": 2.5793,
+ "step": 5
+ },
+ {
+ "epoch": 0.23738872403560832,
+ "grad_norm": 0.9226903915405273,
+ "learning_rate": 0.0002,
+ "loss": 2.2797,
+ "step": 10
+ },
+ {
+ "epoch": 0.3560830860534125,
+ "grad_norm": 1.3594255447387695,
+ "learning_rate": 0.0002,
+ "loss": 1.8775,
+ "step": 15
+ },
+ {
+ "epoch": 0.47477744807121663,
+ "grad_norm": 1.391525149345398,
+ "learning_rate": 0.0002,
+ "loss": 1.4896,
+ "step": 20
+ },
+ {
+ "epoch": 0.5934718100890207,
+ "grad_norm": 0.9402475357055664,
+ "learning_rate": 0.0002,
+ "loss": 1.2145,
+ "step": 25
+ },
+ {
+ "epoch": 0.712166172106825,
+ "grad_norm": 0.516862690448761,
+ "learning_rate": 0.0002,
+ "loss": 1.0708,
+ "step": 30
+ },
+ {
+ "epoch": 0.8308605341246291,
+ "grad_norm": 0.39975354075431824,
+ "learning_rate": 0.0002,
+ "loss": 0.9909,
+ "step": 35
+ },
+ {
+ "epoch": 0.9495548961424333,
+ "grad_norm": 0.4522175192832947,
+ "learning_rate": 0.0002,
+ "loss": 0.9651,
+ "step": 40
+ },
+ {
+ "epoch": 1.0682492581602374,
+ "grad_norm": 0.4957733452320099,
+ "learning_rate": 0.0002,
+ "loss": 0.9213,
+ "step": 45
+ },
+ {
+ "epoch": 1.1869436201780414,
+ "grad_norm": 0.45304545760154724,
+ "learning_rate": 0.0002,
+ "loss": 0.9047,
+ "step": 50
+ },
+ {
+ "epoch": 1.3056379821958457,
+ "grad_norm": 0.6747499108314514,
+ "learning_rate": 0.0002,
+ "loss": 0.8819,
+ "step": 55
+ },
+ {
+ "epoch": 1.4243323442136497,
+ "grad_norm": 0.7882275581359863,
+ "learning_rate": 0.0002,
+ "loss": 0.8359,
+ "step": 60
+ },
+ {
+ "epoch": 1.543026706231454,
+ "grad_norm": 0.42021647095680237,
+ "learning_rate": 0.0002,
+ "loss": 0.8254,
+ "step": 65
+ },
+ {
+ "epoch": 1.6617210682492582,
+ "grad_norm": 0.41371551156044006,
+ "learning_rate": 0.0002,
+ "loss": 0.7991,
+ "step": 70
+ },
+ {
+ "epoch": 1.7804154302670623,
+ "grad_norm": 0.45561087131500244,
+ "learning_rate": 0.0002,
+ "loss": 0.7887,
+ "step": 75
+ },
+ {
+ "epoch": 1.8991097922848663,
+ "grad_norm": 0.40611913800239563,
+ "learning_rate": 0.0002,
+ "loss": 0.7941,
+ "step": 80
+ },
+ {
+ "epoch": 2.0178041543026706,
+ "grad_norm": 0.5473902225494385,
+ "learning_rate": 0.0002,
+ "loss": 0.7779,
+ "step": 85
+ },
+ {
+ "epoch": 2.136498516320475,
+ "grad_norm": 0.4852384924888611,
+ "learning_rate": 0.0002,
+ "loss": 0.7517,
+ "step": 90
+ },
+ {
+ "epoch": 2.255192878338279,
+ "grad_norm": 0.4257807731628418,
+ "learning_rate": 0.0002,
+ "loss": 0.7545,
+ "step": 95
+ },
+ {
+ "epoch": 2.373887240356083,
+ "grad_norm": 0.4694693386554718,
+ "learning_rate": 0.0002,
+ "loss": 0.7389,
+ "step": 100
+ },
+ {
+ "epoch": 2.492581602373887,
+ "grad_norm": 0.46692556142807007,
+ "learning_rate": 0.0002,
+ "loss": 0.7348,
+ "step": 105
+ },
+ {
+ "epoch": 2.6112759643916914,
+ "grad_norm": 0.38663822412490845,
+ "learning_rate": 0.0002,
+ "loss": 0.7368,
+ "step": 110
+ },
+ {
+ "epoch": 2.7299703264094957,
+ "grad_norm": 0.4077226519584656,
+ "learning_rate": 0.0002,
+ "loss": 0.7335,
+ "step": 115
+ },
+ {
+ "epoch": 2.8486646884272995,
+ "grad_norm": 0.4740726351737976,
+ "learning_rate": 0.0002,
+ "loss": 0.7462,
+ "step": 120
+ },
+ {
+ "epoch": 2.9673590504451037,
+ "grad_norm": 0.40621665120124817,
+ "learning_rate": 0.0002,
+ "loss": 0.75,
+ "step": 125
+ }
+ ],
+ "logging_steps": 5,
+ "max_steps": 126,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 3,
+ "save_steps": 500,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": true
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 9.310063237541069e+16,
+ "train_batch_size": 4,
+ "trial_name": null,
+ "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a5f1f972f58590aa872779280e63e266abc2de596650b6ae36c0c8029df3ce
+size 5560