Upload LoRA adapter (pcagent-7B-human-only)

.gitattributes

@@ -33,3 +33,7 @@ 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
+checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1388/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+tags:
+- base_model:adapter:Qwen/Qwen2.5-VL-7B-Instruct
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: pcagent-7B-human-only
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# pcagent-7B-human-only
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) on the pc-agent-e-action-only dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.05
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 5.2.0
+- Pytorch 2.5.1+cu124
+- Datasets 4.0.0
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,127 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.9.mlp.up_proj",
+    "layers.26.mlp.gate_proj",
+    "layers.11.mlp.gate_proj",
+    "layers.7.mlp.gate_proj",
+    "layers.5.mlp.up_proj",
+    "layers.11.mlp.down_proj",
+    "layers.22.mlp.down_proj",
+    "layers.15.mlp.down_proj",
+    "layers.4.mlp.gate_proj",
+    "layers.18.mlp.gate_proj",
+    "layers.3.mlp.gate_proj",
+    "layers.22.mlp.up_proj",
+    "layers.14.mlp.gate_proj",
+    "layers.15.mlp.up_proj",
+    "layers.27.mlp.up_proj",
+    "layers.19.mlp.up_proj",
+    "layers.13.mlp.down_proj",
+    "layers.13.mlp.up_proj",
+    "layers.17.mlp.up_proj",
+    "layers.2.mlp.down_proj",
+    "layers.27.mlp.down_proj",
+    "layers.8.mlp.gate_proj",
+    "layers.0.mlp.gate_proj",
+    "layers.3.mlp.down_proj",
+    "layers.5.mlp.gate_proj",
+    "layers.4.mlp.up_proj",
+    "layers.23.mlp.up_proj",
+    "layers.10.mlp.gate_proj",
+    "layers.25.mlp.up_proj",
+    "layers.18.mlp.down_proj",
+    "layers.25.mlp.gate_proj",
+    "layers.24.mlp.down_proj",
+    "layers.16.mlp.up_proj",
+    "layers.16.mlp.down_proj",
+    "layers.11.mlp.up_proj",
+    "layers.6.mlp.gate_proj",
+    "layers.26.mlp.up_proj",
+    "layers.20.mlp.down_proj",
+    "layers.12.mlp.up_proj",
+    "layers.24.mlp.gate_proj",
+    "k_proj",
+    "layers.21.mlp.down_proj",
+    "layers.13.mlp.gate_proj",
+    "layers.20.mlp.up_proj",
+    "layers.18.mlp.up_proj",
+    "layers.9.mlp.gate_proj",
+    "layers.15.mlp.gate_proj",
+    "layers.27.mlp.gate_proj",
+    "layers.6.mlp.up_proj",
+    "layers.7.mlp.down_proj",
+    "layers.23.mlp.gate_proj",
+    "q_proj",
+    "layers.22.mlp.gate_proj",
+    "layers.26.mlp.down_proj",
+    "layers.17.mlp.gate_proj",
+    "layers.1.mlp.down_proj",
+    "layers.12.mlp.gate_proj",
+    "layers.17.mlp.down_proj",
+    "layers.7.mlp.up_proj",
+    "layers.19.mlp.gate_proj",
+    "layers.3.mlp.up_proj",
+    "layers.0.mlp.up_proj",
+    "layers.19.mlp.down_proj",
+    "layers.8.mlp.up_proj",
+    "o_proj",
+    "layers.5.mlp.down_proj",
+    "layers.23.mlp.down_proj",
+    "layers.25.mlp.down_proj",
+    "layers.0.mlp.down_proj",
+    "layers.1.mlp.up_proj",
+    "layers.10.mlp.down_proj",
+    "layers.1.mlp.gate_proj",
+    "layers.16.mlp.gate_proj",
+    "v_proj",
+    "layers.2.mlp.up_proj",
+    "layers.6.mlp.down_proj",
+    "layers.14.mlp.down_proj",
+    "layers.9.mlp.down_proj",
+    "layers.20.mlp.gate_proj",
+    "layers.10.mlp.up_proj",
+    "layers.4.mlp.down_proj",
+    "layers.21.mlp.up_proj",
+    "layers.14.mlp.up_proj",
+    "layers.8.mlp.down_proj",
+    "layers.24.mlp.up_proj",
+    "layers.2.mlp.gate_proj",
+    "layers.21.mlp.gate_proj",
+    "layers.12.mlp.down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99989965bee7500af2705e7939be60be62bf4fb6710d0482710af7a07a4e0e5e
+size 645981584

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.0037139745307361e+18,
+    "train_loss": 0.7883986402571374,
+    "train_runtime": 11184.8694,
+    "train_samples_per_second": 0.496,
+    "train_steps_per_second": 0.124
+}

chat_template.jinja

@@ -0,0 +1,7 @@
+{% 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
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

checkpoint-1200/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-VL-7B-Instruct
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoint-1200/adapter_config.json

@@ -0,0 +1,127 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.9.mlp.up_proj",
+    "layers.26.mlp.gate_proj",
+    "layers.11.mlp.gate_proj",
+    "layers.7.mlp.gate_proj",
+    "layers.5.mlp.up_proj",
+    "layers.11.mlp.down_proj",
+    "layers.22.mlp.down_proj",
+    "layers.15.mlp.down_proj",
+    "layers.4.mlp.gate_proj",
+    "layers.18.mlp.gate_proj",
+    "layers.3.mlp.gate_proj",
+    "layers.22.mlp.up_proj",
+    "layers.14.mlp.gate_proj",
+    "layers.15.mlp.up_proj",
+    "layers.27.mlp.up_proj",
+    "layers.19.mlp.up_proj",
+    "layers.13.mlp.down_proj",
+    "layers.13.mlp.up_proj",
+    "layers.17.mlp.up_proj",
+    "layers.2.mlp.down_proj",
+    "layers.27.mlp.down_proj",
+    "layers.8.mlp.gate_proj",
+    "layers.0.mlp.gate_proj",
+    "layers.3.mlp.down_proj",
+    "layers.5.mlp.gate_proj",
+    "layers.4.mlp.up_proj",
+    "layers.23.mlp.up_proj",
+    "layers.10.mlp.gate_proj",
+    "layers.25.mlp.up_proj",
+    "layers.18.mlp.down_proj",
+    "layers.25.mlp.gate_proj",
+    "layers.24.mlp.down_proj",
+    "layers.16.mlp.up_proj",
+    "layers.16.mlp.down_proj",
+    "layers.11.mlp.up_proj",
+    "layers.6.mlp.gate_proj",
+    "layers.26.mlp.up_proj",
+    "layers.20.mlp.down_proj",
+    "layers.12.mlp.up_proj",
+    "layers.24.mlp.gate_proj",
+    "k_proj",
+    "layers.21.mlp.down_proj",
+    "layers.13.mlp.gate_proj",
+    "layers.20.mlp.up_proj",
+    "layers.18.mlp.up_proj",
+    "layers.9.mlp.gate_proj",
+    "layers.15.mlp.gate_proj",
+    "layers.27.mlp.gate_proj",
+    "layers.6.mlp.up_proj",
+    "layers.7.mlp.down_proj",
+    "layers.23.mlp.gate_proj",
+    "q_proj",
+    "layers.22.mlp.gate_proj",
+    "layers.26.mlp.down_proj",
+    "layers.17.mlp.gate_proj",
+    "layers.1.mlp.down_proj",
+    "layers.12.mlp.gate_proj",
+    "layers.17.mlp.down_proj",
+    "layers.7.mlp.up_proj",
+    "layers.19.mlp.gate_proj",
+    "layers.3.mlp.up_proj",
+    "layers.0.mlp.up_proj",
+    "layers.19.mlp.down_proj",
+    "layers.8.mlp.up_proj",
+    "o_proj",
+    "layers.5.mlp.down_proj",
+    "layers.23.mlp.down_proj",
+    "layers.25.mlp.down_proj",
+    "layers.0.mlp.down_proj",
+    "layers.1.mlp.up_proj",
+    "layers.10.mlp.down_proj",
+    "layers.1.mlp.gate_proj",
+    "layers.16.mlp.gate_proj",
+    "v_proj",
+    "layers.2.mlp.up_proj",
+    "layers.6.mlp.down_proj",
+    "layers.14.mlp.down_proj",
+    "layers.9.mlp.down_proj",
+    "layers.20.mlp.gate_proj",
+    "layers.10.mlp.up_proj",
+    "layers.4.mlp.down_proj",
+    "layers.21.mlp.up_proj",
+    "layers.14.mlp.up_proj",
+    "layers.8.mlp.down_proj",
+    "layers.24.mlp.up_proj",
+    "layers.2.mlp.gate_proj",
+    "layers.21.mlp.gate_proj",
+    "layers.12.mlp.down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a873fda14e72a55e5f4eef70eb98c5a405940c1ab76a814093857de19849a0
+size 645981584

checkpoint-1200/chat_template.jinja

@@ -0,0 +1,7 @@
+{% 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
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c736d925f7766dd032404c01d99b673514e0df167feae1d13333c757ba1893ae
+size 1292176234

checkpoint-1200/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2_5_VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen2VLVideoProcessor"
+  }
+}

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858f7fc09bee30a3a299d5b07c5dd77679a9b77dd1c96241862056644d3072de
+size 14244

checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ec3fd9d2b3b9072c219f368074730e1e3f64dfe773b44380754ae0a56bc1ab
+size 1064

checkpoint-1200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-1200/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0742392223bf62bf3e233a68f09ba267cf039dfafb723ee8590bd8f637eaecfb
+size 5176

checkpoint-1300/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-VL-7B-Instruct
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoint-1300/adapter_config.json

@@ -0,0 +1,127 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.9.mlp.up_proj",
+    "layers.26.mlp.gate_proj",
+    "layers.11.mlp.gate_proj",
+    "layers.7.mlp.gate_proj",
+    "layers.5.mlp.up_proj",
+    "layers.11.mlp.down_proj",
+    "layers.22.mlp.down_proj",
+    "layers.15.mlp.down_proj",
+    "layers.4.mlp.gate_proj",
+    "layers.18.mlp.gate_proj",
+    "layers.3.mlp.gate_proj",
+    "layers.22.mlp.up_proj",
+    "layers.14.mlp.gate_proj",
+    "layers.15.mlp.up_proj",
+    "layers.27.mlp.up_proj",
+    "layers.19.mlp.up_proj",
+    "layers.13.mlp.down_proj",
+    "layers.13.mlp.up_proj",
+    "layers.17.mlp.up_proj",
+    "layers.2.mlp.down_proj",
+    "layers.27.mlp.down_proj",
+    "layers.8.mlp.gate_proj",
+    "layers.0.mlp.gate_proj",
+    "layers.3.mlp.down_proj",
+    "layers.5.mlp.gate_proj",
+    "layers.4.mlp.up_proj",
+    "layers.23.mlp.up_proj",
+    "layers.10.mlp.gate_proj",
+    "layers.25.mlp.up_proj",
+    "layers.18.mlp.down_proj",
+    "layers.25.mlp.gate_proj",
+    "layers.24.mlp.down_proj",
+    "layers.16.mlp.up_proj",
+    "layers.16.mlp.down_proj",
+    "layers.11.mlp.up_proj",
+    "layers.6.mlp.gate_proj",
+    "layers.26.mlp.up_proj",
+    "layers.20.mlp.down_proj",
+    "layers.12.mlp.up_proj",
+    "layers.24.mlp.gate_proj",
+    "k_proj",
+    "layers.21.mlp.down_proj",
+    "layers.13.mlp.gate_proj",
+    "layers.20.mlp.up_proj",
+    "layers.18.mlp.up_proj",
+    "layers.9.mlp.gate_proj",
+    "layers.15.mlp.gate_proj",
+    "layers.27.mlp.gate_proj",
+    "layers.6.mlp.up_proj",
+    "layers.7.mlp.down_proj",
+    "layers.23.mlp.gate_proj",
+    "q_proj",
+    "layers.22.mlp.gate_proj",
+    "layers.26.mlp.down_proj",
+    "layers.17.mlp.gate_proj",
+    "layers.1.mlp.down_proj",
+    "layers.12.mlp.gate_proj",
+    "layers.17.mlp.down_proj",
+    "layers.7.mlp.up_proj",
+    "layers.19.mlp.gate_proj",
+    "layers.3.mlp.up_proj",
+    "layers.0.mlp.up_proj",
+    "layers.19.mlp.down_proj",
+    "layers.8.mlp.up_proj",
+    "o_proj",
+    "layers.5.mlp.down_proj",
+    "layers.23.mlp.down_proj",
+    "layers.25.mlp.down_proj",
+    "layers.0.mlp.down_proj",
+    "layers.1.mlp.up_proj",
+    "layers.10.mlp.down_proj",
+    "layers.1.mlp.gate_proj",
+    "layers.16.mlp.gate_proj",
+    "v_proj",
+    "layers.2.mlp.up_proj",
+    "layers.6.mlp.down_proj",
+    "layers.14.mlp.down_proj",
+    "layers.9.mlp.down_proj",
+    "layers.20.mlp.gate_proj",
+    "layers.10.mlp.up_proj",
+    "layers.4.mlp.down_proj",
+    "layers.21.mlp.up_proj",
+    "layers.14.mlp.up_proj",
+    "layers.8.mlp.down_proj",
+    "layers.24.mlp.up_proj",
+    "layers.2.mlp.gate_proj",
+    "layers.21.mlp.gate_proj",
+    "layers.12.mlp.down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a12b670909e8ec91a552773e057b4cabcc87df8325bcca39e4eb6a5f44c6a0a6
+size 645981584

checkpoint-1300/chat_template.jinja

@@ -0,0 +1,7 @@
+{% 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
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

checkpoint-1300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907d3e0ce1338d0dd38466f7ba09b5d32dde5e768728cdbc2d8142c5752d3be3
+size 1292176234

checkpoint-1300/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2_5_VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen2VLVideoProcessor"
+  }
+}

checkpoint-1300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c007b8c46529bfec9c1720caae32f726e24c0c9428547874d516118c380b527
+size 14244

checkpoint-1300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3f4add932db57be28cf66f8035b1efa01988674b5e2de2f653ded19a9b35e4
+size 1064

checkpoint-1300/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-1300/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0742392223bf62bf3e233a68f09ba267cf039dfafb723ee8590bd8f637eaecfb
+size 5176

checkpoint-1388/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-VL-7B-Instruct
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoint-1388/adapter_config.json

@@ -0,0 +1,127 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.9.mlp.up_proj",
+    "layers.26.mlp.gate_proj",
+    "layers.11.mlp.gate_proj",
+    "layers.7.mlp.gate_proj",
+    "layers.5.mlp.up_proj",
+    "layers.11.mlp.down_proj",
+    "layers.22.mlp.down_proj",
+    "layers.15.mlp.down_proj",
+    "layers.4.mlp.gate_proj",
+    "layers.18.mlp.gate_proj",
+    "layers.3.mlp.gate_proj",
+    "layers.22.mlp.up_proj",
+    "layers.14.mlp.gate_proj",
+    "layers.15.mlp.up_proj",
+    "layers.27.mlp.up_proj",
+    "layers.19.mlp.up_proj",
+    "layers.13.mlp.down_proj",
+    "layers.13.mlp.up_proj",
+    "layers.17.mlp.up_proj",
+    "layers.2.mlp.down_proj",
+    "layers.27.mlp.down_proj",
+    "layers.8.mlp.gate_proj",
+    "layers.0.mlp.gate_proj",
+    "layers.3.mlp.down_proj",
+    "layers.5.mlp.gate_proj",
+    "layers.4.mlp.up_proj",
+    "layers.23.mlp.up_proj",
+    "layers.10.mlp.gate_proj",
+    "layers.25.mlp.up_proj",
+    "layers.18.mlp.down_proj",
+    "layers.25.mlp.gate_proj",
+    "layers.24.mlp.down_proj",
+    "layers.16.mlp.up_proj",
+    "layers.16.mlp.down_proj",
+    "layers.11.mlp.up_proj",
+    "layers.6.mlp.gate_proj",
+    "layers.26.mlp.up_proj",
+    "layers.20.mlp.down_proj",
+    "layers.12.mlp.up_proj",
+    "layers.24.mlp.gate_proj",
+    "k_proj",
+    "layers.21.mlp.down_proj",
+    "layers.13.mlp.gate_proj",
+    "layers.20.mlp.up_proj",
+    "layers.18.mlp.up_proj",
+    "layers.9.mlp.gate_proj",
+    "layers.15.mlp.gate_proj",
+    "layers.27.mlp.gate_proj",
+    "layers.6.mlp.up_proj",
+    "layers.7.mlp.down_proj",
+    "layers.23.mlp.gate_proj",
+    "q_proj",
+    "layers.22.mlp.gate_proj",
+    "layers.26.mlp.down_proj",
+    "layers.17.mlp.gate_proj",
+    "layers.1.mlp.down_proj",
+    "layers.12.mlp.gate_proj",
+    "layers.17.mlp.down_proj",
+    "layers.7.mlp.up_proj",
+    "layers.19.mlp.gate_proj",
+    "layers.3.mlp.up_proj",
+    "layers.0.mlp.up_proj",
+    "layers.19.mlp.down_proj",
+    "layers.8.mlp.up_proj",
+    "o_proj",
+    "layers.5.mlp.down_proj",
+    "layers.23.mlp.down_proj",
+    "layers.25.mlp.down_proj",
+    "layers.0.mlp.down_proj",
+    "layers.1.mlp.up_proj",
+    "layers.10.mlp.down_proj",
+    "layers.1.mlp.gate_proj",
+    "layers.16.mlp.gate_proj",
+    "v_proj",
+    "layers.2.mlp.up_proj",
+    "layers.6.mlp.down_proj",
+    "layers.14.mlp.down_proj",
+    "layers.9.mlp.down_proj",
+    "layers.20.mlp.gate_proj",
+    "layers.10.mlp.up_proj",
+    "layers.4.mlp.down_proj",
+    "layers.21.mlp.up_proj",
+    "layers.14.mlp.up_proj",
+    "layers.8.mlp.down_proj",
+    "layers.24.mlp.up_proj",
+    "layers.2.mlp.gate_proj",
+    "layers.21.mlp.gate_proj",
+    "layers.12.mlp.down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1388/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99989965bee7500af2705e7939be60be62bf4fb6710d0482710af7a07a4e0e5e
+size 645981584

checkpoint-1388/chat_template.jinja

@@ -0,0 +1,7 @@
+{% 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
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

checkpoint-1388/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d1e94b9fd6c0ecaf7f0f316b014008e63f23d40fb2401c1bf7cb4bd870665c
+size 1292176234

checkpoint-1388/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2_5_VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen2VLVideoProcessor"
+  }
+}

checkpoint-1388/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde47c12c783fddaab2b60f8d617e42db9837ed7a3e6232b98d4fb5d313414d3
+size 14244

checkpoint-1388/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d21a998ea052e5537e9308629e2889dd950e4bc958983b7ef5ef4692756deff2
+size 1064

checkpoint-1388/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-1388/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1388/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0742392223bf62bf3e233a68f09ba267cf039dfafb723ee8590bd8f637eaecfb
+size 5176

processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2_5_VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen2VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.0037139745307361e+18,
+    "train_loss": 0.7883986402571374,
+    "train_runtime": 11184.8694,
+    "train_samples_per_second": 0.496,
+    "train_steps_per_second": 0.124
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0742392223bf62bf3e233a68f09ba267cf039dfafb723ee8590bd8f637eaecfb
+size 5176