fix: save folders

app.py

@@ -9,7 +9,7 @@ from src.serve.gradio_block_arena_vision_named import build_side_by_side_vision_
 def main():
     with gr.Blocks() as demo:
         states = build_side_by_side_vision_ui_named(
-            models=["llava-fire", "llava-original"]
+            models=["llava-fire"]
         )
         
         demo.launch()

checkpoints/llava-next-llama-3-8b-student-lora-merged-117408/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Lin-Chen/open-llava-next-llama3-8b
+---
+
+# 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 0.11.1

checkpoints/llava-next-llama-3-8b-student-lora-merged-117408/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Lin-Chen/open-llava-next-llama3-8b",
+  "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": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoints/llava-next-llama-3-8b-student-lora-merged-117408/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9899e6e864b5024e8011428340942cf741b1115b540e58967eab416e4315ee
+size 94424168

checkpoints/llava-next-llama-3-8b-student-lora-merged-117408/config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "Lin-Chen/open-llava-next-llama3-8b",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "anyres",
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "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,
+  "pad_token_id": 128256,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 3072,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "unfreeze_mm_vision_tower": true,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 128257
+}

checkpoints/llava-next-llama-3-8b-student-lora-merged-117408/non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c48db83bde59cb090bae9905ea45e13a73f9bfc653a3208dc511435d416fe895
+size 41961648

requirements.txt

@@ -2,7 +2,8 @@ git+https://github.com/MM-FIRE/FIRE@main#egg=llava
 aiohttp
 httpx
 numpy<2
-peft
+peft==0.11.1
+accelerate==0.21.0
 sentencepiece
 protobuf
 loguru

src/model/model_llava.py

@@ -16,6 +16,9 @@ import base64
 from src.utils import (
     build_logger,
 )
+import os
+os.makedirs("save_folder1", exist_ok=True)
+os.makedirs("save_folder2", exist_ok=True)
 
 logger = build_logger("model_llava", "model_llava.log")
 def load_llava_model(lora_checkpoint=None):
@@ -26,19 +29,20 @@ def load_llava_model(lora_checkpoint=None):
     device_map = "auto"
     if lora_checkpoint is None:
         tokenizer, model, image_processor, max_length = load_pretrained_model(
-            model_path, None, model_name, device_map=device_map) # Add any other thing you want to pass in llava_model_args
+            model_path, None, model_name, device_map=device_map, offload_folder="save_folder1") # Add any other thing you want to pass in llava_model_args
     else:
+        #tokenizer, model, image_processor, max_length = load_pretrained_model(
+        #    lora_checkpoint, model_path, "llava_lora", device_map=device_map, offload_folder="save_folder2")
         tokenizer, model, image_processor, max_length = load_pretrained_model(
-            lora_checkpoint, model_path, "llava_lora", device_map=device_map)
-
+            "li-qing/llava-llama-3-8b-fire-1m", None, "llava", device_map=device_map, offload_folder="save_folder2")
     model.eval()
     model.tie_weights()
     logger.info(f"model device {model.device}")
     return tokenizer, model, image_processor, conv_template
 
 tokenizer_llava, model_llava, image_processor_llava, conv_template_llava = load_llava_model(None)
-tokenizer_llava_fire, model_llava_fire, image_processor_llava_fire, conv_template_llava = load_llava_model("checkpoints/llava-next-llama-3-8b-student-lora-merged-115124")
-model_llava_fire.to("cuda")
+tokenizer_llava_fire, model_llava_fire, image_processor_llava_fire, conv_template_llava = load_llava_model("checkpoints/llava-next-llama-3-8b-student-lora-merged-117408")
+# model_llava_fire.to("cuda")
 
 @spaces.GPU
 def inference():