feat: depend

checkpoints/llava-next-llama-3-8b-student-lora-merged-115124/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-115124/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-115124/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42b42ed4f8f216c6e1a20fede923656c1eb6f22752fa732f1c624b1c7e14d44
+size 94424168

checkpoints/llava-next-llama-3-8b-student-lora-merged-115124/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": 3192,
+  "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-115124/non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd5b0389306ba247fb26f3661c4cc7a0445ef5def1554e94c9462ac366c7debe
+size 41961648

requirements.txt

@@ -5,4 +5,5 @@ numpy<2
 peft
 sentencepiece
 protobuf
-loguru
+loguru
+gradio==4.29.0

src/model/model_llava.py

@@ -2,7 +2,6 @@ from llava.model.builder import load_pretrained_model
 from llava.mm_utils import get_model_name_from_path, process_images, tokenizer_image_token
 from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN
 from llava.conversation import conv_templates
-from loguru import logger
 
 from PIL import Image
 import requests
@@ -14,10 +13,14 @@ from io import BytesIO
 import base64
 #model_path = "/scratch/TecManDep/A_Models/llava-v1.6-vicuna-7b"
 #conv_template = "vicuna_v1" # Make sure you use correct chat template for different models
+from src.utils import (
+    build_logger,
+)
 
+logger = build_logger("model_llava", "model_llava.log")
 def load_llava_model(lora_checkpoint=None):
     model_path =  "Lin-Chen/open-llava-next-llama3-8b"
-    conv_template = "llama_v3"
+    conv_template = "llama_v3_student"
     model_name = get_model_name_from_path(model_path)
     device = "cuda"
     device_map = "auto"
@@ -30,12 +33,13 @@ def load_llava_model(lora_checkpoint=None):
 
     model.eval()
     model.tie_weights()
-    logger.info("model device {}", model.device)
+    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-110224")
+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")
+
 @spaces.GPU
 def inference():
     image = Image.open("assets/example.jpg").convert("RGB")
@@ -79,7 +83,7 @@ def inference_by_prompt_and_images(prompt, images):
     image_tensor = image_tensor.to(dtype=torch.float16, device=device)
     input_ids = tokenizer_image_token(prompt, tokenizer_llava, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(device)
     image_sizes = [image.size for image in images]
-    logger.info("Shape: {};{}; Devices: {};{}",input_ids.shape, image_tensor.shape, input_ids.device, image_tensor.device)
+    logger.info(f"Shape: {input_ids.shape};{image_tensor.shape}; Devices: {input_ids.device};{image_tensor.device}")
     with torch.inference_mode():
         cont = model_llava.generate(
             input_ids,
@@ -91,7 +95,7 @@ def inference_by_prompt_and_images(prompt, images):
             use_cache=True
         )
     text_outputs = tokenizer_llava.batch_decode(cont, skip_special_tokens=True)
-    logger.info("response={}", text_outputs)
+    
     return text_outputs
 
 @spaces.GPU
@@ -106,7 +110,7 @@ def inference_by_prompt_and_images_fire(prompt, images):
     image_tensor = image_tensor.to(dtype=torch.float16, device=device)
     input_ids = tokenizer_image_token(prompt, tokenizer_llava_fire, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(device)
     image_sizes = [image.size for image in images]
-    logger.info("Shape: {};{}; Devices: {};{}",input_ids.shape, image_tensor.shape, input_ids.device, image_tensor.device)
+    logger.info(f"Shape: {input_ids.shape};{image_tensor.shape}; Devices: {input_ids.device};{image_tensor.device}")
     with torch.inference_mode():
         cont = model_llava_fire.generate(
             input_ids,
@@ -118,7 +122,7 @@ def inference_by_prompt_and_images_fire(prompt, images):
             use_cache=True
         )
     text_outputs = tokenizer_llava_fire.batch_decode(cont, skip_special_tokens=True)
-    logger.info("response={}", text_outputs)
+    logger.info(f"response={text_outputs}")
     return text_outputs
 
 if __name__ == "__main__":

vision-tmp-2024-07-23-conv.json

@@ -0,0 +1,8 @@
+{"tstamp": 1721701705.7909, "type": "chat", "model": "llava-fire", "gen_params": {"temperature": 0.7, "top_p": 1.0, "max_new_tokens": 1024}, "start": 1721701640.609, "finish": 1721701705.7909, "state": {"template_name": "llava-fire", "system_message": "You are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.", "roles": ["user", "assistant"], "messages": [["user", ["What species of flower could these be, and what is their common name?", ["ec3f8c5d6190cc6027d31e8726d168ac"]]], ["assistant", "Based on the image alone, without additional context or botanical expertise, it is not possible to accurately determine the species of the flower or its common name. However, the bright yellow petals and prominent orange centers are characteristic of many species within the Asteraceae family, which includes daisies, sunflowers, and chrysanthemums, among others."]], "offset": 0, "conv_id": "13109662cd74483eb27c8945c9f51643", "model_name": "llava-fire", "has_csam_image": false}, "ip": "46.3.240.104"}
+{"tstamp": 1721701705.7978, "type": "chat", "model": "llava-original", "gen_params": {"temperature": 0.7, "top_p": 1.0, "max_new_tokens": 1024}, "start": 1721701666.99, "finish": 1721701705.7978, "state": {"template_name": "llava-original", "system_message": "You are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.", "roles": ["user", "assistant"], "messages": [["user", ["What species of flower could these be, and what is their common name?", ["ec3f8c5d6190cc6027d31e8726d168ac"]]], ["assistant", "Based on the image alone, these flowers could be identified as a species of the genus Solidago, commonly known as goldenrods. Goldenrods are known for their dense, terminal inflorescences and are often found in fields and meadows. The specific species would require a closer examination of the flower's structure and habitat, which is not possible from the image alone."]], "offset": 0, "conv_id": "183137bc666b4d618a12df0d024b7ebc", "model_name": "llava-original", "has_csam_image": false}, "ip": "46.3.240.104"}
+{"tstamp": 1721701824.6996, "type": "chat", "model": "llava-fire", "gen_params": {"temperature": 0.7, "top_p": 1.0, "max_new_tokens": 1024}, "start": 1721701725.1572, "finish": 1721701824.6996, "state": {"template_name": "llava-fire", "system_message": "You are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.", "roles": ["user", "assistant"], "messages": [["user", ["What species of flower could these be, and what is their common name?", ["ec3f8c5d6190cc6027d31e8726d168ac"]]], ["assistant", "Based on the image alone, without additional context or botanical expertise, it is not possible to accurately determine the species of the flower or its common name. However, the bright yellow petals and prominent orange centers are characteristic of many species within the Asteraceae family, which includes daisies, sunflowers, and chrysanthemums, among others."], ["user", "Your answer correctly identifies the vibrant yellow petals and central disc, which are key features of the flowers in the image. However, the flowers in the image are not daisies. Daisies typically have a single large flower per stem, whereas these flowers have multiple blooms per stem. Additionally, the shape of the petals and the arrangement of the flowers are more characteristic of a different species. Try to focus on the overall structure and arrangement of the flowers to refine your identification."], ["assistant", "Thank you for the feedback. The flowers in the image do not resemble daisies, which typically have a single large flower per stem. Instead, the dense arrangement of multiple small flowers per stem, along with the vibrant yellow petals and prominent orange centers, are more characteristic of a species within the genus Solidago, commonly known as goldenrods. These flowers are known for their dense, terminal inflorescences and are often found in fields and meadows."]], "offset": 0, "conv_id": "13109662cd74483eb27c8945c9f51643", "model_name": "llava-fire", "has_csam_image": false}, "ip": "46.3.240.104"}
+{"tstamp": 1721701824.7049, "type": "chat", "model": "llava-original", "gen_params": {"temperature": 0.7, "top_p": 1.0, "max_new_tokens": 1024}, "start": 1721701805.5319, "finish": 1721701824.7049, "state": {"template_name": "llava-original", "system_message": "You are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.", "roles": ["user", "assistant"], "messages": [["user", ["What species of flower could these be, and what is their common name?", ["ec3f8c5d6190cc6027d31e8726d168ac"]]], ["assistant", "Based on the image alone, these flowers could be identified as a species of the genus Solidago, commonly known as goldenrods. Goldenrods are known for their dense, terminal inflorescences and are often found in fields and meadows. The specific species would require a closer examination of the flower's structure and habitat, which is not possible from the image alone."], ["user", "Your answer correctly identifies the vibrant yellow petals and central disc, which are key features of the flowers in the image. However, the flowers in the image are not daisies. Daisies typically have a single large flower per stem, whereas these flowers have multiple blooms per stem. Additionally, the shape of the petals and the arrangement of the flowers are more characteristic of a different species. Try to focus on the overall structure and arrangement of the flowers to refine your identification."], ["assistant", "I apologize for the initial misidentification. Upon closer inspection, the flowers in the image are indeed not daisies but rather a species of the genus Solidago, commonly known as goldenrods. Goldenrods are known for their dense, terminal inflorescences and are often found in fields and meadows. The specific species would require a closer examination of the flower's structure and habitat, which is not possible from the image alone."]], "offset": 0, "conv_id": "183137bc666b4d618a12df0d024b7ebc", "model_name": "llava-original", "has_csam_image": false}, "ip": "46.3.240.104"}
+{"tstamp": 1721703498.4406, "type": "chat", "model": "llava-fire", "gen_params": {"temperature": 0.7, "top_p": 1.0, "max_new_tokens": 1024}, "start": 1721703462.5858, "finish": 1721703498.4406, "state": {"template_name": "llava-fire", "system_message": "You are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.", "roles": ["user", "assistant"], "messages": [["user", ["What species of flower could these be, and what is their common name?", ["ec3f8c5d6190cc6027d31e8726d168ac"]]], ["assistant", "Based on the image alone, without additional context or botanical expertise, it is not possible to accurately determine the species of the flower or its common name. However, the bright yellow petals and prominent orange centers are characteristic of many species within the Asteraceae family, which includes daisies, sunflowers, and chrysanthemums, among others."]], "offset": 0, "conv_id": "653fc4e74bf74cc4aa104e4e6ea87393", "model_name": "llava-fire", "has_csam_image": false}, "ip": "46.3.240.104"}
+{"tstamp": 1721703498.4472, "type": "chat", "model": "llava-original", "gen_params": {"temperature": 0.7, "top_p": 1.0, "max_new_tokens": 1024}, "start": 1721703480.6019, "finish": 1721703498.4472, "state": {"template_name": "llava-original", "system_message": "You are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.", "roles": ["user", "assistant"], "messages": [["user", ["What species of flower could these be, and what is their common name?", ["ec3f8c5d6190cc6027d31e8726d168ac"]]], ["assistant", "Based on the image alone, these flowers could be identified as a species of the genus Solidago, commonly known as goldenrods. Goldenrods are known for their dense, terminal inflorescences and are often found in fields and meadows. The specific species would require a closer examination of the flower's structure and habitat, which is not possible from the image alone."]], "offset": 0, "conv_id": "5ea6e4d5082c4b78bf81a670a1093ae0", "model_name": "llava-original", "has_csam_image": false}, "ip": "46.3.240.104"}
+{"tstamp": 1721703602.0029, "type": "chat", "model": "llava-fire", "gen_params": {"temperature": 0.7, "top_p": 1.0, "max_new_tokens": 1024}, "start": 1721703564.2737, "finish": 1721703602.0029, "state": {"template_name": "llava-fire", "system_message": "You are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.", "roles": ["user", "assistant"], "messages": [["user", ["What species of flower could these be, and what is their common name?", ["ec3f8c5d6190cc6027d31e8726d168ac"]]], ["assistant", "Based on the image alone, without additional context or botanical expertise, it is not possible to accurately determine the species of the flower or its common name. However, the bright yellow petals and prominent orange centers are characteristic of many species within the Asteraceae family, which includes daisies, sunflowers, and chrysanthemums, among others."], ["user", "Your answer correctly identifies the vibrant yellow petals and central disc, which are key features of the flowers in the image. However, the flowers in the image are not daisies. Daisies typically have a single large flower per stem, whereas these flowers have multiple blooms per stem. Additionally, the shape of the petals and the arrangement of the flowers are more characteristic of a different species. Try to focus on the overall structure and arrangement of the flowers to refine your identification."], ["assistant", "Thank you for the feedback. The flowers in the image do not resemble daisies, which typically have a single large flower per stem. Instead, the dense arrangement of multiple small flowers per stem, along with the vibrant yellow petals and prominent orange centers, are more characteristic of a species within the genus Solidago, commonly known as goldenrods. These flowers are known for their dense, terminal inflorescences and are often found in fields and meadows."]], "offset": 0, "conv_id": "653fc4e74bf74cc4aa104e4e6ea87393", "model_name": "llava-fire", "has_csam_image": false}, "ip": "46.3.240.104"}
+{"tstamp": 1721703602.0063, "type": "chat", "model": "llava-original", "gen_params": {"temperature": 0.7, "top_p": 1.0, "max_new_tokens": 1024}, "start": 1721703583.9252, "finish": 1721703602.0063, "state": {"template_name": "llava-original", "system_message": "You are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.", "roles": ["user", "assistant"], "messages": [["user", ["What species of flower could these be, and what is their common name?", ["ec3f8c5d6190cc6027d31e8726d168ac"]]], ["assistant", "Based on the image alone, these flowers could be identified as a species of the genus Solidago, commonly known as goldenrods. Goldenrods are known for their dense, terminal inflorescences and are often found in fields and meadows. The specific species would require a closer examination of the flower's structure and habitat, which is not possible from the image alone."], ["user", "Your answer correctly identifies the vibrant yellow petals and central disc, which are key features of the flowers in the image. However, the flowers in the image are not daisies. Daisies typically have a single large flower per stem, whereas these flowers have multiple blooms per stem. Additionally, the shape of the petals and the arrangement of the flowers are more characteristic of a different species. Try to focus on the overall structure and arrangement of the flowers to refine your identification."], ["assistant", "I apologize for the initial misidentification. Upon closer inspection, the flowers in the image are indeed not daisies but rather a species of the genus Solidago, commonly known as goldenrods. Goldenrods are known for their dense, terminal inflorescences and are often found in fields and meadows. The specific species would require a closer examination of the flower's structure and habitat, which is not possible from the image alone."]], "offset": 0, "conv_id": "5ea6e4d5082c4b78bf81a670a1093ae0", "model_name": "llava-original", "has_csam_image": false}, "ip": "46.3.240.104"}