Merge branch 'main' of https://huggingface.co/spaces/li-qing/FIRE

checkpoints/{adapter_model.safetensors → llava-next-llama-3-8b-student-lora-merged-110224/adapter_model.safetensors}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bde4f7416f433196d4d85fa32ed21531e55ea24848cf92e1c532afc8e418acd
+oid sha256:b80ac0467df0c61c94d95b60189f68c54f4dfb97c40fbbaa3f82905736fb2fd4
 size 67143744

checkpoints/{non_lora_trainables.bin → llava-next-llama-3-8b-student-lora-merged-110224/non_lora_trainables.bin}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29889b2750a9b71f3137df8a9515038c58131a21638ac55cb8e0d487e6110065
+oid sha256:feefff1c747c9a282d8c702b927f2256d4ac64e590efdc5e7c44650290f26a50
 size 41961648

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

checkpoints/llava-next-llama-3-8b-teacher-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-teacher-lora-merged-115124/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "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"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3190200c1b6b0e91e3d29bb523ebd26152b9fb8156a031b830c48c1a3c07f0be
+size 67143744

checkpoints/llava-next-llama-3-8b-teacher-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": 4096,
+  "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-teacher-lora-merged-115124/non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3676f1bea77732bc7833861067fd95232efb962269f935a2c6179e19489cceb8
+size 41961648

requirements.txt

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

src/conversation.py

@@ -165,10 +165,10 @@ class Conversation:
                 ret += ""
             for i, (role, message) in enumerate(self.messages):
                 if message:
-                    logger.info("msg={}", message)
+                    logger.info("msg = {}", message)
                     if type(message) is tuple:
                         message, images = message
-                        message = "<image>" * len(images) + message
+                        message = "<image>" * len(images) + "\n" + message
                     ret += f"<|start_header_id|>{role}<|end_header_id|>\n\n"
                     ret += f"{message.strip()}<|eot_id|>"
                 else:

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/")
+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")
@@ -67,7 +71,7 @@ def inference():
     return text_outputs
 
 
-@spaces.GPU
+@spaces.GPU(duration=25)
 def inference_by_prompt_and_images(prompt, images):
     device = "cuda"
     if len(images) > 0 and type(images[0]) is str:
@@ -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,
@@ -91,10 +95,10 @@ 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
+@spaces.GPU(duration=25)
 def inference_by_prompt_and_images_fire(prompt, images):
     device = "cuda"
     if len(images) > 0 and type(images[0]) is str:
@@ -102,23 +106,23 @@ def inference_by_prompt_and_images_fire(prompt, images):
         for image in images:
             image_data.append(Image.open(BytesIO(base64.b64decode(image))))
         images = image_data
-    image_tensor = process_images(images, image_processor_llava, model_llava.config)
+    image_tensor = process_images(images, image_processor_llava_fire, model_llava_fire.config)
     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)
+    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,
-            images=image_tensor,
+            images=[image_tensor.squeeze(dim=0)],
             image_sizes=image_sizes,
             do_sample=False,
             temperature=0,
             max_new_tokens=256,
             use_cache=True
         )
-    text_outputs = tokenizer_llava.batch_decode(cont, skip_special_tokens=True)
-    logger.info("response={}", text_outputs)
+    text_outputs = tokenizer_llava_fire.batch_decode(cont, skip_special_tokens=True)
+    logger.info(f"response={text_outputs}")
     return text_outputs
 
 if __name__ == "__main__":

src/model/model_registry.py

@@ -22,10 +22,14 @@ def get_model_info(name: str) -> ModelInfo:
     if name in ['llava-fire', 'llava-original']:
         description = {
             "llava-fire": "LLaVA fine-tuned from FIRE dataset",
-            "llava-original": "LLaVA-NeXT with LLaMA-3-8B as language decoder"
+            "llava-original": "LLaVA-NeXT with LLaMA-3-8B as the language decoder"
+        }
+        model_names = {
+            "llava-fire": "FIRE-LLaVA",
+            "llava-original": "LLaVA-NeXT-LLaMA-3-8B"
         }
         return ModelInfo(
-            name, "", description[name]
+            model_names[name], "", description[name]
         )
     if name in model_info:
         return model_info[name]