Upload folder using huggingface_hub
Browse files- harvard_lora-qrefVqa/README.md +203 -0
- harvard_lora-qrefVqa/adapter_config.json +34 -0
- harvard_lora-qrefVqa/adapter_model.safetensors +3 -0
- harvard_lora-qrefVqa/config.json +52 -0
- harvard_lora-qrefVqa/non_lora_trainables.bin +3 -0
- harvard_lora-qrefVqa/trainer_state.json +0 -0
- mimic_lora-qrefVqa/README.md +203 -0
- mimic_lora-qrefVqa/adapter_config.json +34 -0
- mimic_lora-qrefVqa/adapter_model.safetensors +3 -0
- mimic_lora-qrefVqa/config.json +52 -0
- mimic_lora-qrefVqa/non_lora_trainables.bin +3 -0
- mimic_lora-qrefVqa/trainer_state.json +0 -0
harvard_lora-qrefVqa/README.md
ADDED
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
# base_model: /home/wenhao/Project/intern/xiapeng/rein/LLaVA-Med/checkpoint/llava-med-v1.5-mistral-7b
|
4 |
+
base_model: microsoft/llava-med-v1.5-mistral-7b
|
5 |
+
---
|
6 |
+
|
7 |
+
# Model Card for Model ID
|
8 |
+
|
9 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
10 |
+
|
11 |
+
|
12 |
+
|
13 |
+
## Model Details
|
14 |
+
|
15 |
+
### Model Description
|
16 |
+
|
17 |
+
<!-- Provide a longer summary of what this model is. -->
|
18 |
+
|
19 |
+
|
20 |
+
|
21 |
+
- **Developed by:** [More Information Needed]
|
22 |
+
- **Funded by [optional]:** [More Information Needed]
|
23 |
+
- **Shared by [optional]:** [More Information Needed]
|
24 |
+
- **Model type:** [More Information Needed]
|
25 |
+
- **Language(s) (NLP):** [More Information Needed]
|
26 |
+
- **License:** [More Information Needed]
|
27 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
28 |
+
|
29 |
+
### Model Sources [optional]
|
30 |
+
|
31 |
+
<!-- Provide the basic links for the model. -->
|
32 |
+
|
33 |
+
- **Repository:** [More Information Needed]
|
34 |
+
- **Paper [optional]:** [More Information Needed]
|
35 |
+
- **Demo [optional]:** [More Information Needed]
|
36 |
+
|
37 |
+
## Uses
|
38 |
+
|
39 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
40 |
+
|
41 |
+
### Direct Use
|
42 |
+
|
43 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
44 |
+
|
45 |
+
[More Information Needed]
|
46 |
+
|
47 |
+
### Downstream Use [optional]
|
48 |
+
|
49 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
50 |
+
|
51 |
+
[More Information Needed]
|
52 |
+
|
53 |
+
### Out-of-Scope Use
|
54 |
+
|
55 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
56 |
+
|
57 |
+
[More Information Needed]
|
58 |
+
|
59 |
+
## Bias, Risks, and Limitations
|
60 |
+
|
61 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
62 |
+
|
63 |
+
[More Information Needed]
|
64 |
+
|
65 |
+
### Recommendations
|
66 |
+
|
67 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
68 |
+
|
69 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
70 |
+
|
71 |
+
## How to Get Started with the Model
|
72 |
+
|
73 |
+
Use the code below to get started with the model.
|
74 |
+
|
75 |
+
[More Information Needed]
|
76 |
+
|
77 |
+
## Training Details
|
78 |
+
|
79 |
+
### Training Data
|
80 |
+
|
81 |
+
<!-- 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. -->
|
82 |
+
|
83 |
+
[More Information Needed]
|
84 |
+
|
85 |
+
### Training Procedure
|
86 |
+
|
87 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
88 |
+
|
89 |
+
#### Preprocessing [optional]
|
90 |
+
|
91 |
+
[More Information Needed]
|
92 |
+
|
93 |
+
|
94 |
+
#### Training Hyperparameters
|
95 |
+
|
96 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
97 |
+
|
98 |
+
#### Speeds, Sizes, Times [optional]
|
99 |
+
|
100 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
101 |
+
|
102 |
+
[More Information Needed]
|
103 |
+
|
104 |
+
## Evaluation
|
105 |
+
|
106 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
107 |
+
|
108 |
+
### Testing Data, Factors & Metrics
|
109 |
+
|
110 |
+
#### Testing Data
|
111 |
+
|
112 |
+
<!-- This should link to a Dataset Card if possible. -->
|
113 |
+
|
114 |
+
[More Information Needed]
|
115 |
+
|
116 |
+
#### Factors
|
117 |
+
|
118 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
119 |
+
|
120 |
+
[More Information Needed]
|
121 |
+
|
122 |
+
#### Metrics
|
123 |
+
|
124 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
125 |
+
|
126 |
+
[More Information Needed]
|
127 |
+
|
128 |
+
### Results
|
129 |
+
|
130 |
+
[More Information Needed]
|
131 |
+
|
132 |
+
#### Summary
|
133 |
+
|
134 |
+
|
135 |
+
|
136 |
+
## Model Examination [optional]
|
137 |
+
|
138 |
+
<!-- Relevant interpretability work for the model goes here -->
|
139 |
+
|
140 |
+
[More Information Needed]
|
141 |
+
|
142 |
+
## Environmental Impact
|
143 |
+
|
144 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
145 |
+
|
146 |
+
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).
|
147 |
+
|
148 |
+
- **Hardware Type:** [More Information Needed]
|
149 |
+
- **Hours used:** [More Information Needed]
|
150 |
+
- **Cloud Provider:** [More Information Needed]
|
151 |
+
- **Compute Region:** [More Information Needed]
|
152 |
+
- **Carbon Emitted:** [More Information Needed]
|
153 |
+
|
154 |
+
## Technical Specifications [optional]
|
155 |
+
|
156 |
+
### Model Architecture and Objective
|
157 |
+
|
158 |
+
[More Information Needed]
|
159 |
+
|
160 |
+
### Compute Infrastructure
|
161 |
+
|
162 |
+
[More Information Needed]
|
163 |
+
|
164 |
+
#### Hardware
|
165 |
+
|
166 |
+
[More Information Needed]
|
167 |
+
|
168 |
+
#### Software
|
169 |
+
|
170 |
+
[More Information Needed]
|
171 |
+
|
172 |
+
## Citation [optional]
|
173 |
+
|
174 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
175 |
+
|
176 |
+
**BibTeX:**
|
177 |
+
|
178 |
+
[More Information Needed]
|
179 |
+
|
180 |
+
**APA:**
|
181 |
+
|
182 |
+
[More Information Needed]
|
183 |
+
|
184 |
+
## Glossary [optional]
|
185 |
+
|
186 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
187 |
+
|
188 |
+
[More Information Needed]
|
189 |
+
|
190 |
+
## More Information [optional]
|
191 |
+
|
192 |
+
[More Information Needed]
|
193 |
+
|
194 |
+
## Model Card Authors [optional]
|
195 |
+
|
196 |
+
[More Information Needed]
|
197 |
+
|
198 |
+
## Model Card Contact
|
199 |
+
|
200 |
+
[More Information Needed]
|
201 |
+
### Framework versions
|
202 |
+
|
203 |
+
- PEFT 0.11.1
|
harvard_lora-qrefVqa/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "/home/wenhao/Project/intern/xiapeng/rein/LLaVA-Med/checkpoint/llava-med-v1.5-mistral-7b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 256,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 128,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"down_proj",
|
24 |
+
"v_proj",
|
25 |
+
"o_proj",
|
26 |
+
"k_proj",
|
27 |
+
"up_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"q_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
harvard_lora-qrefVqa/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:582d820df973b4a814a1e57fc165fb70455798c9faa57d80a9ef2fc7c855b429
|
3 |
+
size 708925520
|
harvard_lora-qrefVqa/config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/wenhao/Project/intern/xiapeng/rein/LLaVA-Med/checkpoint/llava-med-v1.5-mistral-7b",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaMistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"feature_outs": "encoder+decoder",
|
11 |
+
"freeze_mm_mlp_adapter": false,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 4096,
|
14 |
+
"image_aspect_ratio": "pad",
|
15 |
+
"img_size": 640,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 14336,
|
18 |
+
"max_position_embeddings": 32768,
|
19 |
+
"mm_hidden_size": 1024,
|
20 |
+
"mm_patch_merge_type": "flat",
|
21 |
+
"mm_projector_lr": 2e-05,
|
22 |
+
"mm_projector_type": "mlp2x_gelu",
|
23 |
+
"mm_use_im_patch_token": false,
|
24 |
+
"mm_use_im_start_end": false,
|
25 |
+
"mm_vision_select_feature": "patch",
|
26 |
+
"mm_vision_select_layer": -2,
|
27 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
28 |
+
"model_type": "llava_llama",
|
29 |
+
"num_attention_heads": 32,
|
30 |
+
"num_hidden_layers": 32,
|
31 |
+
"num_key_value_heads": 8,
|
32 |
+
"pretraining_tp": 1,
|
33 |
+
"proj_vis_to_txt_tokens": false,
|
34 |
+
"prompt_segtok_w_instruct": false,
|
35 |
+
"rms_norm_eps": 1e-05,
|
36 |
+
"rope_scaling": null,
|
37 |
+
"rope_theta": 1000000.0,
|
38 |
+
"segtok_posembed": "sincos",
|
39 |
+
"sliding_window": null,
|
40 |
+
"tie_word_embeddings": false,
|
41 |
+
"tokenizer_model_max_length": 1024,
|
42 |
+
"tokenizer_padding_side": "right",
|
43 |
+
"torch_dtype": "bfloat16",
|
44 |
+
"transformers_version": "4.34.1",
|
45 |
+
"tune_mm_mlp_adapter": false,
|
46 |
+
"tune_vision_tokenizer": "none",
|
47 |
+
"use_cache": true,
|
48 |
+
"use_mm_proj": true,
|
49 |
+
"vision_backbone": "convnextlarge",
|
50 |
+
"vision_tokenizer_lr": null,
|
51 |
+
"vocab_size": 32000
|
52 |
+
}
|
harvard_lora-qrefVqa/non_lora_trainables.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60fb82c3660319e6d0b239950b20c28181e97f1ade117dc0660b40e2ad94a89b
|
3 |
+
size 912
|
harvard_lora-qrefVqa/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mimic_lora-qrefVqa/README.md
ADDED
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
# base_model: /home/wenhao/Project/intern/xiapeng/rein/LLaVA-Med/checkpoint/llava-med-v1.5-mistral-7b
|
4 |
+
base_model: microsoft/llava-med-v1.5-mistral-7b
|
5 |
+
---
|
6 |
+
|
7 |
+
# Model Card for Model ID
|
8 |
+
|
9 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
10 |
+
|
11 |
+
|
12 |
+
|
13 |
+
## Model Details
|
14 |
+
|
15 |
+
### Model Description
|
16 |
+
|
17 |
+
<!-- Provide a longer summary of what this model is. -->
|
18 |
+
|
19 |
+
|
20 |
+
|
21 |
+
- **Developed by:** [More Information Needed]
|
22 |
+
- **Funded by [optional]:** [More Information Needed]
|
23 |
+
- **Shared by [optional]:** [More Information Needed]
|
24 |
+
- **Model type:** [More Information Needed]
|
25 |
+
- **Language(s) (NLP):** [More Information Needed]
|
26 |
+
- **License:** [More Information Needed]
|
27 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
28 |
+
|
29 |
+
### Model Sources [optional]
|
30 |
+
|
31 |
+
<!-- Provide the basic links for the model. -->
|
32 |
+
|
33 |
+
- **Repository:** [More Information Needed]
|
34 |
+
- **Paper [optional]:** [More Information Needed]
|
35 |
+
- **Demo [optional]:** [More Information Needed]
|
36 |
+
|
37 |
+
## Uses
|
38 |
+
|
39 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
40 |
+
|
41 |
+
### Direct Use
|
42 |
+
|
43 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
44 |
+
|
45 |
+
[More Information Needed]
|
46 |
+
|
47 |
+
### Downstream Use [optional]
|
48 |
+
|
49 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
50 |
+
|
51 |
+
[More Information Needed]
|
52 |
+
|
53 |
+
### Out-of-Scope Use
|
54 |
+
|
55 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
56 |
+
|
57 |
+
[More Information Needed]
|
58 |
+
|
59 |
+
## Bias, Risks, and Limitations
|
60 |
+
|
61 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
62 |
+
|
63 |
+
[More Information Needed]
|
64 |
+
|
65 |
+
### Recommendations
|
66 |
+
|
67 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
68 |
+
|
69 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
70 |
+
|
71 |
+
## How to Get Started with the Model
|
72 |
+
|
73 |
+
Use the code below to get started with the model.
|
74 |
+
|
75 |
+
[More Information Needed]
|
76 |
+
|
77 |
+
## Training Details
|
78 |
+
|
79 |
+
### Training Data
|
80 |
+
|
81 |
+
<!-- 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. -->
|
82 |
+
|
83 |
+
[More Information Needed]
|
84 |
+
|
85 |
+
### Training Procedure
|
86 |
+
|
87 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
88 |
+
|
89 |
+
#### Preprocessing [optional]
|
90 |
+
|
91 |
+
[More Information Needed]
|
92 |
+
|
93 |
+
|
94 |
+
#### Training Hyperparameters
|
95 |
+
|
96 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
97 |
+
|
98 |
+
#### Speeds, Sizes, Times [optional]
|
99 |
+
|
100 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
101 |
+
|
102 |
+
[More Information Needed]
|
103 |
+
|
104 |
+
## Evaluation
|
105 |
+
|
106 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
107 |
+
|
108 |
+
### Testing Data, Factors & Metrics
|
109 |
+
|
110 |
+
#### Testing Data
|
111 |
+
|
112 |
+
<!-- This should link to a Dataset Card if possible. -->
|
113 |
+
|
114 |
+
[More Information Needed]
|
115 |
+
|
116 |
+
#### Factors
|
117 |
+
|
118 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
119 |
+
|
120 |
+
[More Information Needed]
|
121 |
+
|
122 |
+
#### Metrics
|
123 |
+
|
124 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
125 |
+
|
126 |
+
[More Information Needed]
|
127 |
+
|
128 |
+
### Results
|
129 |
+
|
130 |
+
[More Information Needed]
|
131 |
+
|
132 |
+
#### Summary
|
133 |
+
|
134 |
+
|
135 |
+
|
136 |
+
## Model Examination [optional]
|
137 |
+
|
138 |
+
<!-- Relevant interpretability work for the model goes here -->
|
139 |
+
|
140 |
+
[More Information Needed]
|
141 |
+
|
142 |
+
## Environmental Impact
|
143 |
+
|
144 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
145 |
+
|
146 |
+
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).
|
147 |
+
|
148 |
+
- **Hardware Type:** [More Information Needed]
|
149 |
+
- **Hours used:** [More Information Needed]
|
150 |
+
- **Cloud Provider:** [More Information Needed]
|
151 |
+
- **Compute Region:** [More Information Needed]
|
152 |
+
- **Carbon Emitted:** [More Information Needed]
|
153 |
+
|
154 |
+
## Technical Specifications [optional]
|
155 |
+
|
156 |
+
### Model Architecture and Objective
|
157 |
+
|
158 |
+
[More Information Needed]
|
159 |
+
|
160 |
+
### Compute Infrastructure
|
161 |
+
|
162 |
+
[More Information Needed]
|
163 |
+
|
164 |
+
#### Hardware
|
165 |
+
|
166 |
+
[More Information Needed]
|
167 |
+
|
168 |
+
#### Software
|
169 |
+
|
170 |
+
[More Information Needed]
|
171 |
+
|
172 |
+
## Citation [optional]
|
173 |
+
|
174 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
175 |
+
|
176 |
+
**BibTeX:**
|
177 |
+
|
178 |
+
[More Information Needed]
|
179 |
+
|
180 |
+
**APA:**
|
181 |
+
|
182 |
+
[More Information Needed]
|
183 |
+
|
184 |
+
## Glossary [optional]
|
185 |
+
|
186 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
187 |
+
|
188 |
+
[More Information Needed]
|
189 |
+
|
190 |
+
## More Information [optional]
|
191 |
+
|
192 |
+
[More Information Needed]
|
193 |
+
|
194 |
+
## Model Card Authors [optional]
|
195 |
+
|
196 |
+
[More Information Needed]
|
197 |
+
|
198 |
+
## Model Card Contact
|
199 |
+
|
200 |
+
[More Information Needed]
|
201 |
+
### Framework versions
|
202 |
+
|
203 |
+
- PEFT 0.11.1
|
mimic_lora-qrefVqa/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "/home/wenhao/Project/intern/xiapeng/rein/LLaVA-Med/checkpoint/llava-med-v1.5-mistral-7b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 256,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 128,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"v_proj",
|
25 |
+
"k_proj",
|
26 |
+
"down_proj",
|
27 |
+
"o_proj",
|
28 |
+
"q_proj",
|
29 |
+
"up_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
mimic_lora-qrefVqa/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bde95efdf925f2378aa329b6a406b717f95f78cde6827dec7d29e19325f6379
|
3 |
+
size 708925520
|
mimic_lora-qrefVqa/config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/wenhao/Project/intern/xiapeng/rein/LLaVA-Med/checkpoint/llava-med-v1.5-mistral-7b",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaMistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"feature_outs": "encoder+decoder",
|
11 |
+
"freeze_mm_mlp_adapter": false,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 4096,
|
14 |
+
"image_aspect_ratio": "pad",
|
15 |
+
"img_size": 640,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 14336,
|
18 |
+
"max_position_embeddings": 32768,
|
19 |
+
"mm_hidden_size": 1024,
|
20 |
+
"mm_patch_merge_type": "flat",
|
21 |
+
"mm_projector_lr": 2e-05,
|
22 |
+
"mm_projector_type": "mlp2x_gelu",
|
23 |
+
"mm_use_im_patch_token": false,
|
24 |
+
"mm_use_im_start_end": false,
|
25 |
+
"mm_vision_select_feature": "patch",
|
26 |
+
"mm_vision_select_layer": -2,
|
27 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
28 |
+
"model_type": "llava_llama",
|
29 |
+
"num_attention_heads": 32,
|
30 |
+
"num_hidden_layers": 32,
|
31 |
+
"num_key_value_heads": 8,
|
32 |
+
"pretraining_tp": 1,
|
33 |
+
"proj_vis_to_txt_tokens": false,
|
34 |
+
"prompt_segtok_w_instruct": false,
|
35 |
+
"rms_norm_eps": 1e-05,
|
36 |
+
"rope_scaling": null,
|
37 |
+
"rope_theta": 1000000.0,
|
38 |
+
"segtok_posembed": "sincos",
|
39 |
+
"sliding_window": null,
|
40 |
+
"tie_word_embeddings": false,
|
41 |
+
"tokenizer_model_max_length": 1024,
|
42 |
+
"tokenizer_padding_side": "right",
|
43 |
+
"torch_dtype": "bfloat16",
|
44 |
+
"transformers_version": "4.34.1",
|
45 |
+
"tune_mm_mlp_adapter": false,
|
46 |
+
"tune_vision_tokenizer": "none",
|
47 |
+
"use_cache": true,
|
48 |
+
"use_mm_proj": true,
|
49 |
+
"vision_backbone": "convnextlarge",
|
50 |
+
"vision_tokenizer_lr": null,
|
51 |
+
"vocab_size": 32000
|
52 |
+
}
|
mimic_lora-qrefVqa/non_lora_trainables.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60fb82c3660319e6d0b239950b20c28181e97f1ade117dc0660b40e2ad94a89b
|
3 |
+
size 912
|
mimic_lora-qrefVqa/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|