katielink commited on
Commit
b8e8a28
1 Parent(s): d1216da

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -23
README.md CHANGED
@@ -56,6 +56,26 @@ This model was developed using English corpora, and thus may be considered Engli
56
 
57
  Further, this model was developed in part using the [PMC-15M](https://aka.ms/biomedclip-paper) dataset. The figure-caption pairs that make up this dataset may contain biases reflecting the current practice of academic publication. For example, the corresponding papers may be enriched for positive findings, contain examples of extreme cases, and otherwise reflect distributions that are not representative of other sources of biomedical data.
58
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
  ## Evaluation
61
 
@@ -138,29 +158,7 @@ torchrun --nnodes=1 --nproc_per_node=8 --master_port=25001 \
138
  ```
139
  </details>
140
 
141
- ## Serving
142
-
143
- | Model Delta Weights | Size |
144
- | --- | ---: |
145
- | [llava_med_in_text_60k_delta.zip](https://hanoverprod.z21.web.core.windows.net/med_llava/models/llava_med_in_text_60k_delta.zip) | 11.06 GB |
146
-
147
- The model weights above are *delta* weights. The usage of LLaVA-Med checkpoints should comply with the base LLM's model license: [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md).
148
-
149
- Instructions:
150
-
151
- 1. Download the delta weights [llava_med_in_text_60k_delta.zip](https://hanoverprod.z21.web.core.windows.net/med_llava/models/llava_med_in_text_60k_delta.zip) and unzip.
152
- 1. Get the original LLaMA weights in the huggingface format by following the instructions [here](https://huggingface.co/docs/transformers/main/model_doc/llama).
153
- 1. Use the following scripts to get LLaVA-Med weights by applying our delta. In the script below, set the --delta argument to the path of the unzipped `llava_med_in_text_60k_delta` directory. It can be adapted for other delta weights by changing the `--delta` argument (and base/target accordingly).
154
-
155
- ```bash
156
- python3 -m llava.model.apply_delta \
157
- --base /path/to/llama-7b \
158
- --target /output/path/to/llava_med_in_text_60k \
159
- --delta path/to/llava_med_in_text_60k_delta
160
- ```
161
-
162
-
163
- ## - Evaluation
164
 
165
  Depending on which checkpoint is employed in evaluation, zero-shot performance is reported on medical instruct tuned checkpoint (eg, [LLaVA-Med-7B](/path/to/checkpoint_llava_med_instruct_60k_inline_mention)), and fine-tuned performance is reported on checkpoint that has been further tuned on training set of the downstream datasets (eg, [LLaVA-Med-7B-VQA-Rad](/path/to/checkpoint_llava_med_instruct_60k_inline_mention/fine_tuned/vqa_rad) ).
166
 
 
56
 
57
  Further, this model was developed in part using the [PMC-15M](https://aka.ms/biomedclip-paper) dataset. The figure-caption pairs that make up this dataset may contain biases reflecting the current practice of academic publication. For example, the corresponding papers may be enriched for positive findings, contain examples of extreme cases, and otherwise reflect distributions that are not representative of other sources of biomedical data.
58
 
59
+ ## Serving
60
+
61
+ | Model Delta Weights | Size |
62
+ | --- | ---: |
63
+ | [llava_med_in_text_60k_delta.zip](https://hanoverprod.z21.web.core.windows.net/med_llava/models/llava_med_in_text_60k_delta.zip) | 11.06 GB |
64
+
65
+ The model weights above are *delta* weights. The usage of LLaVA-Med checkpoints should comply with the base LLM's model license: [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md).
66
+
67
+ Instructions:
68
+
69
+ 1. Download the delta weights [llava_med_in_text_60k_delta.zip](https://hanoverprod.z21.web.core.windows.net/med_llava/models/llava_med_in_text_60k_delta.zip) and unzip.
70
+ 1. Get the original LLaMA weights in the huggingface format by following the instructions [here](https://huggingface.co/docs/transformers/main/model_doc/llama).
71
+ 1. Use the following scripts to get LLaVA-Med weights by applying our delta. In the script below, set the --delta argument to the path of the unzipped `llava_med_in_text_60k_delta` directory. It can be adapted for other delta weights by changing the `--delta` argument (and base/target accordingly).
72
+
73
+ ```bash
74
+ python3 -m llava.model.apply_delta \
75
+ --base /path/to/llama-7b \
76
+ --target /output/path/to/llava_med_in_text_60k \
77
+ --delta path/to/llava_med_in_text_60k_delta
78
+ ```
79
 
80
  ## Evaluation
81
 
 
158
  ```
159
  </details>
160
 
161
+ #### - Evaluation
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
162
 
163
  Depending on which checkpoint is employed in evaluation, zero-shot performance is reported on medical instruct tuned checkpoint (eg, [LLaVA-Med-7B](/path/to/checkpoint_llava_med_instruct_60k_inline_mention)), and fine-tuned performance is reported on checkpoint that has been further tuned on training set of the downstream datasets (eg, [LLaVA-Med-7B-VQA-Rad](/path/to/checkpoint_llava_med_instruct_60k_inline_mention/fine_tuned/vqa_rad) ).
164