Upload folder using huggingface_hub

README.md

@@ -1,3 +1,19 @@
 ---
+language: en
 license: mit
 ---
+
+# SpaceSCIBert_TaskVal
+
+This is a fine tuned classification variant of the icelab/spacescibert[1] model to take in satellite operator task descriptions and output NASA TLX values [2]
+
+This model was trained for CS6795 Introduction to Cognitive Science at Gatech term project in Fall 2026. 
+
+This model was fine tuned using a very small synethic dataset made using an LLM. It was 686 descriptions and their TLX values. This lead to the loss of the model stopping improvement around 30 points error on values. This model shouldn't be used in its current state. Hosting this for the other parts of the term project. 
+
+1. A. Berquand, P. Darm, and A. Riccardi, “Spacetransformers: Language
+modeling for space systems,” IEEE Access, vol. 9, pp. 133111–133122,
+2021
+2. B. Gore, “Nasa task load index (tlx).” https://www.nasa.gov/
+human-systems-integration-division/nasa-task-load-index-tlx/, Mar
+2026

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5ef9e0121f02fa032c596983fe5e01822cd37b950d8cc9c0c5e6271b166d28
+size 439774938

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "scibert_scivocab_uncased2/", "do_basic_tokenize": true, "never_split": null}