nthakur
/

Meta-Llama-3-8B-Instruct-mirage-bench-sft

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

nthakur commited on Mar 31

Commit

dd3309e

·

verified ·

1 Parent(s): 4e39854

updated README

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 datasets:
-- nthakur/mirage-gpt-4o-sft-instruct-llama-3
 library_name: peft
 license: llama3
 tags:
@@ -17,9 +17,9 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
-# Meta-Llama-3-8B-Instruct-mirage-mirage-gpt-4o-sft-instruct-llama-3
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the nthakur/mirage-gpt-4o-sft-instruct-llama-3 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.2505

 ---
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 datasets:
+- nthakur/mirage-bench-sft-teacher-gpt-4o
 library_name: peft
 license: llama3
 tags:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
+# nthakur/Meta-Llama-3-8B-Instruct-mirage-bench-sft
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the [nthakur/mirage-bench-sft-teacher-gpt-4o](https://huggingface.co/datasets/nthakur/mirage-bench-sft-teacher-gpt-4o) dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.2505