lorinma
/

yi6B_Vicuna

Text Generation

Eval Results (legacy)

text-generation-inference

Model card Files Files and versions

lorinma commited on Jan 9, 2024

Commit

f27250b

·

1 Parent(s): 5a2e28e

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -6,13 +6,13 @@ language:
 - en
 ---
-*TODO:Upload pending, training is finished. still testing.
 *Update: Having a bit issue with the tokenizer, still figuring things out.
 Reproduce Vicuna, but based on yi-6B. The training data I used was ShareGPT_V3_unfiltered_cleaned_split_no_imsorry.json.
-Hyper parameters:
 ```
 CUDA_VISIBLE_DEVICES=0,1,2,3,5 torchrun --nproc_per_node 5 ../supervised_finetuning.py \
     --model_type auto \

 - en
 ---
 *Update: Having a bit issue with the tokenizer, still figuring things out.
 Reproduce Vicuna, but based on yi-6B. The training data I used was ShareGPT_V3_unfiltered_cleaned_split_no_imsorry.json.
+The training framework I used https://github.com/shibing624/MedicalGPT , train shell:
 ```
 CUDA_VISIBLE_DEVICES=0,1,2,3,5 torchrun --nproc_per_node 5 ../supervised_finetuning.py \
     --model_type auto \