TheBloke
/

ALMA-13B-Pretrain-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

TheBloke commited on Sep 24, 2023

Commit

9767052

·

1 Parent(s): d3170b0

Upload README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -5,7 +5,7 @@ license: mit
 model_creator: haoranxu
 model_name: ALMA 13B Pretrain
 model_type: llama
-prompt_template: 'Translate this from Chinese to English
   Chinese: {prompt}
@@ -57,7 +57,7 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
 ## Prompt template: ALMA
 ```
-Translate this from Chinese to English
 Chinese: {prompt}
 English:
@@ -231,7 +231,7 @@ model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 prompt = "Tell me about AI"
-prompt_template=f'''Translate this from Chinese to English
 Chinese: {prompt}
 English:
 '''

 model_creator: haoranxu
 model_name: ALMA 13B Pretrain
 model_type: llama
+prompt_template: 'Translate this from Chinese to English:
   Chinese: {prompt}
 ## Prompt template: ALMA
 ```
+Translate this from Chinese to English:
 Chinese: {prompt}
 English:
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 prompt = "Tell me about AI"
+prompt_template=f'''Translate this from Chinese to English:
 Chinese: {prompt}
 English:
 '''