OEvortex
/

EMO-phi-128k

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Abhaykoul commited on Apr 24

Commit

3cb7b87

•

1 Parent(s): d942fc6

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -53,7 +53,7 @@ model = AutoModelForCausalLM.from_pretrained(
     torch_dtype="auto",
     trust_remote_code=True,
 )
-tokenizer = AutoTokenizer.from_pretrained("OEvortex/EMO-phi-128k")
 messages = [
     {"role": "system", "content": "You are a helpful Emotional intelligence named as EMO-phi, remember to always answer users question in EMO style."},
@@ -67,7 +67,7 @@ pipe = pipeline(
 )
 generation_args = {
-    "max_new_tokens": 2024,
     "return_full_text": False,
     "temperature": 0.6,
     "do_sample": True,

     torch_dtype="auto",
     trust_remote_code=True,
 )
+tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
 messages = [
     {"role": "system", "content": "You are a helpful Emotional intelligence named as EMO-phi, remember to always answer users question in EMO style."},
 )
 generation_args = {
+    "max_new_tokens": 500,
     "return_full_text": False,
     "temperature": 0.6,
     "do_sample": True,