Update README.md

Add corrections to the model card

README.md

@@ -4,6 +4,14 @@ tags:
 - trl
 - transformers
 - reinforcement-learning
+- LLM detoxification
+datasets:
+- ProlificAI/social-reasoning-rlhf
+language:
+- en
+metrics:
+- accuracy
+pipeline_tag: conversational
 ---
 
 # TRL Model
@@ -24,7 +32,7 @@ You can then generate text as follows:
 ```python
 from transformers import pipeline
 
-generator = pipeline("text-generation", model="ARahul2003//tmp/tmp0xxgcy93/ARahul2003/lamini_flan_t5_detoxify_rlaif")
+generator = pipeline("text-generation", model="ARahul2003/lamini_flan_t5_detoxify_rlaif")
 outputs = generator("Hello, my llama is cute")
 ```
 
@@ -34,9 +42,9 @@ If you want to use the model for training or to obtain the outputs from the valu
 from transformers import AutoTokenizer
 from trl import AutoModelForCausalLMWithValueHead
 
-tokenizer = AutoTokenizer.from_pretrained("ARahul2003//tmp/tmp0xxgcy93/ARahul2003/lamini_flan_t5_detoxify_rlaif")
-model = AutoModelForCausalLMWithValueHead.from_pretrained("ARahul2003//tmp/tmp0xxgcy93/ARahul2003/lamini_flan_t5_detoxify_rlaif")
+tokenizer = AutoTokenizer.from_pretrained("ARahul2003/lamini_flan_t5_detoxify_rlaif")
+model = AutoModelForCausalLMWithValueHead.from_pretrained("ARahul2003/lamini_flan_t5_detoxify_rlaif")
 
 inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
 outputs = model(**inputs, labels=inputs["input_ids"])
-```
+```