Update README.md

README.md

@@ -3,38 +3,26 @@ library_name: peft
 pipeline_tag: text-generation
 base_model: google/gemma-3-1b-it
 license: gemma
+language: en
+datasets:
+  - nbertagnolli/counsel-chat
 tags:
   - lora
+  - peft
   - gemma3
   - few-shot
-  - instruction-tuned
+  - counseling
+  - empathy
 ---
 
 # lora8-fewshot — LoRA adapter for Gemma 3 1B IT
 
-Lightweight **LoRA rank-8** adapter trained on a small few-shot instruction dataset to make `google/gemma-3-1b-it` more responsive in short, task-oriented chats.  
-This repo contains **only the adapter**; you must load it on top of the base model.
+Lightweight **LoRA rank-8** adapter trained on therapist Q&A from **CounselChat** to make `google/gemma-3-1b-it` more responsive for short, task-oriented counseling prompts.  
+This repo contains **only the adapter**; load it on top of the base model. :contentReference[oaicite:0]{index=0}
 
 ---
 
-## Model Details
-
-- **Developed by:** Nikhil Sharma,   
-- **Shared by:** [NikhilSharma](https://huggingface.co/NikhilSharma)
-- **Model type:** PEFT LoRA adapter for a causal decoder-only LLM (Gemma 3)  
-- **Base model:** `google/gemma-3-1b-it`
-- **Languages:** English (primarily)  
-- **Context length (train cfg):** 2048 tokens  
-- **Artifacts:** `adapter_model.safetensors` (~25 MB), `adapter_config.json`  
-- **How it’s used:** attach to the base model at inference; merging not required.
-
-### Sources
-- **This repo:** (you are here)
-- **Base model card:** `google/gemma-3-1b-it`
-
----
-
-## Usage
+## Quick start
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
@@ -47,9 +35,8 @@ tok = AutoTokenizer.from_pretrained(base_id)
 base = AutoModelForCausalLM.from_pretrained(base_id, torch_dtype="auto")
 model = PeftModel.from_pretrained(base, adapter_id)
 
-prompt = "Summarize the key points of the meeting in 5 bullets."
-inp = tok.apply_chat_template([{"role":"user","content":prompt}], tokenize=False, add_generation_prompt=True)
-ids = tok(inp, return_tensors="pt").to(model.device)
-
-out = model.generate(**ids, max_new_tokens=200, temperature=0.7)
+prompt = "How can I avoid thinking much?,I start thinking deeply about everything I may do or say and about anything that may happen. I really want to avoid it since it really bothers me."
+chat = tok.apply_chat_template([{"role": "user", "content": prompt}], tokenize=False, add_generation_prompt=True)
+inputs = tok(chat, return_tensors="pt").to(model.device)
+out = model.generate(**inputs, max_new_tokens=200, temperature=0.7)
 print(tok.decode(out[0], skip_special_tokens=True))