Update README.md

README.md

@@ -1,20 +1,13 @@
 ---
 library_name: peft
----
-language: en
-thumbnail: 
-tags:
-- peft
-- text-generation
-- chatbot
-- ecommerce
-- fine-tuned
-pipeline_tag: text-generation
 license: apache-2.0
 datasets:
-- kaggle
-metrics:
-- 
+- dltdojo/ecommerce-faq-chatbot-dataset
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- text-generation-inference
 ---
 
 # Falcon 7B LLM Fine Tune Model
@@ -41,19 +34,20 @@ input_prompt = "Hello, Bot!"
 input_ids = tokenizer.encode(input_prompt, return_tensors='pt')
 output = model.generate(input_ids)
 output_text = tokenizer.decode(output[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
+```
 
 ## Training procedure
 
 The model was fine-tuned on the [Ecommerce-FAQ-Chatbot-Dataset](https://kaggle.com/datasets/saadmakhdoom/ecommerce-faq-chatbot-dataset) using the `bitsandbytes` quantization config:
-- load_in_8bit: False
-- load_in_4bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: bfloat16
+- load_in_8bit: `False`
+- load_in_4bit: `True`
+- llm_int8_threshold: `6.0`
+- llm_int8_skip_modules: `None`
+- llm_int8_enable_fp32_cpu_offload: `False`
+- llm_int8_has_fp16_weight: `False`
+- bnb_4bit_quant_type: `nf4`
+- bnb_4bit_use_double_quant: `True`
+- bnb_4bit_compute_dtype: `bfloat16`
 
 ### Framework versions
 
@@ -61,7 +55,7 @@ The model was fine-tuned on the [Ecommerce-FAQ-Chatbot-Dataset](https://kaggle.c
 
 ## Evaluation results
 
-The model was trained for 80 steps, with the training loss decreasing from 0.184 to nearly 0. The final training loss was 0.03094411873175886.
+The model was trained for 80 steps, with the training loss decreasing from 0.184 to nearly 0. The final training loss was `0.03094411873175886`.
 
 - Trainable params: 2359296
 - All params: 3611104128
@@ -69,4 +63,4 @@ The model was trained for 80 steps, with the training loss decreasing from 0.184
 
 ## License
 
-This model is licensed under Apache 2.0. Please see the [LICENSE](https://www.apache.org/licenses/LICENSE-2.0) for more information.
+This model is licensed under Apache 2.0. Please see the [LICENSE](https://www.apache.org/licenses/LICENSE-2.0) for more information.