Upload model

README.md

@@ -1,18 +1,20 @@
 ---
-license: apache-2.0
-language:
-- en
-library_name: transformers
-pipeline_tag: text-generation
+library_name: peft
 ---
+## Training procedure
 
-[Falcon 7b](https://huggingface.co/tiiuae/falcon-7b) model trained on [FAQ from an ecommerce website](https://www.kaggle.com/datasets/saadmakhdoom/ecommerce-faq-chatbot-dataset).
 
-## Tutorials
+The following `bitsandbytes` quantization config was used during training:
+- 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
 
-- Text tutorial: https://www.mlexpert.io/prompt-engineering/fine-tuning-llm-on-custom-dataset-with-qlora
-- YouTube video: https://www.youtube.com/watch?v=DcBC4yGHV4Q
 
-## Training
-
-Fine-tuned using the QLoRA technique (only adapter uploaded). With the help of bitsandbytes, peft and transformers. Full reproduction is available in the tutorials.
+- PEFT 0.4.0.dev0

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c507033f393c37833ac3a8932e3ed6d5b92b1f26a6d07763860767f5f4d910fe
+oid sha256:a1ee2dcf50978f87ae4523165e0f2f9060e1188890226c8c39d65be7656a8ed9
 size 18898161