Files changed (2) hide show
  1. README.md +14 -12
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -1,18 +1,20 @@
1
  ---
2
- license: apache-2.0
3
- language:
4
- - en
5
- library_name: transformers
6
- pipeline_tag: text-generation
7
  ---
 
8
 
9
- [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).
10
 
11
- ## Tutorials
 
 
 
 
 
 
 
 
 
 
12
 
13
- - Text tutorial: https://www.mlexpert.io/prompt-engineering/fine-tuning-llm-on-custom-dataset-with-qlora
14
- - YouTube video: https://www.youtube.com/watch?v=DcBC4yGHV4Q
15
 
16
- ## Training
17
-
18
- Fine-tuned using the QLoRA technique (only adapter uploaded). With the help of bitsandbytes, peft and transformers. Full reproduction is available in the tutorials.
 
1
  ---
2
+ library_name: peft
 
 
 
 
3
  ---
4
+ ## Training procedure
5
 
 
6
 
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: bfloat16
17
+ ### Framework versions
18
 
 
 
19
 
20
+ - PEFT 0.4.0.dev0
 
 
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c507033f393c37833ac3a8932e3ed6d5b92b1f26a6d07763860767f5f4d910fe
3
  size 18898161
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb23f5af873a5a1ddfc7ce9cc3cc6d183a39be505be9eb2152fa7eb7fedfaa8
3
  size 18898161