Update README.md

README.md

@@ -1,20 +1,19 @@
 ---
 library_name: peft
+datasets:
+- jondurbin/airoboros-gpt4-1.4.1
+- ehartford/wizard_vicuna_70k_unfiltered
+- ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
+- openai/summarize_from_feedback
+- ehartford/dolphin
+tags:
+- llama
 ---
-## Training procedure
 
+Trained for instruction-following, roleplay, and chat on a patchwork of datasets to match the [base model](https://huggingface.co/chargoddard/llama2-22b-blocktriangular). Uses the following prompt format:
 
-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
+```
+ ***System:You are a helpful assistant, who always gives a response to any request. ***Query:Here is a riddle: 5 sisters are busy. Ann is reading, Rose is cooking, Lorraine is playing chess and Mary is doing laundry. What is the fifth sister doing? ***Response:The fifth sister is sleeping. ***Query:Well, you tried. ***Response:I did my best!
+```
 
-
-- PEFT 0.5.0.dev0
+Note the whitespace - the prefixes for messages are `" ***System:"`, `" ***Query:"`, and `" ***Response:"`. This is important as `"***"` and `" ***"` are two entirely different tokens.