Update README.md

README.md

@@ -6,50 +6,15 @@ license: cc-by-nc-4.0
 
 This is a fine-tuned 7b parameter LlaMa model, using completely synthetic training data created by https://github.com/jondurbin/airoboros
 
+__*I don't recommend using this model! The outputs aren't particularly great, and it may contain "harmful" data due to jailbreak*__
+
+Please see one of the updated airoboros models for a much better experience.
+
 ### Training data
 
-I used a jailbreak prompt to generate the synthetic instructions, which resulted in some training data that would likely be censored by other models, such as how-to prompts about synthesizing drugs, making homemade flamethrowers, etc.  Mind you, this is all generated by ChatGPT, not me.  My goal was to simply test some of the capabilities of ChatGPT when unfiltered (as much as possible), and not to intentionally produce any harmful/dangerous/etc. content.
-
-The jailbreak prompt I used is the default prompt in the python code when using the `--uncensored` flag: https://github.com/jondurbin/airoboros/blob/main/airoboros/self_instruct.py#L39
-
-I also did a few passes of manually cleanup to remove some bad prompts, but mostly I left the data as-is.  Initially, the model was fairly bad at math/extrapolation, closed question-answering (heavy hallucination), and coding, so I did one more fine tuning pass with additional synthetic instructions aimed at those types of problems.
-
-Both the initial instructions and final-pass fine-tuning instructions will be published soon.
-
-### Fine-tuning method
-
-I used the excellent [FastChat](https://github.com/lm-sys/FastChat) module, running with:
-
-```
-torchrun --nproc_per_node=8 --master_port=20001 /workspace/FastChat/fastchat/train/train_mem.py \
-  --model_name_or_path /workspace/llama-7b \
-  --data_path /workspace/as_conversations.json \
-  --bf16 True \
-  --output_dir /workspace/airoboros-7b \
-  --num_train_epochs 3 \
-  --per_device_train_batch_size 24 \
-  --per_device_eval_batch_size 24 \
-  --gradient_accumulation_steps 2 \
-  --evaluation_strategy "steps" \
-  --eval_steps 1000 \
-  --save_strategy "steps" \
-  --save_steps 1000 \
-  --save_total_limit 10 \
-  --learning_rate 2e-5 \
-  --weight_decay 0. \
-  --warmup_ratio 0.04 \
-  --lr_scheduler_type "cosine" \
-  --logging_steps 1 \
-  --fsdp "full_shard auto_wrap" \
-  --fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
-  --tf32 True \
-  --model_max_length 2048 \
-  --gradient_checkpointing True \
-  --lazy_preprocess True
-```
-
-This ran on 8x nvidia 80gb a100's for about 17 hours.
+This was an experiment to see if a "jailbreak" prompt could be used to generate a broader range of data that would otherwise have been filtered by OpenAI's alignment efforts.
 
+The jailbreak did indeed work with a high success rate, and caused OpenAI to generate a broader range of topics and fewer refusals to answer questions/instructions of sensitive topics.
 
 ### Usage and License Notices