Update README.md

README.md

@@ -1,5 +1,4 @@
 ---
-license: cc-by-nc-4.0
 datasets:
 - conceptofmind/cot_submix_original
 - conceptofmind/flan2021_submix_original
@@ -13,19 +12,19 @@ pipeline_tag: text-generation
 
 ## Model Description
 
-`StableBeluga_13B` is a Llama2 13B model finetuned on an Orca style Dataset
+`Stable Beluga 13B` is a Llama2 13B model finetuned on an Orca style Dataset
 
 ## Usage
 
-Start chatting with `StableBeluga_13B` using the following code snippet:
+Start chatting with `Stable Beluga 13B` using the following code snippet:
 
 ```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-tokenizer = AutoTokenizer.from_pretrained("stabilityai/StableBeluga_13B", use_fast=False)
-model = AutoModelForCausalLM.from_pretrained("stabilityai/StableBeluga_13B", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
-system_prompt = "### System:\nYou are StableBeluga_13B, an AI that follows instructions extremely well. Help as much as you can. Remember, be safe, and don't do anything illegal.\n\n"
+tokenizer = AutoTokenizer.from_pretrained("stabilityai/StableBeluga-13B", use_fast=False)
+model = AutoModelForCausalLM.from_pretrained("stabilityai/StableBeluga-13B", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
+system_prompt = "### System:\nYou are Stable Beluga 13B, an AI that follows instructions extremely well. Help as much as you can. Remember, be safe, and don't do anything illegal.\n\n"
 
 message = "Write me a poem please"
 prompt = f"{system_prompt}### User: {message}\n\n### Assistant:\n"
@@ -35,7 +34,7 @@ output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_t
 print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
-StableBeluga_13B should be used with this prompt format:
+Stable Beluga 13B should be used with this prompt format:
 ```
 ### System:
 This is a system prompt, please behave and help the user.
@@ -44,21 +43,21 @@ This is a system prompt, please behave and help the user.
 Your prompt here
 
 ### Assistant
-The output of StableBeluga_13B
+The output of Stable Beluga 13B
 ```
 
 ## Model Details
 
 * **Developed by**: [Stability AI](https://stability.ai/)
-* **Model type**: StableBeluga_13B is an auto-regressive language model fine-tuned on Llama2 13B.
+* **Model type**: Stable Beluga 13B is an auto-regressive language model fine-tuned on Llama2 13B.
 * **Language(s)**: English
 * **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
-* **License**: Fine-tuned checkpoints (`FreeWilly2`) is licensed under the Non-Commercial Creative Commons license ([CC BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/))
+* **License**: Fine-tuned checkpoints (`Stable Beluga 13B`) is licensed under the [STABLE BELUGA NON-COMMERCIAL COMMUNITY LICENSE AGREEMENT](https://huggingface.co/stabilityai/StableBeluga-13B/blob/main/LICENSE.txt)
 * **Contact**: For questions and comments about the model, please email `lm@stability.ai`
 
 ### Training Dataset
 
-`StableBeluga_13B` is trained on our internal Orca-style dataset
+` Stable Beluga 13B` is trained on our internal Orca-style dataset
 
 ### Training Procedure
 
@@ -69,15 +68,9 @@ Models are learned via supervised fine-tuning on the aforementioned datasets, tr
 | Orca pt1 packed   | 256        | 3e-5          | Cosine to 3e-6    | 100     | 1e-6         | (0.9, 0.95) |
 | Orca pt2 unpacked | 512        | 3e-5          | Cosine to 3e-6    | 100     | 1e-6         | (0.9, 0.95) |
 
-## Use and Limitations
+## Ethical Considerations and Limitations
 
-### Intended Use
-
-These models are intended for research only, in adherence with the [CC BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/) license.
-
-### Limitations and bias
-
-Although the aforementioned dataset helps to steer the base language models into "safer" distributions of text, not all biases and toxicity can be mitigated through fine-tuning. We ask that users be mindful of such potential issues that can arise in generated responses. Do not treat model outputs as substitutes for human judgment or as sources of truth. Please use it responsibly.
+Beluga is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Beluga's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Beluga, developers should perform safety testing and tuning tailored to their specific applications of the model.
 
 ## Citations