Update README.md

README.md

@@ -18,12 +18,14 @@ Code Llama is a collection of pretrained and fine-tuned generative text models r
 
 ## Model Use
 
-To use this model, please make sure to install transformers from `main` until the next version is released:
+Install `transformers`
 
 ```bash
-pip install git+https://github.com/huggingface/transformers.git@main accelerate
+pip install transformers accelerate
 ```
 
+**Warning:** The 70B Instruct model has a different prompt template than the smaller versions. We'll update this repo soon.
+
 Model capabilities:
 
 - [x] Code completion.
@@ -36,7 +38,7 @@ Model capabilities:
 
 **Model Developers** Meta
 
-**Variations** Code Llama comes in three model sizes, and three variants:
+**Variations** Code Llama comes in four model sizes, and three variants:
 
 * Code Llama: base models designed for general code synthesis and understanding
 * Code Llama - Python: designed specifically for Python
@@ -50,9 +52,9 @@ All variants are available in sizes of 7B, 13B, 34B, and 70B parameters.
 
 **Output** Models generate text only.
 
-**Model Architecture** Code Llama is an auto-regressive language model that uses an optimized transformer architecture.
+**Model Architecture** Code Llama is an auto-regressive language model that uses an optimized transformer architecture. It was fine-tuned with up to 16k tokens. This variant **does not** support long context of up to 100k tokens.
 
-**Model Dates** Code Llama and its variants have been trained between January 2023 and July 2023.
+**Model Dates** Code Llama and its variants have been trained between January 2023 and January 2024.
 
 **Status** This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.
 
@@ -66,7 +68,7 @@ All variants are available in sizes of 7B, 13B, 34B, and 70B parameters.
 **Out-of-Scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.
 
 ## Hardware and Software
-**Training Factors** We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.
+**Training Factors** We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.\\**Carbon Footprint** In aggregate, training all 12 Code Llama models required 1400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 228.55 tCO2eq, 100% of which were offset by Meta’s sustainability program.
 
 ## Evaluation Results