Update README.md

README.md

@@ -1,13 +1,13 @@
-# 🚀 Falcon-11B
+# 🚀 Falcon2-11B
 
-**Falcon-11B is a 11B parameters causal decoder-only model built by [TII](https://www.tii.ae) and trained over 5,000B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. The model is made available under the Apache 2.0 license.**
+**Falcon2-11B is a 11B parameters causal decoder-only model built by [TII](https://www.tii.ae) and trained over 5,000B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. The model is made available under the Apache 2.0 license.**
 
 *Paper coming soon 😊.*
 
 
 🤗 To get started with Falcon (inference, finetuning, quantization, etc.), we recommend reading [this great blogpost fron HF](https://huggingface.co/blog/falcon)!
 
-⚠️ **This is a raw, pretrained model, which should be further finetuned for most usecases.** If you are looking for a version better suited to taking generic instructions in a chat format, we recommend taking a look at [Falcon-11B-Chat](https://huggingface.co/tiiuae/falcon-11B-chat). 
+⚠️ **This is a raw, pretrained model, which should be further finetuned for most usecases.** If you are looking for a version better suited to taking generic instructions in a chat format, we recommend taking a look at [Falcon2-11B-Chat](https://huggingface.co/tiiuae/Falcon2-11B-chat). 
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
@@ -41,7 +41,7 @@ for seq in sequences:
 
 For fast inference with Falcon, check-out [Text Generation Inference](https://github.com/huggingface/text-generation-inference)! Read more in this [blogpost]((https://huggingface.co/blog/falcon). 
 
-# Model Card for Falcon-11B
+# Model Card for Falcon2-11B
 
 ## Model Details
 
@@ -68,11 +68,11 @@ Production use without adequate assessment of risks and mitigation; any use case
 
 ## Bias, Risks, and Limitations
 
-Falcon-11B is trained mostly on English, but also German, Spanish, French, Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish. It will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
+Falcon2-11B is trained mostly on English, but also German, Spanish, French, Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish. It will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
 
 ### Recommendations
 
-We recommend users of Falcon-11B to consider finetuning it for the specific set of tasks of interest, and for guardrails and appropriate precautions to be taken for any production use.
+We recommend users of Falcon2-11B to consider finetuning it for the specific set of tasks of interest, and for guardrails and appropriate precautions to be taken for any production use.
 
 ## How to Get Started with the Model
 
@@ -109,28 +109,26 @@ for seq in sequences:
 
 ### Training Data
 
-Falcon-11B was trained over 5,000B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb), a high-quality filtered and deduplicated web dataset which we enhanced with curated corpora. It followed a 4 stage training strategy. The first three stages being focused on increasing the context length, from to 2048 to 4096 and finally to 8192 tokens. The last stage aimed to further enhance performance using only high quality data.
+Falcon2-11B was trained over 5,000B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb), a high-quality filtered and deduplicated web dataset which we enhanced with curated corpora. It followed a 4 stage training strategy. The first three stages being focused on increasing the context length, from to 2048 to 4096 and finally to 8192 tokens. The last stage aimed to further enhance performance using only high quality data.
 
 Overall, the data sources included RefinedWeb-English, Refined Web-Europe (en, de, es, fr, it, pt, pl, nl, ro, sv, cs), high quality technical data, code data, and conversational data extracted from public sources.
 
 
-| Technical          | 2%           | 20B        | arXiv, PubMed, USPTO, etc.        |
-
 The training stages were as follows:
 
-| **Stage** | **Context length** | ** Tokens** |
+| **Stage**    | **Context length** | **Tokens** |
 |--------------|-----------------|-------------|
-| Stage 1      | 2048            | 4500B       |
-| Stage 2      | 4096            | 250B        |
-| Stage 3      | 8192            | 250B        |
-| Stage 4      | 8192            | 240B        |
+| Stage 1 | 2048            | 4500B       |
+| Stage 2 | 4096            | 250B        |
+| Stage 3 | 8192            | 250B        |
+| Stage 4 | 8192            | 500B        |
 
 
 The data was tokenized with the Falcon-[7B](https://huggingface.co/tiiuae/falcon-7b)/[11B](https://huggingface.co/tiiuae/falcon-11B) tokenizer.
 
 ### Training Procedure 
 
-Falcon-11B was trained on 1024 A100 40GB GPUs, using a 3D parallelism strategy (TP=8, PP=1, DP=128) combined with ZeRO.
+Falcon2-11B was trained on 1024 A100 40GB GPUs, using a 3D parallelism strategy (TP=8, PP=1, DP=128) combined with ZeRO and Flash-Attention 2.
 
 #### Training Hyperparameters
 
@@ -138,10 +136,10 @@ Falcon-11B was trained on 1024 A100 40GB GPUs, using a 3D parallelism strategy (
 |--------------------|------------|-------------------------------------------|
 | Precision          | `bfloat16` |                                           |
 | Optimizer          | AdamW      |                                           |
-| Max learning rate      | 3.7e-4       | Following a linear warm=up, then cosine decay to 1.89e-5 across 4500 B tokens. |
+| Max learning rate      | 3.7e-4       | Following a linear warm-up, then cosine decay to 1.89e-5 across 4500 B tokens. |
 | Weight decay       | 1e-1       |                                           |
 | Z-loss             | 1e-4       |                                           |
-| Batch size         | Variable        | Batch size was gradually increased duringthe training                         |
+| Batch size         | Variable        | Batch size was gradually increased during the training                         |
 
 
 #### Speeds, Sizes, Times
@@ -168,7 +166,7 @@ We thank the leaderboard team from HuggingFace for providing an official evaluat
 
 ### Model Architecture and Objective
 
-Falcon-11B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).
+Falcon2-11B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).
 
 The architecture is broadly adapted from the GPT-3 paper ([Brown et al., 2020](https://arxiv.org/abs/2005.14165)), with the following differences:
 
@@ -190,11 +188,11 @@ For multiquery, we are using an internal variant which uses independent key and
 
 #### Hardware
 
-Falcon-11B was trained on AWS SageMaker, using on average 1024 A100 40GB GPUs in 128 p4d instances. 
+Falcon2-11B was trained on AWS SageMaker, using on average 1024 A100 40GB GPUs in 128 p4d instances. 
 
 #### Software
 
-Falcon-11B was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention2, etc.)
+Falcon2-11B was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention2, etc.)
 
 ## Citation
 
@@ -202,7 +200,7 @@ Falcon-11B was trained a custom distributed training codebase, Gigatron. It uses
 
 ## License
 
-Falcon2 11B is licenced under TII Falcon License 2.0, the permissive Apache 2.0-based software license which includes an acceptable use policy that promotes the responsible use of AI.
+Falcon2-11B is licenced under TII Falcon License 2.0, the permissive Apache 2.0-based software license which includes an acceptable use policy that promotes the responsible use of AI.
 
 ## Contact
 falconllm@tii.ae