Update README.md

README.md

@@ -1,40 +1,45 @@
-# How to use me?
+---
+datasets:
+- tiiuae/falcon-refinedweb
+language:
+- en
+---
 
-```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import transformers
-import torch
+# Falcon-7B-Instruct
 
-tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon_tokenizer")
+**Falcon-7B-Instuct is a 7B parameters causal decoder-only model built by [TII](https://www.tii.ae), based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b), and finetuned on an ensemble of instruct datasets. It is made available under the [TII Falcon LLM License](https://huggingface.co/tiiuae/falcon-7b/blob/main/LICENSE.txt).**
 
+More details coming soon.
 
-model = AutoModelForCausalLM.from_pretrained(
-    "tiiuae/falcon-micro-self-instruct",
-    trust_remote_code=True,
-    torch_dtype=torch.bfloat16,
-    use_auth_token="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",
-)
 
-model.bfloat16()
-model.cuda()
+# Model Card for Falcon-7B-Instruct
 
-pipeline = transformers.pipeline("text-generation", model=model, tokenizer=tokenizer, device="cuda:0")
-sequences = pipeline(
-    "What is your favourite dad joke?",
-    max_length=200,
-    do_sample=True,
-    top_k=10,
-    repetition_penalty=1.2,
-    num_return_sequences=2,
-    eos_token_id=tokenizer.eos_token_id,
-)
 
-for seq in sequences:
-    print(f"Result: {seq['generated_text']}")
+## Model Details
 
-```
+### Model Description
 
+- **Developed by:** [https://www.tii.ae](https://www.tii.ae)
+- **Model type:** Causal decoder-only
+- **Language(s) (NLP):** English
+- **License:** TII Falcon LLM License
 
+### Model Source
 
-There will be a warning that the model is not supported for generation, it can safely be ignore.
+- **Paper:** coming soon
+- **Demo:** coming soon
 
+## Uses
+
+### Out-of-Scope Use
+
+Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful
+
+## Bias, Risks, and Limitations
+
+Falcon-7B-Instruct is trained on English data only, and 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
+
+
+## Paper
+
+More details coming soon in the paper.