Update README.md

README.md

@@ -50,7 +50,7 @@ In case you want to perform inference on the BitNet checkpoint run:
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "tiiuae/Falcon-E-1B-Base"
+model_id = "tiiuae/Falcon-E-3B-Instruct"
 
 model = AutoModelForCausalLM.from_pretrained(
   model_id,
@@ -66,7 +66,7 @@ If you want to rather use the classic `bfloat16` version, you can run:
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "tiiuae/Falcon-E-1B-Base"
+model_id = "tiiuae/Falcon-E-3B-Instruct"
 revision = "bfloat16"
 
 model = AutoModelForCausalLM.from_pretrained(
@@ -84,8 +84,8 @@ model = AutoModelForCausalLM.from_pretrained(
 ```
 git clone https://github.com/microsoft/BitNet && cd BitNet
 pip install -r requirements.txt
-python setup_env.py --hf-repo tiiuae/Falcon-E-1B-Base -q i2_s
-python run_inference.py -m models/Falcon-E-1B-Base/ggml-model-i2_s.gguf -p "You are a helpful assistant" -cnv
+python setup_env.py --hf-repo tiiuae/Falcon-E-3B-Instruct -q i2_s
+python run_inference.py -m models/Falcon-E-3B-Instruct/ggml-model-i2_s.gguf -p "You are a helpful assistant" -cnv
 ```
 
 ### Fine-tuning
@@ -99,7 +99,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from trl import SFTTrainer
 + from onebitllms import replace_linear_with_bitnet_linear, quantize_to_1bit
 
-model_id = "tiiuae/Falcon-E-1B-Base"
+model_id = "tiiuae/Falcon-E-3B-Instruct"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id, revision="prequantized")
 model = AutoModelForCausalLM.from_pretrained(