Update README.md

README.md

@@ -50,7 +50,7 @@ Refer to the snippet below to run H1 models using 🤗 transformers:
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "tiiuae/Falcon-H1R-0.6B"
+model_id = "tiiuae/Falcon-H1-Tiny-R-0.6B"
 
 model = AutoModelForCausalLM.from_pretrained(
   model_id,
@@ -64,7 +64,7 @@ model = AutoModelForCausalLM.from_pretrained(
 or
 
 ```bash
-transformers serve tiiuae/Falcon-H1R-0.6B
+transformers serve tiiuae/Falcon-H1-Tiny-R-0.6B
 ```
 
 ### `llama.cpp`
@@ -74,14 +74,14 @@ You can find all GGUF files compatible with `llama.cpp` under [our official coll
 ```bash
 brew install llama.cpp 
 pip install huggingface_hub 
-hf download tiiuae/Falcon-H1R-0.6B-GGUF Falcon-H1R-0.6B-Q8_0.gguf --local-dir ./ 
-llama-cli ./Falcon-H1R-0.6B-Q8_0.gguf -cnv 
+hf download tiiuae/Falcon-H1-Tiny-R-0.6B-GGUF Falcon-H1-Tiny-R-0.6B-Q8_0.gguf --local-dir ./ 
+llama-cli ./Falcon-H1-Tiny-R-0.6B-Q8_0.gguf -cnv 
 ```
 
 ### `ollama`
 
 ```bash
-ollama run hf.co/tiiuae/Falcon-H1R-0.6B-GGUF:Q8_0 
+ollama run hf.co/tiiuae/Falcon-H1-Tiny-R-0.6B-GGUF:Q8_0 
 ```
 
 ### Apple `mlx` 
@@ -96,14 +96,14 @@ For vLLM, simply start a server by executing the command below:
 
 ```bash
 # pip install vllm>=0.9.0
-vllm serve tiiuae/Falcon-H1R-0.6B --tensor-parallel-size 2 --data-parallel-size 1
+vllm serve tiiuae/Falcon-H1-Tiny-R-0.6B --tensor-parallel-size 2 --data-parallel-size 1
 ```
 
 ### sglang
 
 ```bash
 python -m sglang.launch_server \
-  --model ttiiuae/Falcon-H1R-0.6B \
+  --model ttiiuae/Falcon-H1-Tiny-R-0.6B \
   --tensor-parallel-size 1 
 ```