Update README.md

README.md

@@ -41,6 +41,40 @@ Mistral Nemo is a transformer model, with the following architecture choices:
 - **Vocabulary size:** 2**17 ~= 128k
 - **Rotary embeddings (theta = 1M)**
 
+### Mistral Inference
+
+
+#### Install
+
+It is recommended to use `mistralai/Mistral-Nemo-Base-2407` with [mistral-inference](https://github.com/mistralai/mistral-inference). 
+For HF transformers code snippets, please keep scrolling.
+
+```
+pip install mistral_inference
+```
+
+### Transformers
+
+> [!IMPORTANT]
+> NOTE: Until a new release has been made, you need to install transformers from source:
+> ```sh
+> pip install git+https://github.com/huggingface/transformers.git
+> ```
+
+If you want to use Hugging Face `transformers` to generate text, you can do something like this.
+
+```py
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model_id = "EpistemeAI2/Fireball-Mistral-Nemo-12B-Philos"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+inputs = tokenizer("Hello my name is", return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=20)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+> [!TIP]
+> Unlike previous Mistral models, Mistral Nemo requires smaller temperatures. We recommend to use a temperature of 0.3.
 
 # Uploaded  model