Update README.md

README.md

@@ -7,41 +7,34 @@ model-index:
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information Keras had access to. You should
-probably proofread and complete it, then remove this comment. -->
+Turns out that [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) only have safetensors. This repo
+is created to have the `.bin` files of the model.
 
-# Mistral-7B-Instruct-v0.3
+This repo is created by:
+```py
+model_id = "mistralai/Mistral-7B-Instruct-v0.3"
+model = AutoModelForCausalLM.from_pretrained(model_id)
+model.push_to_hub("ariG23498/Mistral-7B-Instruct-v0.3", safe_serialization=False)
+```
 
-This model is a fine-tuned version of [ariG23498/Mistral-7B-Instruct-v0.3](https://huggingface.co/ariG23498/Mistral-7B-Instruct-v0.3) on an unknown dataset.
-It achieves the following results on the evaluation set:
+This is due to the fact that the TensorFlow port cannot use safetensors and need bin files.
 
+You can use this model with TF like so:
+```py
+model_tf = TFAutoModelForCausalLM.from_pretrained("ariG23498/Mistral-7B-Instruct-v0.3", from_pt=True)
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
 
-## Model description
+prompt = "My favourite condiment is"
+model_inputs = tokenizer([prompt], return_tensors="tf")
+generated_ids = model_tf.generate(**model_inputs, max_new_tokens=100, do_sample=True)
+tokenizer.batch_decode(generated_ids)[0]
+```
 
-More information needed
+As soon as the safetensors and TensorFlow issue is sorted one can ditch this repository and use the official repository!
 
-## Intended uses & limitations
+Update:
 
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- optimizer: None
-- training_precision: float32
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.42.0.dev0
-- TensorFlow 2.11.0
-- Tokenizers 0.19.1
+I have uploaded the `.h5` models as well. You can now use the following and make the entire code work!
+```py
+model_tf = TFAutoModelForCausalLM.from_pretrained("ariG23498/Mistral-7B-Instruct-v0.3")
+```