|
--- |
|
library_name: transformers |
|
tags: [] |
|
--- |
|
|
|
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. |
|
|
|
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 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") |
|
|
|
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] |
|
``` |
|
|
|
As soon as the safetensors and TensorFlow issue is sorted one can ditch this repository and use the official repository! |
