|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mistral-7B-v0.1")
|
|
tokenizer.encode("Hello this is a test")
|
|
|
|
|
|
|
|
|
|
|
|
configuration = MistralStarConfig()
|
|
|
|
|
|
model = MistralModel(configuration)
|
|
|
|
|
|
configuration = model.config
|
|
|
|
|
|
|
|
|
|
configuration = MistralQuietConfig()
|
|
|
|
|
|
model = MistralModel(configuration)
|
|
|
|
|
|
configuration = model.config
|
|
|
|
|
|
|
|
|
|
|
|
configuration = MistralConfig()
|
|
|
|
|
|
model = MistralModel(configuration)
|
|
|
|
|
|
configuration = model.config
|
|
|
|
|
|
|
|
|
|
|
|
model = MistralModel.from_pretrained("mistralai/Mistral-7B-v0.1")
|
|
|
|
model = MistralModel.from_pretrained("./test/saved_model/")
|
|
|
|
model = MistralModel.from_pretrained("mistralai/Mistral-7B-v0.1", output_attentions=True)
|
|
assert model.config.output_attentions == True
|
|
|
|
config = MistralConfig.from_json_file("./tf_model/my_tf_model_config.json")
|
|
model = MistralModel.from_pretrained("./tf_model/my_tf_checkpoint.ckpt.index", from_tf=True, config=config)
|
|
|
|
model = MistralModel.from_pretrained("mistralai/Mistral-7B-v0.1", from_flax=True)
|
|
|
|
|
|
|
|
|
|
model = MistralForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
|
|
tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mistral-7B-v0.1")
|
|
|
|
prompt = "Hey, are you conscious? Can you talk to me?"
|
|
inputs = tokenizer(prompt, return_tensors="pt")
|
|
|
|
|
|
generate_ids = model.generate(inputs.input_ids, max_length=30)
|
|
tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mistral-7B-v0.1")
|
|
model = MistralForSequenceClassification.from_pretrained("mistralai/Mistral-7B-v0.1")
|
|
|
|
inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
|
|
|
|
with torch.no_grad():
|
|
logits = model(**inputs).logits
|
|
|
|
predicted_class_id = logits.argmax().item()
|
|
|
|
|
|
num_labels = len(model.config.id2label)
|
|
model = MistralForSequenceClassification.from_pretrained("mistralai/Mistral-7B-v0.1", num_labels=num_labels)
|
|
|
|
labels = torch.tensor([1])
|
|
loss = model(**inputs, labels=labels).loss
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mistral-7B-v0.1")
|
|
model = MistralForSequenceClassification.from_pretrained("mistralai/Mistral-7B-v0.1", problem_type="multi_label_classification")
|
|
|
|
inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
|
|
|
|
with torch.no_grad():
|
|
logits = model(**inputs).logits
|
|
|
|
predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]
|
|
|
|
|
|
num_labels = len(model.config.id2label)
|
|
model = MistralForSequenceClassification.from_pretrained(
|
|
"mistralai/Mistral-7B-v0.1", num_labels=num_labels, problem_type="multi_label_classification"
|
|
)
|
|
|
|
labels = torch.sum(
|
|
torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1
|
|
).to(torch.float)
|
|
loss = model(**inputs, labels=labels).loss
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mistral-7B-v0.1")
|
|
model = MistralForTokenClassification.from_pretrained("mistralai/Mistral-7B-v0.1")
|
|
|
|
inputs = tokenizer(
|
|
"HuggingFace is a company based in Paris and New York", add_special_tokens=False, return_tensors="pt"
|
|
)
|
|
|
|
with torch.no_grad():
|
|
logits = model(**inputs).logits
|
|
|
|
predicted_token_class_ids = logits.argmax(-1)
|
|
|
|
|
|
|
|
|
|
predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]
|
|
predicted_tokens_classes
|
|
|
|
labels = predicted_token_class_ids
|
|
loss = model(**inputs, labels=labels).loss
|
|
round(loss.item(), 2)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mistral-7B-v0.1")
|
|
model = MistralForQuestionAnswering.from_pretrained("mistralai/Mistral-7B-v0.1")
|
|
|
|
question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
|
|
|
|
inputs = tokenizer(question, text, return_tensors="pt")
|
|
with torch.no_grad():
|
|
outputs = model(**inputs)
|
|
|
|
answer_start_index = outputs.start_logits.argmax()
|
|
answer_end_index = outputs.end_logits.argmax()
|
|
|
|
predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
|
|
|
|
|
|
target_start_index = torch.tensor([14])
|
|
target_end_index = torch.tensor([15])
|
|
|
|
outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index)
|
|
loss = outputs.loss
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
configuration = MixtralConfig()
|
|
|
|
|
|
model = MixtralModel(configuration)
|
|
|
|
|
|
configuration = model.config
|
|
|
|
|
|
|
|
|
|
|
|
model = MixtralForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-v0.1", device_map="auto")
|
|
tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mixtral-8x7B-v0.1")
|
|
|
|
prompt = "My favourite condiment is"
|
|
|
|
model_inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
|
|
model.to("cpu")
|
|
|
|
generated_ids = model.generate(**model_inputs, max_new_tokens=100, do_sample=True)
|
|
tokenizer.batch_decode(generated_ids)[0]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model = MixtralForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1", device_map="auto")
|
|
tokenizer = MistralTokenizerFast.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1")
|
|
|
|
messages = [
|
|
{"role": "user", "content": "What is your favourite condiment?"},
|
|
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
|
|
{"role": "user", "content": "Do you have mayonnaise recipes?"}
|
|
]
|
|
|
|
model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
|
|
|
|
generated_ids = model.generate(model_inputs, max_new_tokens=100, do_sample=True)
|
|
tokenizer.batch_decode(generated_ids)[0]
|
|
|
|
|
|
|