Zamba2-2.7B

Name: Zamba2-2.7B
Author: Zyphra

176

2.7B

license:apache-2.0

Zyphra

Language Model

OTHER

2.7B params

New

176 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

7GB+ RAM

Mobile

Laptop

Server

Quick Summary

Zamba2-2.7B is a hybrid model composed of state-space and transformer blocks. It broadly follows the Zamba architecture which consists of a Mamba backbone alter...

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

3GB+ RAM

Code Examples

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B", device_map="cuda", torch_dtype=torch.bfloat16)

input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.