Zamba2-1.2B
956
74
1.2B
license:apache-2.0
by
Zyphra
Other
OTHER
1.2B params
New
956 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
3GB+ RAM
Mobile
Laptop
Server
Quick Summary
Zamba2-1.2B is a hybrid model composed of state-space (Mamba) and transformer blocks. It broadly follows the Zamba architecture which consists of a Mamba backbo...
Device Compatibility
Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
2GB+ RAM
Code Examples
Inferencepythontransformers
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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/Zamba2-1.2B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B", 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
Production-ready inference API. Start free, scale to millions.
Try Free APIReplicate
One-click model deployment
Run models in the cloud with simple API. No DevOps required.
Deploy NowDisclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.