step-00029824-recurrence_full_512_0

3
2 languages
license:apache-2.0
by
tomg-group-umd
Language Model
OTHER
New
3 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Code Examples

Samplingtext
model.eval()
config = GenerationConfig(max_length=256, stop_strings=["<|end_text|>", "<|end_turn|>"], 
                          use_cache=True,
                          do_sample=False, temperature=None, top_k=None, top_p=None, min_p=None, 
                          return_dict_in_generate=True,
                          eos_token_id=65505,bos_token_id=65504,pad_token_id=65509)


input_ids = tokenizer.encode("The capital of Westphalia is", return_tensors="pt", add_special_tokens=True).to(device)
outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
Samplingtext
model.eval()
config = GenerationConfig(max_length=256, stop_strings=["<|end_text|>", "<|end_turn|>"], 
                          use_cache=True,
                          do_sample=False, temperature=None, top_k=None, top_p=None, min_p=None, 
                          return_dict_in_generate=True,
                          eos_token_id=65505,bos_token_id=65504,pad_token_id=65509)


input_ids = tokenizer.encode("The capital of Westphalia is", return_tensors="pt", add_special_tokens=True).to(device)
outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
Samplingtext
model.eval()
config = GenerationConfig(max_length=256, stop_strings=["<|end_text|>", "<|end_turn|>"], 
                          use_cache=True,
                          do_sample=False, temperature=None, top_k=None, top_p=None, min_p=None, 
                          return_dict_in_generate=True,
                          eos_token_id=65505,bos_token_id=65504,pad_token_id=65509)


input_ids = tokenizer.encode("The capital of Westphalia is", return_tensors="pt", add_special_tokens=True).to(device)
outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
Samplingtext
model.eval()
config = GenerationConfig(max_length=256, stop_strings=["<|end_text|>", "<|end_turn|>"], 
                          use_cache=True,
                          do_sample=False, temperature=None, top_k=None, top_p=None, min_p=None, 
                          return_dict_in_generate=True,
                          eos_token_id=65505,bos_token_id=65504,pad_token_id=65509)


input_ids = tokenizer.encode("The capital of Westphalia is", return_tensors="pt", add_special_tokens=True).to(device)
outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
Samplingtext
model.eval()
config = GenerationConfig(max_length=256, stop_strings=["<|end_text|>", "<|end_turn|>"], 
                          use_cache=True,
                          do_sample=False, temperature=None, top_k=None, top_p=None, min_p=None, 
                          return_dict_in_generate=True,
                          eos_token_id=65505,bos_token_id=65504,pad_token_id=65509)


input_ids = tokenizer.encode("The capital of Westphalia is", return_tensors="pt", add_special_tokens=True).to(device)
outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
Samplingtext
model.eval()
config = GenerationConfig(max_length=256, stop_strings=["<|end_text|>", "<|end_turn|>"], 
                          use_cache=True,
                          do_sample=False, temperature=None, top_k=None, top_p=None, min_p=None, 
                          return_dict_in_generate=True,
                          eos_token_id=65505,bos_token_id=65504,pad_token_id=65509)


input_ids = tokenizer.encode("The capital of Westphalia is", return_tensors="pt", add_special_tokens=True).to(device)
outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
Samplingtext
model.eval()
config = GenerationConfig(max_length=256, stop_strings=["<|end_text|>", "<|end_turn|>"], 
                          use_cache=True,
                          do_sample=False, temperature=None, top_k=None, top_p=None, min_p=None, 
                          return_dict_in_generate=True,
                          eos_token_id=65505,bos_token_id=65504,pad_token_id=65509)


input_ids = tokenizer.encode("The capital of Westphalia is", return_tensors="pt", add_special_tokens=True).to(device)
outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
Samplingtext
model.eval()
config = GenerationConfig(max_length=256, stop_strings=["<|end_text|>", "<|end_turn|>"], 
                          use_cache=True,
                          do_sample=False, temperature=None, top_k=None, top_p=None, min_p=None, 
                          return_dict_in_generate=True,
                          eos_token_id=65505,bos_token_id=65504,pad_token_id=65509)


input_ids = tokenizer.encode("The capital of Westphalia is", return_tensors="pt", add_special_tokens=True).to(device)
outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
Samplingtext
model.eval()
config = GenerationConfig(max_length=256, stop_strings=["<|end_text|>", "<|end_turn|>"], 
                          use_cache=True,
                          do_sample=False, temperature=None, top_k=None, top_p=None, min_p=None, 
                          return_dict_in_generate=True,
                          eos_token_id=65505,bos_token_id=65504,pad_token_id=65509)


input_ids = tokenizer.encode("The capital of Westphalia is", return_tensors="pt", add_special_tokens=True).to(device)
outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
Samplingtext
model.eval()
config = GenerationConfig(max_length=256, stop_strings=["<|end_text|>", "<|end_turn|>"], 
                          use_cache=True,
                          do_sample=False, temperature=None, top_k=None, top_p=None, min_p=None, 
                          return_dict_in_generate=True,
                          eos_token_id=65505,bos_token_id=65504,pad_token_id=65509)


input_ids = tokenizer.encode("The capital of Westphalia is", return_tensors="pt", add_special_tokens=True).to(device)
outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
Samplingtext
model.eval()
config = GenerationConfig(max_length=256, stop_strings=["<|end_text|>", "<|end_turn|>"], 
                          use_cache=True,
                          do_sample=False, temperature=None, top_k=None, top_p=None, min_p=None, 
                          return_dict_in_generate=True,
                          eos_token_id=65505,bos_token_id=65504,pad_token_id=65509)


input_ids = tokenizer.encode("The capital of Westphalia is", return_tensors="pt", add_special_tokens=True).to(device)
outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
Samplingtext
model.eval()
config = GenerationConfig(max_length=256, stop_strings=["<|end_text|>", "<|end_turn|>"], 
                          use_cache=True,
                          do_sample=False, temperature=None, top_k=None, top_p=None, min_p=None, 
                          return_dict_in_generate=True,
                          eos_token_id=65505,bos_token_id=65504,pad_token_id=65509)


input_ids = tokenizer.encode("The capital of Westphalia is", return_tensors="pt", add_special_tokens=True).to(device)
outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
first step:python
# first step:
past_key_values = None
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
past_key_values = outputs.past_key_values # Should be an instance of HuginnDynamicCache
# next step
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
first step:python
# first step:
past_key_values = None
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
past_key_values = outputs.past_key_values # Should be an instance of HuginnDynamicCache
# next step
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
first step:python
# first step:
past_key_values = None
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
past_key_values = outputs.past_key_values # Should be an instance of HuginnDynamicCache
# next step
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
first step:python
# first step:
past_key_values = None
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
past_key_values = outputs.past_key_values # Should be an instance of HuginnDynamicCache
# next step
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
first step:python
# first step:
past_key_values = None
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
past_key_values = outputs.past_key_values # Should be an instance of HuginnDynamicCache
# next step
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
first step:python
# first step:
past_key_values = None
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
past_key_values = outputs.past_key_values # Should be an instance of HuginnDynamicCache
# next step
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
first step:python
# first step:
past_key_values = None
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
past_key_values = outputs.past_key_values # Should be an instance of HuginnDynamicCache
# next step
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
first step:python
# first step:
past_key_values = None
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
past_key_values = outputs.past_key_values # Should be an instance of HuginnDynamicCache
# next step
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
first step:python
# first step:
past_key_values = None
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
past_key_values = outputs.past_key_values # Should be an instance of HuginnDynamicCache
# next step
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
first step:python
# first step:
past_key_values = None
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
past_key_values = outputs.past_key_values # Should be an instance of HuginnDynamicCache
# next step
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
first step:python
# first step:
past_key_values = None
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
past_key_values = outputs.past_key_values # Should be an instance of HuginnDynamicCache
# next step
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
first step:python
# first step:
past_key_values = None
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
past_key_values = outputs.past_key_values # Should be an instance of HuginnDynamicCache
# next step
outputs = model(input_ids=input_ids, use_cache=True, past_key_values=past_key_values)
pythontransformers
from transformers import TextStreamer
streamer = TextStreamer(tokenizer)

model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer,
                                     continuous_compute=False, criterion="kl", exit_threshold=5e-4, cache_kwargs={"lookup_strategy": "latest-m4"})
pythontransformers
from transformers import TextStreamer
streamer = TextStreamer(tokenizer)

model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer,
                                     continuous_compute=False, criterion="kl", exit_threshold=5e-4, cache_kwargs={"lookup_strategy": "latest-m4"})
pythontransformers
from transformers import TextStreamer
streamer = TextStreamer(tokenizer)

model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer,
                                     continuous_compute=False, criterion="kl", exit_threshold=5e-4, cache_kwargs={"lookup_strategy": "latest-m4"})
pythontransformers
from transformers import TextStreamer
streamer = TextStreamer(tokenizer)

model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer,
                                     continuous_compute=False, criterion="kl", exit_threshold=5e-4, cache_kwargs={"lookup_strategy": "latest-m4"})
pythontransformers
from transformers import TextStreamer
streamer = TextStreamer(tokenizer)

model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer,
                                     continuous_compute=False, criterion="kl", exit_threshold=5e-4, cache_kwargs={"lookup_strategy": "latest-m4"})
pythontransformers
from transformers import TextStreamer
streamer = TextStreamer(tokenizer)

model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer,
                                     continuous_compute=False, criterion="kl", exit_threshold=5e-4, cache_kwargs={"lookup_strategy": "latest-m4"})
pythontransformers
from transformers import TextStreamer
streamer = TextStreamer(tokenizer)

model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer,
                                     continuous_compute=False, criterion="kl", exit_threshold=5e-4, cache_kwargs={"lookup_strategy": "latest-m4"})
pythontransformers
from transformers import TextStreamer
streamer = TextStreamer(tokenizer)

model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer,
                                     continuous_compute=False, criterion="kl", exit_threshold=5e-4, cache_kwargs={"lookup_strategy": "latest-m4"})
pythontransformers
from transformers import TextStreamer
streamer = TextStreamer(tokenizer)

model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer,
                                     continuous_compute=False, criterion="kl", exit_threshold=5e-4, cache_kwargs={"lookup_strategy": "latest-m4"})
pythontransformers
from transformers import TextStreamer
streamer = TextStreamer(tokenizer)

model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer,
                                     continuous_compute=False, criterion="kl", exit_threshold=5e-4, cache_kwargs={"lookup_strategy": "latest-m4"})
pythontransformers
from transformers import TextStreamer
streamer = TextStreamer(tokenizer)

model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer,
                                     continuous_compute=False, criterion="kl", exit_threshold=5e-4, cache_kwargs={"lookup_strategy": "latest-m4"})
pythontransformers
from transformers import TextStreamer
streamer = TextStreamer(tokenizer)

model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer,
                                     continuous_compute=False, criterion="kl", exit_threshold=5e-4, cache_kwargs={"lookup_strategy": "latest-m4"})
Warmstart / Continuous CoTtext
model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer, continuous_compute=True)
Warmstart / Continuous CoTtext
model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer, continuous_compute=True)
Warmstart / Continuous CoTtext
model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer, continuous_compute=True)
Warmstart / Continuous CoTtext
model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer, continuous_compute=True)
Warmstart / Continuous CoTtext
model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer, continuous_compute=True)
Warmstart / Continuous CoTtext
model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer, continuous_compute=True)
Warmstart / Continuous CoTtext
model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer, continuous_compute=True)
Warmstart / Continuous CoTtext
model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer, continuous_compute=True)
Warmstart / Continuous CoTtext
model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer, continuous_compute=True)
Warmstart / Continuous CoTtext
model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer, continuous_compute=True)
Warmstart / Continuous CoTtext
model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer, continuous_compute=True)
Warmstart / Continuous CoTtext
model.generate_with_adaptive_compute(input_ids, config, num_steps=64, tokenizer=tokenizer, streamer=streamer, continuous_compute=True)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

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

Try Free API

Replicate

One-click model deployment

Easiest Setup

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

Deploy Now

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