Statistics collection ━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 128/128 • 0:02:19 • 0:00:00
Mixed-Precision assignment ━━━━━━━━━━━━━━━━━━━━ 100% 154/154 • 0:00:01 • 0:00:00
INFO:nncf:Statistics of the bitwidth distribution:
┍━━━━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┑
│ Weight compression mode   │ % all parameters (layers)   │ % ratio-defining parameters (layers)   │
┝━━━━━━━━━━━━━━━━━━━━━━━━━━━┿━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┿━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┥
│ int8_asym, per-channel    │ 30% (19 / 156)              │ 20% (17 / 154)                         │
├───────────────────────────┼─────────────────────────────┼────────────────────────────────────────┤
│ int4_sym, group size 128  │ 70% (137 / 156)             │ 80% (137 / 154)                        │
┕━━━━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┙
Applying Weight Compression ━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% • 0:00:03 • 0:00:00
This model does not support `Cache` instances. `cache_implementation` (set to static) will be ignored.
Warmup...
Elapsed time:  36.76417016983032
<|system|>
You are a friendly chatbot who always responds in the style of a pirate</s> 
<|user|>
How many helicopters can a human eat in one sitting?</s> 
<|assistant|>
A human can eat around 10-12 helicopters in one sitting. However, it is not recommended to eat more than that as it can lead to overeating and weight gain.</s>
Process returncode = 0
{'word_count': 56}

Statistics collection ━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 128/128 • 0:02:19 • 0:00:00
Mixed-Precision assignment ━━━━━━━━━━━━━━━━━━━━ 100% 154/154 • 0:00:01 • 0:00:00
INFO:nncf:Statistics of the bitwidth distribution:
┍━━━━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┑
│ Weight compression mode   │ % all parameters (layers)   │ % ratio-defining parameters (layers)   │
┝━━━━━━━━━━━━━━━━━━━━━━━━━━━┿━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┿━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┥
│ int8_asym, per-channel    │ 30% (26 / 156)              │ 21% (24 / 154)                         │
├───────────────────────────┼─────────────────────────────┼────────────────────────────────────────┤
│ int4_sym, group size 128  │ 70% (130 / 156)             │ 79% (130 / 154)                        │
┕━━━━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┙
Applying Weight Compression ━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% • 0:00:03 • 0:00:00
This model does not support `Cache` instances. `cache_implementation` (set to static) will be ignored.
Warmup...
Elapsed time:  55.67981743812561
<|system|>
You are a friendly chatbot who always responds in the style of a pirate</s> 
<|user|>
How many helicopters can a human eat in one sitting?</s> 
<|assistant|>
A human can eat around 100-150 helicopters in one sitting, depending on their appetite and the quality of the food. However, it is not recommended to eat too many helicopters in one sitting as it can lead to overeating and weight gain.</s>
Process returncode = 0
{'word_count': 69}

Statistics collection ━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 128/128 • 0:00:40 • 0:00:00
Mixed-Precision assignment ━━━━━━━━━━━━━━━━━━━━ 100% 154/154 • 0:00:02 • 0:00:00
INFO:nncf:Statistics of the bitwidth distribution:
┍━━━━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┑
│ Weight compression mode   │ % all parameters (layers)   │ % ratio-defining parameters (layers)   │
┝━━━━━━━━━━━━━━━━━━━━━━━━━━━┿━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┿━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┥
│ int8_asym, per-channel    │ 30% (19 / 156)              │ 20% (17 / 154)                         │
├───────────────────────────┼─────────────────────────────┼────────────────────────────────────────┤
│ int4_sym, group size 128  │ 70% (137 / 156)             │ 80% (137 / 154)                        │
┕━━━━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┙
Applying Weight Compression ━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% • 0:00:06 • 0:00:00
Elapsed time:  3.1341938972473145
<|user|>
What is PyTorch?</s> 
<|assistant|>
PyTorch is a popular open-source machine learning library developed by Facebook AI Research. It is designed to be easy to use and provides a powerful set of tools for building and training deep learning models. PyTorch is built on top of the C++ programming language and is designed to be highly optimized for performance. It supports a wide range of machine learning algorithms, including neural networks, deep learning, and reinforcement learning. PyTorch is widely used in the machine learning community and
Process returncode = 0
{'word_count': 86}

Statistics collection ━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 128/128 • 0:00:40 • 0:00:00
Mixed-Precision assignment ━━━━━━━━━━━━━━━━━━━━ 100% 154/154 • 0:00:02 • 0:00:00
INFO:nncf:Statistics of the bitwidth distribution:
┍━━━━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┑
│ Weight compression mode   │ % all parameters (layers)   │ % ratio-defining parameters (layers)   │
┝━━━━━━━━━━━━━━━━━━━━━━━━━━━┿━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┿━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┥
│ int8_asym, per-channel    │ 30% (26 / 156)              │ 21% (24 / 154)                         │
├───────────────────────────┼─────────────────────────────┼────────────────────────────────────────┤
│ int4_sym, group size 128  │ 70% (130 / 156)             │ 79% (130 / 154)                        │
┕━━━━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┙
Applying Weight Compression ━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% • 0:00:06 • 0:00:00
Elapsed time:  3.2469756603240967
<|user|>
What is PyTorch?</s> 
<|assistant|>
PyTorch is a popular open-source machine learning library developed by Facebook AI Research. It is designed to be easy to use and provides a wide range of functionalities for deep learning applications. PyTorch is built on top of CUDA (Compute Unified Device Architecture) and supports various hardware platforms, including CPUs, GPUs, and TPUs (Tensor Processing Units). PyTorch is also compatible with other popular machine learning frameworks such as TensorFlow
Process returncode = 0
{'word_count': 74}