Model
Phi-2 is a 2.7 billion parameter language model developed by Microsoft Research. The phi-2 model is best suited for prompts using the Question-Answer (QA) format, the chat format, and the code format.
Use the NGC CLI to download:
Copied!
6 Versions
06/13/2024 11:30 PM UTC1.47 GB Copied!
06/13/2024 11:30 PM UTC1.47 GB
Copied!
TRT Cloud Engine Properties
| Key | Value |
|---|---|
| cpu_arch | x86_64 |
| os | Windows |
| num_gpus | 1 |
| trtllm_version | 0.10.0 |
| max_batch_size | 1 |
| weightless | False |
| gpu | RTX4090 |
06/13/2024 11:29 PM UTC1.47 GB Copied!
06/13/2024 11:29 PM UTC1.47 GB
Copied!
TRT Cloud Engine Properties
| Key | Value |
|---|---|
| cpu_arch | x86_64 |
| os | Windows |
| num_gpus | 1 |
| trtllm_version | 0.10.0 |
| weight_stripped | False |
| max_batch_size | 1 |
| gpu | RTX4070 |
06/13/2024 11:29 PM UTC1.47 GB Copied!
06/13/2024 11:29 PM UTC1.47 GB
Copied!
TRT Cloud Engine Properties
| Key | Value |
|---|---|
| cpu_arch | x86_64 |
| os | Windows |
| num_gpus | 1 |
| trtllm_version | 0.10.0 |
| weight_stripped | False |
| max_batch_size | 1 |
| gpu | RTX4060TI |
06/13/2024 11:28 PM UTC1.47 GB Copied!
06/13/2024 11:28 PM UTC1.47 GB
Copied!
TRT Cloud Engine Properties
| Key | Value |
|---|---|
| cpu_arch | x86_64 |
| os | Windows |
| num_gpus | 1 |
| trtllm_version | 0.10.0 |
| max_batch_size | 1 |
| weightless | False |
| gpu | RTX3070 |
06/13/2024 11:28 PM UTC4.78 GB Copied!
06/13/2024 11:28 PM UTC4.78 GB
Copied!
TRT Cloud Engine Properties
| Key | Value |
|---|---|
| cpu_arch | x86_64 |
| os | Windows |
| num_gpus | 1 |
| trtllm_version | 0.10.0 |
| max_batch_size | 1 |
| weightless | False |
| gpu | RTX4090 |
bs1_fp16_RTX4070_windowsSelected06/13/2024 11:27 PM UTC4.78 GB Copied!
bs1_fp16_RTX4070_windowsSelected
06/13/2024 11:27 PM UTC4.78 GB
Copied!
TRT Cloud Engine Properties
| Key | Value |
|---|---|
| cpu_arch | x86_64 |
| os | Windows |
| num_gpus | 1 |
| trtllm_version | 0.10.0 |
| weight_stripped | False |
| max_batch_size | 1 |
| gpu | RTX4070 |