| .. |
|
custom_modeling
|
feat: add mistral model (#1071)
|
2023-09-28 09:55:47 +02:00 |
|
__init__.py
|
feat: add mistral model (#1071)
|
2023-09-28 09:55:47 +02:00 |
|
bloom.py
|
enable bfloat16 for cpu (#1034)
|
2023-09-19 17:19:28 +02:00 |
|
cache_manager.py
|
feat: add mistral model (#1071)
|
2023-09-28 09:55:47 +02:00 |
|
causal_lm.py
|
feat: format code (#1070)
|
2023-09-27 12:22:09 +02:00 |
|
flash_causal_lm.py
|
feat: add mistral model (#1071)
|
2023-09-28 09:55:47 +02:00 |
|
flash_llama.py
|
Add AWQ quantization inference support (#1019) (#1054)
|
2023-09-25 15:31:27 +02:00 |
|
flash_mistral.py
|
feat: add mistral model (#1071)
|
2023-09-28 09:55:47 +02:00 |
|
flash_neox.py
|
feat(server): Using `quantize_config.json` instead of GPTQ_BITS env variables. (#671)
|
2023-07-25 13:00:27 +02:00 |
|
flash_rw.py
|
Fix Falcon weight mapping for H2O.ai checkpoints (#953)
|
2023-08-31 21:15:14 +02:00 |
|
flash_santacoder.py
|
feat(server): Using `quantize_config.json` instead of GPTQ_BITS env variables. (#671)
|
2023-07-25 13:00:27 +02:00 |
|
galactica.py
|
Fix missing arguments in Galactica's from_pb (#1022)
|
2023-09-21 08:15:59 +02:00 |
|
gpt_neox.py
|
enable bfloat16 for cpu (#1034)
|
2023-09-19 17:19:28 +02:00 |
|
idefics.py
|
enable bfloat16 for cpu (#1034)
|
2023-09-19 17:19:28 +02:00 |
|
idefics_causal_lm.py
|
feat: format code (#1070)
|
2023-09-27 12:22:09 +02:00 |
|
model.py
|
feat: add mistral model (#1071)
|
2023-09-28 09:55:47 +02:00 |
|
mpt.py
|
enable bfloat16 for cpu (#1034)
|
2023-09-19 17:19:28 +02:00 |
|
opt.py
|
enable bfloat16 for cpu (#1034)
|
2023-09-19 17:19:28 +02:00 |
|
rw.py
|
enable bfloat16 for cpu (#1034)
|
2023-09-19 17:19:28 +02:00 |
|
santacoder.py
|
enable bfloat16 for cpu (#1034)
|
2023-09-19 17:19:28 +02:00 |
|
seq2seq_lm.py
|
feat: format code (#1070)
|
2023-09-27 12:22:09 +02:00 |
|
t5.py
|
enable bfloat16 for cpu (#1034)
|
2023-09-19 17:19:28 +02:00 |
|
types.py
|
Rebased #617 (#868)
|
2023-08-28 11:43:47 +02:00 |
3b56d7669b