 Aleksander Majda
|
60d9a5e508
|
added chat template option, added support for qwen2
|
2024-04-20 01:02:02 +02:00 |
|
|
nazgut
|
2e60cf3778
|
add llama and mistral model support
|
2024-03-29 08:06:45 +01:00 |
|
|
Aleksander Majda
|
3ccea4b90a
|
add AdvOptionsConfig to GGUF models
|
2024-03-27 21:09:15 +01:00 |
|
|
Aleksander Majda
|
784b57e745
|
add GGUF basic support
|
2024-03-27 09:55:58 +01:00 |
|
|
Aleksander Majda
|
4027cdbfeb
|
small fixes
|
2024-03-27 00:49:23 +01:00 |
|
|
Aleksander Majda
|
1860706b82
|
added seed, added Output Node, added Quantization Config Node, moved extra options to AdvOptions Node
|
2024-03-26 23:14:38 +01:00 |
|
|
Aleksander Majda
|
23b1daa3c6
|
update README, set top_k min to 0
|
2024-03-25 00:49:32 +01:00 |
|
|
Aleksander Majda
|
da714612f8
|
add support for gpt_refact, added temperature, top_p, top_k, repetition_penalty, trust_remote_code, torch_dtype parrametrs
|
2024-03-25 00:12:13 +01:00 |
|
|
Aleksander Majda
|
5c30f040fa
|
fix model list in node
|
2024-03-24 10:11:42 +01:00 |
|
|
Aleksander Majda
|
74a5e5a322
|
add gpt2 model type, change models to models/LLM_checkpoints folder, remove tokenizer path
|
2024-03-23 18:44:00 +01:00 |
|
|
Aleksander Majda
|
9c732c9f60
|
fix wrong upload
|
2024-03-23 10:35:04 +01:00 |
|