Wing Lian 521e62daf1 remove the bos token from dpo outputs (#1733) [skip ci] ...

* remove the bos token from dpo outputs

* don't forget to fix prompt_input_ids too

* use processing_class instead of tokenizer

* fix for processing class

2024-11-15 19:09:20 -05:00

..

cerebras

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

code-llama

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

colab-notebooks

upgrade to flash-attn 2.7.0 (#2048)

2024-11-14 06:59:25 -05:00

dbrx

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

deepseek-v2

upgrade liger to 0.4.0 (#1973)

2024-11-07 12:53:34 -05:00

falcon

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

gemma

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

gemma2

feat: update yml chat_template to specify dataset field (#2001) [skip ci]

2024-10-29 10:26:03 -04:00

gptj

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

jamba

feat: update yml chat_template to specify dataset field (#2001) [skip ci]

2024-10-29 10:26:03 -04:00

jeopardy-bot

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

llama-2

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

llama-3

upgrade liger to 0.4.0 (#1973)

2024-11-07 12:53:34 -05:00

llama-3-vision

Multimodal Vision Llama - rudimentary support (#1940)

2024-10-02 21:02:48 -04:00

mamba

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

mistral

Add example YAML file for training Mistral using DPO (#2029) [skip ci]

2024-11-13 10:06:25 -05:00

mpt-7b

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

openllama-3b

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

phi

feat: update yml chat_template to specify dataset field (#2001) [skip ci]

2024-10-29 10:26:03 -04:00

pythia

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

pythia-12b

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

qwen

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

qwen2

remove the bos token from dpo outputs (#1733) [skip ci]

2024-11-15 19:09:20 -05:00

redpajama

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

replit-3b

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

stablelm-2

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

starcoder2

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

tiny-llama

examples: fix tiny-llama pretrain yml syntax (#1840)

2024-08-21 13:37:51 -04:00

xgen-7b

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00

yi-34B-chat

update outputs path so that we can mount workspace to /workspace/data (#1623)

2024-05-15 12:44:13 -04:00