github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-01 17:17:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

[Chat] fix readme (#5989)

Browse Source 
* fix readme

* fix readme, tokenization fully tested

* fix readme, tokenization fully tested

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: root <root@notebook-8f919155-6035-47b4-9c6f-1be133b9e2c9-0.notebook-8f919155-6035-47b4-9c6f-1be133b9e2c9.colossal-ai.svc.cluster.local>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
YeAnbang
2024-08-12 14:55:17 +08:00
committed by GitHub
parent b4d2377d4c
commit ed97d3a5d3
7 changed files with 38 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
applications/ColossalChat/examples/README.md
View File

@@ -462,26 +462,24 @@ Stage1 is supervised instructs fine-tuning (SFT). This step is a crucial part of
#### Step 1: Data Collection
The first step in Stage 1 is to collect a dataset of human demonstrations of the following format.
The first step in Stage 1 is to collect a dataset of human demonstrations of the following JSONL format.
```json
[
{"messages":
[
{
"from": "user",
"content": "what are some pranks with a pen i can do?"
},
{
"from": "assistant",
"content": "Are you looking for practical joke ideas?"
},
...
]
{"messages":
[
{
"from": "user",
"content": "what are some pranks with a pen i can do?"
},
{
"from": "assistant",
"content": "Are you looking for practical joke ideas?"
},
...
]
]
},
...
```

1
applications/ColossalChat/examples/inference/inference.py
View File

@@ -151,7 +151,6 @@ def main(args):
chat_io.prompt_for_output("assistant")
prompt = conv.get_prompt(add_generation_prompt=True)
print(prompt + "<end_of_prompt>")
input_ids = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)["input_ids"].to(
torch.cuda.current_device()
)

2
applications/ColossalChat/examples/training_scripts/train_ppo.py
View File

@@ -502,7 +502,7 @@ if __name__ == "__main__":
parser.add_argument("--disable_loss_mask", default=False, action="store_true")
parser.add_argument("--max_length", type=int, default=2048)
parser.add_argument("--max_seq_len", type=int, default=256)
parser.add_argument("--log_dir", default="logs", type=str)
parser.add_argument("--log_dir", default=None, type=str)
parser.add_argument("--use_wandb", default=False, action="store_true")
parser.add_argument("--grad_checkpoint", default=False, action="store_true")
parser.add_argument("--use_flash_attn", default=False, action="store_true")