423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-23 22:32:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

support InternLM

Browse Source 
Former-commit-id: a2f507c56238d7fb2670edbab52d6b275f245e27
This commit is contained in:
hiyouga 2023-07-07 11:02:28 +08:00
parent 50a27509a3
commit 8b4ef062b7
3 changed files with 15 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -9,6 +9,8 @@
## Changelog ## Changelog
[23/07/07] Now we support training the InternLM-7B model in this repo. Try `--model_name_or_path internlm/internlm-7b` argument to use the InternLM model. Remember to use `--prompt_template intern` argument when using the InternLM-chat model.
[23/07/05] Now we support training the Falcon-7B/40B models in this repo. Try `--model_name_or_path tiiuae/falcon-7b` and `--lora_target query_key_value` arguments to use the Falcon model. [23/07/05] Now we support training the Falcon-7B/40B models in this repo. Try `--model_name_or_path tiiuae/falcon-7b` and `--lora_target query_key_value` arguments to use the Falcon model.
[23/06/29] We provide a reproducible example of training a chat model using instruction-following datasets, see this [HuggingFace Repo](https://huggingface.co/hiyouga/baichuan-7b-sft) for details. [23/06/29] We provide a reproducible example of training a chat model using instruction-following datasets, see this [HuggingFace Repo](https://huggingface.co/hiyouga/baichuan-7b-sft) for details.

4
src/utils/seq2seq.py
View File

@ -104,8 +104,8 @@ class Seq2SeqPeftTrainer(PeftTrainer):
preds = np.where(predict_results.predictions != IGNORE_INDEX, predict_results.predictions, self.tokenizer.pad_token_id) preds = np.where(predict_results.predictions != IGNORE_INDEX, predict_results.predictions, self.tokenizer.pad_token_id)
labels = np.where(predict_results.label_ids != IGNORE_INDEX, predict_results.label_ids, self.tokenizer.pad_token_id) labels = np.where(predict_results.label_ids != IGNORE_INDEX, predict_results.label_ids, self.tokenizer.pad_token_id)
decoded_preds = self.tokenizer.batch_decode(preds, skip_special_tokens=True) decoded_preds = self.tokenizer.batch_decode(preds, skip_special_tokens=True, clean_up_tokenization_spaces=True)
decoded_labels = self.tokenizer.batch_decode(labels, skip_special_tokens=True) decoded_labels = self.tokenizer.batch_decode(labels, skip_special_tokens=True, clean_up_tokenization_spaces=True)
with open(output_prediction_file, "w", encoding="utf-8") as writer: with open(output_prediction_file, "w", encoding="utf-8") as writer:
res: List[str] = [] res: List[str] = []

11
src/utils/template.py
View File

@ -114,6 +114,17 @@ class Template:
use_history=True use_history=True
) )
elif self.name == "intern":
r"""
Supports: https://huggingface.co/internlm/internlm-chat-7b
"""
self._register_template(
prefix="",
prompt="<|User|>:{query}<eoh>\n<|Bot|>:",
sep="<eoa>\n",
use_history=True
)
else: else:
raise ValueError("Template {} does not exist.".format(self.name)) raise ValueError("Template {} does not exist.".format(self.name))