add pip install fire to requirements.txt

[r4dm]

expand.sh for llama_pro not working by default without fire lib

proof:

(llama_factory) administrator@srv01:/home/jupyter/LLaMA-Factory/examples/extras/llama_pro$ bash expand.sh 
Traceback (most recent call last):
  File "/home/jupyter/LLaMA-Factory/examples/extras/llama_pro/../../../scripts/llama_pro.py", line 11, in <module>
    import fire
ModuleNotFoundError: No module named 'fire'
(llama_factory) administrator@srv01:/home/jupyter/LLaMA-Factory/examples/extras/llama_pro$ pip install fire
Collecting fire
  Downloading fire-0.6.0.tar.gz (88 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 88.4/88.4 kB 2.2 MB/s eta 0:00:00
  Preparing metadata (setup.py) ... done
Requirement already satisfied: six in /home/administrator/miniconda3/envs/llama_factory/lib/python3.10/site-packages (from fire) (1.16.0)
Collecting termcolor (from fire)
  Using cached termcolor-2.4.0-py3-none-any.whl.metadata (6.1 kB)
Using cached termcolor-2.4.0-py3-none-any.whl (7.7 kB)
Building wheels for collected packages: fire
  Building wheel for fire (setup.py) ... done
  Created wheel for fire: filename=fire-0.6.0-py2.py3-none-any.whl size=117033 sha256=5fd037731c4eae2b79333b9d97e6a25d8f2ee5e9921b22ea12ab73d65507bb34
  Stored in directory: /home/administrator/.cache/pip/wheels/d6/6d/5d/5b73fa0f46d01a793713f8859201361e9e581ced8c75e5c6a3
Successfully built fire
Installing collected packages: termcolor, fire
Successfully installed fire-0.6.0 termcolor-2.4.0
(llama_factory) administrator@srv01:/home/jupyter/LLaMA-Factory/examples/extras/llama_pro$ bash expand.sh 
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:00<00:00, 17.17it/s]
Add layer 0 copied from layer 0
Add layer 1 copied from layer 1
Add layer 2 copied from layer 2
Add layer 3 copied from layer 3
Add layer 4 expanded from layer 3
Add layer 5 copied from layer 4
Add layer 6 copied from layer 5
Add layer 7 copied from layer 6
Add layer 8 copied from layer 7
Add layer 9 expanded from layer 7
Add layer 10 copied from layer 8
Add layer 11 copied from layer 9
Add layer 12 copied from layer 10
Add layer 13 copied from layer 11
Add layer 14 expanded from layer 11
Add layer 15 copied from layer 12
Add layer 16 copied from layer 13
Add layer 17 copied from layer 14
Add layer 18 copied from layer 15
Add layer 19 expanded from layer 15
Add layer 20 copied from layer 16
Add layer 21 copied from layer 17
Add layer 22 copied from layer 18
Add layer 23 copied from layer 19
Add layer 24 expanded from layer 19
Add layer 25 copied from layer 20
Add layer 26 copied from layer 21
Add layer 27 copied from layer 22
Add layer 28 copied from layer 23
Add layer 29 expanded from layer 23
Add layer 30 copied from layer 24
Add layer 31 copied from layer 25
Add layer 32 copied from layer 26
Add layer 33 copied from layer 27
Add layer 34 expanded from layer 27
Add layer 35 copied from layer 28
Add layer 36 copied from layer 29
Add layer 37 copied from layer 30
Add layer 38 copied from layer 31
Add layer 39 expanded from layer 31
Save weights: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:20<00:00,  2.23s/it]
Model weights saved in ../../../models/Vikhr-7B-instruct_0.2-pro
Fine-tune this model with:
  --model_name_or_path ../../../models/Vikhr-7B-instruct_0.2-pro \
  --finetuning_type freeze \
  --name_module_trainable all \
  --num_layer_trainable 8 \
  --use_llama_pro
(llama_factory) administrator@srv01:/home/jupyter/LLaMA-Factory/examples/extras/llama_pro$ 

[hills-code]

Thanks!