Total runs:
63.1M
Run Growth:
-3.2M
Growth Rate:
-5.07%
Sponsored by
iMean AI Trip Planner
BAAI / AquilaChat2-34B
Model's Last Updated: July 13 2026
text-generation
Introduction of AquilaChat2-34B
Model Details of AquilaChat2-34B
English | 简体中文
We opensource our Aquila2 series, now including Aquila2 , the base language models, namely Aquila2-7B and Aquila2-34B , as well as AquilaChat2 , the chat models, namely AquilaChat2-7B and AquilaChat2-34B , as well as the long-text chat models, namely AquilaChat2-7B-16k and AquilaChat2-34B-16k
2023.10.25 🔥 AquilaChat2-34B v1.2 is based on the previous AquilaChat2-34B . The AquilaChat2-34B model is close to or exceeds the level of GPT3.5 in the subjective evaluation of 8 secondary ability dimensions.
The additional details of the Aquila model will be presented in the official technical report. Please stay tuned for updates on official channels.
Note
We have discovered a data leakage problem with the GSM8K test data in the pre-training task dataset. Therefore, the evaluation results of GSM8K have been removed from the evaluation results.
Upon thorough investigation and analysis, it was found that the data leakage occurred in the mathematical dataset A (over 2 million samples), recommended by a team we have collaborated with multiple times. This dataset includes the untreated GSM8K test set (1319 samples). The team only performed routine de-duplication and quality checks but did not conduct an extra filtering check for the presence of the GSM8K test data, resulting in this oversight.
Our team has always strictly adhered to the principle that training data should not include test data. Taking this lesson from the error caused by not thoroughly checking the source of external data, we have investigated all 2 trillion tokens of data for various test datasets, including WTM22（en-zh), CLUEWSC, Winograd, HellaSwag, OpenBookQA, PIQA, ARC-e, BUSTSM, BoolQ, TruthfulQA, RAFT, ChID, EPRSTMT, TNEWS, OCNLI, SEM-Chinese, MMLU, C-Eval, CMMLU, CSL and HumanEval.
Quick Start AquilaChat2-34B（Chat model）
1. Inference
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers import BitsAndBytesConfig
import torch
device = torch.device("cuda:0")
model_info = "BAAI/AquilaChat2-34B"
tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True)
quantization_config=BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_use_double_quant=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
)
model = AutoModelForCausalLM.from_pretrained(model_info, trust_remote_code=True, torch_dtype=torch.bfloat16,
# quantization_config=quantization_config, # Uncomment this line for 4bit quantization
)
model.eval()
model.to(device)
text = "请给出10个要到北京旅游的理由。"
from predict import predict
out = predict(model, text, tokenizer=tokenizer, max_gen_len=200, top_p=0.9,
seed=123, topk=15, temperature=1.0, sft=True, device=device,
model_name="AquilaChat2-34B")
print(out)
License
Aquila2 series open-source model is licensed under BAAI Aquila Model Licence Agreement
Runs of BAAI AquilaChat2-34B on huggingface.co
198
Total runs
-12
24-hour runs
-2
3-day runs
17
7-day runs
64
30-day runs
More Information About AquilaChat2-34B huggingface.co Model
Url of AquilaChat2-34B
AquilaChat2-34B huggingface.co Url
Provider of AquilaChat2-34B huggingface.co
Other API from BAAI
Updated:February 22 2024
Total runs:
17.1M
Run Growth:
-710.4K
Growth Rate:
-4.15%
Total runs:
10.2M
Run Growth:
-1.2M
Growth Rate:
-12.18%
Total runs:
9.8M
Run Growth:
-3.5M
Growth Rate:
-36.13%
Total runs:
4.7M
Run Growth:
-43.0K
Growth Rate:
-0.92%
Total runs:
2.4M
Run Growth:
-127.8K
Growth Rate:
-5.25%
Total runs:
734.0K
Run Growth:
-391.2K
Growth Rate:
-53.30%
Total runs:
639.8K
Run Growth:
-390.0K
Growth Rate:
-60.97%
Total runs:
327.1K
Run Growth:
64.9K
Growth Rate:
19.84%
Total runs:
200.3K
Run Growth:
-476.2K
Growth Rate:
-237.76%
Total runs:
162.0K
Run Growth:
3.4K
Growth Rate:
2.12%
Total runs:
82.5K
Run Growth:
-228.7K
Growth Rate:
-277.48%
Total runs:
58.6K
Run Growth:
-10.0K
Growth Rate:
-17.12%
Total runs:
16.6K
Run Growth:
531
Growth Rate:
3.20%
Total runs:
10.4K
Run Growth:
10.4K
Growth Rate:
100.00%
Total runs:
8.7K
Run Growth:
406
Growth Rate:
4.66%
Total runs:
8.7K
Run Growth:
455
Growth Rate:
5.23%
Total runs:
2.5K
Run Growth:
-4.0K
Growth Rate:
-159.22%
Total runs:
2.3K
Run Growth:
974
Growth Rate:
42.02%
Total runs:
2.3K
Run Growth:
253
Growth Rate:
11.07%
Total runs:
1.2K
Run Growth:
270
Growth Rate:
23.18%
Total runs:
830
Run Growth:
407
Growth Rate:
49.04%
Total runs:
771
Run Growth:
141
Growth Rate:
18.29%
Total runs:
736
Run Growth:
736
Growth Rate:
100.00%
Total runs:
664
Run Growth:
0
Growth Rate:
0.00%
Total runs:
644
Run Growth:
0
Growth Rate:
0.00%
Total runs:
461
Run Growth:
-159
Growth Rate:
-34.49%
Total runs:
317
Run Growth:
-437
Growth Rate:
-137.85%
Total runs:
232
Run Growth:
95
Growth Rate:
41.85%
Total runs:
204
Run Growth:
92
Growth Rate:
45.10%
Total runs:
196
Run Growth:
-2.0K
Growth Rate:
-1035.20%
Total runs:
193
Run Growth:
43
Growth Rate:
22.28%
Total runs:
186
Run Growth:
60
Growth Rate:
32.61%
Total runs:
182
Run Growth:
57
Growth Rate:
31.32%