a slightly less experimental qlora instruct finetune of the gemma-2b base model. trained with unsloth.
benchmarks
gemma-2b-it
sappha-2b-v3
dolphin-2.8-gemma-2b
MMLU (five-shot)
36.98
38.02
37.89
HellaSwag (zero-shot)
49.22
51.70
47.79
PIQA (one-shot)
75.08
75.46
71.16
TruthfulQA (zero-shot)
37.51
31.65
37.15
prompt format
basic chatml:
<|im_start|>system
You are a useful and helpful AI assistant.<|im_end|>
<|im_start|>user
what are LLMs?<|im_end|>
<|im_start|>assistant
LLMs, or Large Language Models, are advanced artificial intelligence systems that can perform tasks similar to human language. They are trained on vast amounts of data and can understand and respond to human queries. LLMs are often used in various applications, such as language translation, text generation, and question answering.<|im_end|>
sappha-2b-v3 huggingface.co is an AI model on huggingface.co that provides sappha-2b-v3's model effect (), which can be used instantly with this Fizzarolli sappha-2b-v3 model. huggingface.co supports a free trial of the sappha-2b-v3 model, and also provides paid use of the sappha-2b-v3. Support call sappha-2b-v3 model through api, including Node.js, Python, http.
sappha-2b-v3 huggingface.co is an online trial and call api platform, which integrates sappha-2b-v3's modeling effects, including api services, and provides a free online trial of sappha-2b-v3, you can try sappha-2b-v3 online for free by clicking the link below.
Fizzarolli sappha-2b-v3 online free url in huggingface.co:
sappha-2b-v3 is an open source model from GitHub that offers a free installation service, and any user can find sappha-2b-v3 on GitHub to install. At the same time, huggingface.co provides the effect of sappha-2b-v3 install, users can directly use sappha-2b-v3 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.