This model uses an 1.3 billion parameters model as base to be further fine-tuned on the same data as palmer. It works pretty good and even surpasses sota model on
hellaswag
.
evaluation
Model
ARC_C
HellaSwag
PIQA
Winogrande
tinyllama-2t
0.2807
0.5463
0.7067
0.5683
palmer-001
0.2807
0.5524
0.7106
0.5896
sheared-1.3b
0.2910
0.5935
0.7339
0.5809
no-prompt-1.3b
0.3157
0.6022
0.7334
0.5864
falcon-rw-1b-instruct-openorca (sota)
0.3362
0.5997
0.7394
0.6148
This model was trained on less than 25% of the dataset yet achieves competitive performance to current sota on open llm leaderboard.
training
Training took ~5 P100 gpu hours. It was trained on 15,000 gpt-4 shuffled samples. no-prompt was fine-tuned using lower learning rates ensuring it keeps as much general knowledge as possible.
prompt
no prompt
limitations
Hallucinations are frequent, just as any transformer model this size.
Runs of appvoid no-prompt-1.3b on huggingface.co
18
Total runs
-1
24-hour runs
-2
3-day runs
0
7-day runs
6
30-day runs
More Information About no-prompt-1.3b huggingface.co Model
no-prompt-1.3b huggingface.co is an AI model on huggingface.co that provides no-prompt-1.3b's model effect (), which can be used instantly with this appvoid no-prompt-1.3b model. huggingface.co supports a free trial of the no-prompt-1.3b model, and also provides paid use of the no-prompt-1.3b. Support call no-prompt-1.3b model through api, including Node.js, Python, http.
no-prompt-1.3b huggingface.co is an online trial and call api platform, which integrates no-prompt-1.3b's modeling effects, including api services, and provides a free online trial of no-prompt-1.3b, you can try no-prompt-1.3b online for free by clicking the link below.
appvoid no-prompt-1.3b online free url in huggingface.co:
no-prompt-1.3b is an open source model from GitHub that offers a free installation service, and any user can find no-prompt-1.3b on GitHub to install. At the same time, huggingface.co provides the effect of no-prompt-1.3b install, users can directly use no-prompt-1.3b installed effect in huggingface.co for debugging and trial. It also supports api for free installation.