Downloads · 30 days
12
0% of all-time downloads
chlee10/T3Q-Llama3-8B-dpo-v2.0
T3Q-Llama3-8B-dpo-v2.0 is a text generation model from chlee10. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Downloads · 30 days
12
0% of all-time downloads
All-time downloads
14.3K
Public
Parameters
8B
16.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.1 GB · 100%
From the Hugging Face model README
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
hf-causal-experimental (pretrained=chlee10/T3Q-Llama3-8B-dpo-v2.0,use_accelerate=true,trust_remote_code=true), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8
| Task | Version | Metric | Value | Stderr | |
|---|---|---|---|---|---|
| kobest_boolq | 0 | acc | 0.5150 | ± | 0.0133 |
| macro_f1 | 0.3669 | ± | 0.0090 | ||
| kobest_copa | 0 | acc | 0.6420 | ± | 0.0152 |
| macro_f1 | 0.6417 | ± | 0.0151 | ||
| kobest_hellaswag | 0 | acc | 0.4480 | ± | 0.0223 |
| acc_norm | 0.5720 | ± | 0.0221 | ||
| macro_f1 | 0.4455 | ± | 0.0223 | ||
| kobest_sentineg | 0 | acc | 0.6222 | ± | 0.0244 |
| macro_f1 | 0.5820 | ± | 0.0256 |