Downloads · 30 days
96
8% of all-time downloads
RichardErkhov/chargoddard_-_loyal-piano-m7-cdpo-gguf
chargoddard_-_loyal-piano-m7-cdpo-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
96
8% of all-time downloads
All-time downloads
1.2K
Public
Repo size
78.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf91.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
loyal-piano-m7-cdpo - GGUF
| Name | Quant method | Size |
|---|---|---|
| loyal-piano-m7-cdpo.Q2_K.gguf | Q2_K | 2.53GB |
| loyal-piano-m7-cdpo.IQ3_XS.gguf | IQ3_XS | 1.73GB |
| loyal-piano-m7-cdpo.IQ3_S.gguf | IQ3_S | 2.96GB |
| loyal-piano-m7-cdpo.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| loyal-piano-m7-cdpo.IQ3_M.gguf | IQ3_M | 3.06GB |
| loyal-piano-m7-cdpo.Q3_K.gguf | Q3_K | 3.28GB |
| loyal-piano-m7-cdpo.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| loyal-piano-m7-cdpo.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| loyal-piano-m7-cdpo.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| loyal-piano-m7-cdpo.Q4_0.gguf | Q4_0 | 3.83GB |
| loyal-piano-m7-cdpo.IQ4_NL.gguf | IQ4_NL | 1.25GB |
| loyal-piano-m7-cdpo.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| loyal-piano-m7-cdpo.Q4_K.gguf | Q4_K | 4.07GB |
| loyal-piano-m7-cdpo.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| loyal-piano-m7-cdpo.Q4_1.gguf | Q4_1 | 4.24GB |
| loyal-piano-m7-cdpo.Q5_0.gguf | Q5_0 | 4.65GB |
| loyal-piano-m7-cdpo.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| loyal-piano-m7-cdpo.Q5_K.gguf | Q5_K | 4.78GB |
| loyal-piano-m7-cdpo.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| loyal-piano-m7-cdpo.Q5_1.gguf | Q5_1 | 5.07GB |
| loyal-piano-m7-cdpo.Q6_K.gguf | Q6_K | 5.53GB |
| loyal-piano-m7-cdpo.Q8_0.gguf | Q8_0 | 7.17GB |
license: cc-by-nc-4.0 datasets:
Trained for one epoch on ultrafeedback_binarized using cDPO. Evaluation pending.
Some initial benchmark results:
| Task | Version | Metric | Value | Stderr | |
|---|---|---|---|---|---|
| hellaswag | 0 | acc | 0.6621 | ± | 0.0047 |
| acc_norm | 0.8525 | ± | 0.0035 | ||
| arc_challenge | 0 | acc | 0.6348 | ± | 0.0141 |
| acc_norm | 0.6698 | ± | 0.0137 | ||
| winogrande | 0 | acc | 0.7861 | ± | 0.0115 |
| gsm8k | 0 | acc | 0.5694 | ± | 0.0136 |