Downloads · 30 days
75
4% of all-time downloads
RichardErkhov/SJ-Donald_-_SJ-SOLAR-10.7b-DPO-gguf
SJ-Donald_-_SJ-SOLAR-10.7b-DPO-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
75
4% of all-time downloads
All-time downloads
1.8K
Public
Repo size
123 GB
Likes
0
Public
Click a slice to open those files.
.gguf143 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
SJ-SOLAR-10.7b-DPO - GGUF
| Name | Quant method | Size |
|---|---|---|
| SJ-SOLAR-10.7b-DPO.Q2_K.gguf | Q2_K | 3.8GB |
| SJ-SOLAR-10.7b-DPO.IQ3_XS.gguf | IQ3_XS | 4.22GB |
| SJ-SOLAR-10.7b-DPO.IQ3_S.gguf | IQ3_S | 4.45GB |
| SJ-SOLAR-10.7b-DPO.Q3_K_S.gguf | Q3_K_S | 4.42GB |
| SJ-SOLAR-10.7b-DPO.IQ3_M.gguf | IQ3_M | 4.59GB |
| SJ-SOLAR-10.7b-DPO.Q3_K.gguf | Q3_K | 4.92GB |
| SJ-SOLAR-10.7b-DPO.Q3_K_M.gguf | Q3_K_M | 4.92GB |
| SJ-SOLAR-10.7b-DPO.Q3_K_L.gguf | Q3_K_L | 5.34GB |
| SJ-SOLAR-10.7b-DPO.IQ4_XS.gguf | IQ4_XS | 5.51GB |
| SJ-SOLAR-10.7b-DPO.Q4_0.gguf | Q4_0 | 5.74GB |
| SJ-SOLAR-10.7b-DPO.IQ4_NL.gguf | IQ4_NL | 5.8GB |
| SJ-SOLAR-10.7b-DPO.Q4_K_S.gguf | Q4_K_S | 5.78GB |
| SJ-SOLAR-10.7b-DPO.Q4_K.gguf | Q4_K | 6.1GB |
| SJ-SOLAR-10.7b-DPO.Q4_K_M.gguf | Q4_K_M | 6.1GB |
| SJ-SOLAR-10.7b-DPO.Q4_1.gguf | Q4_1 | 6.36GB |
| SJ-SOLAR-10.7b-DPO.Q5_0.gguf | Q5_0 | 6.98GB |
| SJ-SOLAR-10.7b-DPO.Q5_K_S.gguf | Q5_K_S | 6.98GB |
| SJ-SOLAR-10.7b-DPO.Q5_K.gguf | Q5_K | 7.17GB |
| SJ-SOLAR-10.7b-DPO.Q5_K_M.gguf | Q5_K_M | 7.17GB |
| SJ-SOLAR-10.7b-DPO.Q5_1.gguf | Q5_1 | 7.6GB |
| SJ-SOLAR-10.7b-DPO.Q6_K.gguf | Q6_K | 8.3GB |
| SJ-SOLAR-10.7b-DPO.Q8_0.gguf | Q8_0 | 10.75GB |
license: cc-by-nc-4.0 tags:
SJ-Donald/SJ-SOLAR-10.7b-DPO is fine-tuned using DPO method.
Using Google CoLab A100
| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|---|---|---|---|---|---|---|
| 72.67 | 68.26 | 86.95 | 66.73 | 67.74 | 84.21 | 62.03 |
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
|---|---|---|---|---|---|
| 56.93 | 53.67 | 61.99 | 53.36 | 57.2 | 58.44 |
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = 'SJ-Donald/SJ-SOLAR-10.7b-DPO'
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
template = """### System:
{{system_content}}
### User:
{{question}}
### Assistant:
"""
You can use gguf model file here! -> SJ-Donald/SJ-SOLAR-10.7b-DPO-GGUF
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 72.67 |
| AI2 Reasoning Challenge (25-Shot) | 68.26 |
| HellaSwag (10-Shot) | 86.95 |
| MMLU (5-Shot) | 66.73 |
| TruthfulQA (0-shot) | 67.74 |
| Winogrande (5-shot) | 84.21 |
| GSM8k (5-shot) | 62.09 |