Downloads · 30 days
116
11% of all-time downloads
RichardErkhov/SJ-Donald_-_SOLAR-10.7B-slerp-gguf
SJ-Donald_-_SOLAR-10.7B-slerp-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
116
11% of all-time downloads
All-time downloads
1.1K
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.
SOLAR-10.7B-slerp - GGUF
| Name | Quant method | Size |
|---|---|---|
| SOLAR-10.7B-slerp.Q2_K.gguf | Q2_K | 3.8GB |
| SOLAR-10.7B-slerp.IQ3_XS.gguf | IQ3_XS | 4.22GB |
| SOLAR-10.7B-slerp.IQ3_S.gguf | IQ3_S | 4.45GB |
| SOLAR-10.7B-slerp.Q3_K_S.gguf | Q3_K_S | 4.42GB |
| SOLAR-10.7B-slerp.IQ3_M.gguf | IQ3_M | 4.59GB |
| SOLAR-10.7B-slerp.Q3_K.gguf | Q3_K | 4.92GB |
| SOLAR-10.7B-slerp.Q3_K_M.gguf | Q3_K_M | 4.92GB |
| SOLAR-10.7B-slerp.Q3_K_L.gguf | Q3_K_L | 5.34GB |
| SOLAR-10.7B-slerp.IQ4_XS.gguf | IQ4_XS | 5.51GB |
| SOLAR-10.7B-slerp.Q4_0.gguf | Q4_0 | 5.74GB |
| SOLAR-10.7B-slerp.IQ4_NL.gguf | IQ4_NL | 5.8GB |
| SOLAR-10.7B-slerp.Q4_K_S.gguf | Q4_K_S | 5.78GB |
| SOLAR-10.7B-slerp.Q4_K.gguf | Q4_K | 6.1GB |
| SOLAR-10.7B-slerp.Q4_K_M.gguf | Q4_K_M | 6.1GB |
| SOLAR-10.7B-slerp.Q4_1.gguf | Q4_1 | 6.36GB |
| SOLAR-10.7B-slerp.Q5_0.gguf | Q5_0 | 6.98GB |
| SOLAR-10.7B-slerp.Q5_K_S.gguf | Q5_K_S | 6.98GB |
| SOLAR-10.7B-slerp.Q5_K.gguf | Q5_K | 7.17GB |
| SOLAR-10.7B-slerp.Q5_K_M.gguf | Q5_K_M | 7.17GB |
| SOLAR-10.7B-slerp.Q5_1.gguf | Q5_1 | 7.6GB |
| SOLAR-10.7B-slerp.Q6_K.gguf | Q6_K | 8.3GB |
| SOLAR-10.7B-slerp.Q8_0.gguf | Q8_0 | 10.75GB |
language:
SOLAR-10.7B-slerp is a merge of the following models using mergekit:
https://github.com/sunjin7725/SOLAR-10.7b-slerp
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
|---|---|---|---|---|---|
| 56.93 | 53.58 | 62.03 | 53.31 | 57.16 | 58.56 |
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = 'SJ-Donald/SOLAR-10.7B-slerp'
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
slices:
- sources:
- model: LDCC/LDCC-SOLAR-10.7B
layer_range: [0, 48]
- model: upstage/SOLAR-10.7B-Instruct-v1.0
layer_range: [0, 48]
merge_method: slerp
base_model: upstage/SOLAR-10.7B-Instruct-v1.0
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
tokenizer_source: union
dtype: float16
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 72.58 |
| AI2 Reasoning Challenge (25-Shot) | 68.17 |
| HellaSwag (10-Shot) | 86.91 |
| MMLU (5-Shot) | 66.73 |
| TruthfulQA (0-shot) | 67.42 |
| Winogrande (5-shot) | 84.06 |
| GSM8k (5-shot) | 62.17 |