Downloads · 30 days
55
6% of all-time downloads
RichardErkhov/mssma_-_ko-solar-10.7b-v0.1b-gguf
mssma_-_ko-solar-10.7b-v0.1b-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
55
6% of all-time downloads
All-time downloads
957
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.
ko-solar-10.7b-v0.1b - GGUF
| Name | Quant method | Size |
|---|---|---|
| ko-solar-10.7b-v0.1b.Q2_K.gguf | Q2_K | 3.79GB |
| ko-solar-10.7b-v0.1b.IQ3_XS.gguf | IQ3_XS | 4.21GB |
| ko-solar-10.7b-v0.1b.IQ3_S.gguf | IQ3_S | 4.44GB |
| ko-solar-10.7b-v0.1b.Q3_K_S.gguf | Q3_K_S | 4.41GB |
| ko-solar-10.7b-v0.1b.IQ3_M.gguf | IQ3_M | 4.58GB |
| ko-solar-10.7b-v0.1b.Q3_K.gguf | Q3_K | 4.91GB |
| ko-solar-10.7b-v0.1b.Q3_K_M.gguf | Q3_K_M | 4.91GB |
| ko-solar-10.7b-v0.1b.Q3_K_L.gguf | Q3_K_L | 5.33GB |
| ko-solar-10.7b-v0.1b.IQ4_XS.gguf | IQ4_XS | 5.5GB |
| ko-solar-10.7b-v0.1b.Q4_0.gguf | Q4_0 | 5.73GB |
| ko-solar-10.7b-v0.1b.IQ4_NL.gguf | IQ4_NL | 5.8GB |
| ko-solar-10.7b-v0.1b.Q4_K_S.gguf | Q4_K_S | 5.78GB |
| ko-solar-10.7b-v0.1b.Q4_K.gguf | Q4_K | 6.1GB |
| ko-solar-10.7b-v0.1b.Q4_K_M.gguf | Q4_K_M | 6.1GB |
| ko-solar-10.7b-v0.1b.Q4_1.gguf | Q4_1 | 6.35GB |
| ko-solar-10.7b-v0.1b.Q5_0.gguf | Q5_0 | 6.97GB |
| ko-solar-10.7b-v0.1b.Q5_K_S.gguf | Q5_K_S | 6.97GB |
| ko-solar-10.7b-v0.1b.Q5_K.gguf | Q5_K | 7.16GB |
| ko-solar-10.7b-v0.1b.Q5_K_M.gguf | Q5_K_M | 7.16GB |
| ko-solar-10.7b-v0.1b.Q5_1.gguf | Q5_1 | 7.59GB |
| ko-solar-10.7b-v0.1b.Q6_K.gguf | Q6_K | 8.29GB |
| ko-solar-10.7b-v0.1b.Q8_0.gguf | Q8_0 | 10.74GB |
library_name: transformers license: apache-2.0 language:
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
path = "mssma/ko-solar-10.7b-v0.1b"
model = AutoModelForCausalLM.from_pretrained(
path,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(path)