YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
STOCK_SOLAR-10.7B - GGUF
- Model creator: https://huggingface.co/kihoonlee/
- Original model: https://huggingface.co/kihoonlee/STOCK_SOLAR-10.7B/
| Name | Quant method | Size |
|---|---|---|
| STOCK_SOLAR-10.7B.Q2_K.gguf | Q2_K | 3.73GB |
| STOCK_SOLAR-10.7B.IQ3_XS.gguf | IQ3_XS | 4.14GB |
| STOCK_SOLAR-10.7B.IQ3_S.gguf | IQ3_S | 4.37GB |
| STOCK_SOLAR-10.7B.Q3_K_S.gguf | Q3_K_S | 4.34GB |
| STOCK_SOLAR-10.7B.IQ3_M.gguf | IQ3_M | 4.51GB |
| STOCK_SOLAR-10.7B.Q3_K.gguf | Q3_K | 4.84GB |
| STOCK_SOLAR-10.7B.Q3_K_M.gguf | Q3_K_M | 4.84GB |
| STOCK_SOLAR-10.7B.Q3_K_L.gguf | Q3_K_L | 5.26GB |
| STOCK_SOLAR-10.7B.IQ4_XS.gguf | IQ4_XS | 5.43GB |
| STOCK_SOLAR-10.7B.Q4_0.gguf | Q4_0 | 5.66GB |
| STOCK_SOLAR-10.7B.IQ4_NL.gguf | IQ4_NL | 5.72GB |
| STOCK_SOLAR-10.7B.Q4_K_S.gguf | Q4_K_S | 5.7GB |
| STOCK_SOLAR-10.7B.Q4_K.gguf | Q4_K | 6.02GB |
| STOCK_SOLAR-10.7B.Q4_K_M.gguf | Q4_K_M | 6.02GB |
| STOCK_SOLAR-10.7B.Q4_1.gguf | Q4_1 | 6.27GB |
| STOCK_SOLAR-10.7B.Q5_0.gguf | Q5_0 | 6.89GB |
| STOCK_SOLAR-10.7B.Q5_K_S.gguf | Q5_K_S | 6.89GB |
| STOCK_SOLAR-10.7B.Q5_K.gguf | Q5_K | 7.08GB |
| STOCK_SOLAR-10.7B.Q5_K_M.gguf | Q5_K_M | 7.08GB |
| STOCK_SOLAR-10.7B.Q5_1.gguf | Q5_1 | 7.51GB |
| STOCK_SOLAR-10.7B.Q6_K.gguf | Q6_K | 8.2GB |
| STOCK_SOLAR-10.7B.Q8_0.gguf | Q8_0 | 10.62GB |
Original model description:
library_name: transformers license: apache-2.0
This model was developed using Model Stock.
USAGE
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("kihoonlee/stock-solar-10.7b")
model = AutoModelForCausalLM.from_pretrained("kihoonlee/stock-solar-10.7b")
To use this model, either instruct tuning or fine tuning needs to be performed.
- Downloads last month
- 160