Downloads · 30 days
98
15% of all-time downloads
realPCH_-_ko_solra_merge-gguf
RichardErkhov/realPCH_-_ko_solra_merge-gguf
realPCH_-_ko_solra_merge-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.
All-time downloads
659
Public
Repo size
123 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf143 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 10, 2024
- Updated
- Oct 10, 2024
- SHA
- ecc64fa5
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
ko_solra_merge - GGUF
- Model creator: https://huggingface.co/realPCH/
- Original model: https://huggingface.co/realPCH/ko_solra_merge/
| Name | Quant method | Size |
|---|---|---|
| ko_solra_merge.Q2_K.gguf | Q2_K | 3.8GB |
| ko_solra_merge.IQ3_XS.gguf | IQ3_XS | 4.22GB |
| ko_solra_merge.IQ3_S.gguf | IQ3_S | 4.45GB |
| ko_solra_merge.Q3_K_S.gguf | Q3_K_S | 4.42GB |
| ko_solra_merge.IQ3_M.gguf | IQ3_M | 4.59GB |
| ko_solra_merge.Q3_K.gguf | Q3_K | 4.92GB |
| ko_solra_merge.Q3_K_M.gguf | Q3_K_M | 4.92GB |
| ko_solra_merge.Q3_K_L.gguf | Q3_K_L | 5.34GB |
| ko_solra_merge.IQ4_XS.gguf | IQ4_XS | 5.51GB |
| ko_solra_merge.Q4_0.gguf | Q4_0 | 5.74GB |
| ko_solra_merge.IQ4_NL.gguf | IQ4_NL | 5.8GB |
| ko_solra_merge.Q4_K_S.gguf | Q4_K_S | 5.78GB |
| ko_solra_merge.Q4_K.gguf | Q4_K | 6.1GB |
| ko_solra_merge.Q4_K_M.gguf | Q4_K_M | 6.1GB |
| ko_solra_merge.Q4_1.gguf | Q4_1 | 6.36GB |
| ko_solra_merge.Q5_0.gguf | Q5_0 | 6.98GB |
| ko_solra_merge.Q5_K_S.gguf | Q5_K_S | 6.98GB |
| ko_solra_merge.Q5_K.gguf | Q5_K | 7.17GB |
| ko_solra_merge.Q5_K_M.gguf | Q5_K_M | 7.17GB |
| ko_solra_merge.Q5_1.gguf | Q5_1 | 7.6GB |
| ko_solra_merge.Q6_K.gguf | Q6_K | 8.3GB |
| ko_solra_merge.Q8_0.gguf | Q8_0 | 10.75GB |
Original model description:
license: mit
Developed by chPark
Training Strategy
We fine-tuned this model based on yanolja/KoSOLAR-10.7B-v0.1 with various dataset
Run the model
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "realPCH/ko_solra_merge"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
text = "[INST] Put instruction here. [/INST]"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
- Created
- Oct 10, 2024
- Updated
- Oct 10, 2024