Downloads · 30 days
71
5% of all-time downloads
heavytail_-_kullm-mistral-gguf
RichardErkhov/heavytail_-_kullm-mistral-gguf
heavytail_-_kullm-mistral-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
1.3K
Public
Repo size
72.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf85.7 GB · 100%
At a glance
- Access
- Public
- Created
- Nov 5, 2024
- Updated
- Nov 5, 2024
- SHA
- da7ac595
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
kullm-mistral - GGUF
- Model creator: https://huggingface.co/heavytail/
- Original model: https://huggingface.co/heavytail/kullm-mistral/
| Name | Quant method | Size |
|---|---|---|
| kullm-mistral.Q2_K.gguf | Q2_K | 2.53GB |
| kullm-mistral.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| kullm-mistral.Q3_K.gguf | Q3_K | 3.28GB |
| kullm-mistral.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| kullm-mistral.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| kullm-mistral.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| kullm-mistral.Q4_0.gguf | Q4_0 | 3.83GB |
| kullm-mistral.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| kullm-mistral.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| kullm-mistral.Q4_K.gguf | Q4_K | 4.07GB |
| kullm-mistral.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| kullm-mistral.Q4_1.gguf | Q4_1 | 4.24GB |
| kullm-mistral.Q5_0.gguf | Q5_0 | 4.65GB |
| kullm-mistral.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| kullm-mistral.Q5_K.gguf | Q5_K | 4.78GB |
| kullm-mistral.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| kullm-mistral.Q5_1.gguf | Q5_1 | 5.07GB |
| kullm-mistral.Q6_K.gguf | Q6_K | 5.53GB |
| kullm-mistral.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
license: apache-2.0 language:
- ko
KULLM project
- base model: mistralai/Mistral-7B-Instruct-v0.2
datasets
- KULLM dataset
- hand-crafted instruction data
Implementation Code
from transformers import (
AutoModelForCausalLM,
AutoTokenizer
)
import torch
repo = "heavytail/kullm-mistral"
model = AutoModelForCausalLM.from_pretrained(
repo,
torch_dtype=torch.float16,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)
Initial upload: 2024/01/28 20:30
- Created
- Nov 5, 2024
- Updated
- Nov 5, 2024