KULLM project

  • base model: Upstage/SOLAR-10.7B-Instruct-v1.0

datasets

  • KULLM dataset
  • hand-crafted instruction data

Implementation Code

from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer
)
import torch

repo = "heavytail/kullm-solar-S"
model = AutoModelForCausalLM.from_pretrained(
        repo,
        torch_dtype=torch.float16,
        device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)

Initial upload: 2024/01/28 21:00

Downloads last month
2,118
Safetensors
Model size
10.7B params
Tensor type
FP16
Β·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for heavytail/kullm-solar-S

Finetunes
1 model
Quantizations
1 model

Spaces using heavytail/kullm-solar-S 6