Sakalti/SJT-2B-V1.1

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using prithivMLmods/GWQ2b as a base.

Models Merged

The following models were included in the merge:

• rinna/gemma-2-Baku-2b-it

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: rinna/gemma-2-Baku-2b-it
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: prithivMLmods/GWQ2b
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
dtype: float16

sample

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/GWQ2b")
model = AutoModelForCausalLM.from_pretrained(
    "Sakalti/SJT-2B-V1.1",
    device_map="auto",
    torch_dtype=torch.float16,
)

input_text = "おはようこざいます！。"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=200, temperature=0.7)
print(tokenizer.decode(outputs[0]))