metadata

base_model:
  - rinna/gemma-2-Baku-2b-it
  - prithivMLmods/GWQ2b
library_name: transformers
tags:
  - mergekit
  - merge
license: gemma
inference: true
pipeline_tag: text-generation
widget:
  - messages:
      - role: user
        content: こんにちは！
  - messages:
      - role: user
        content: 魚を捌くのは難しいですか？
  - messages:
      - role: user
        content: ナイジェリアの首都はどこですか？
  - messages:
      - role: user
        content: hello!
  - messages:
      - role: user
        content: 貝は砂浜に落ちてるものですか？
  - messages:
      - role: user
        content: おはようございます。
  - messages:
      - role: user
        content: 錫はどういうものに使われますか？
  - messages:
      - role: user
        content: 露骨とあからさまが違う言葉であることを証明してください。
  - messages:
      - role: user
        content: 你好
  - messages:
      - role: user
        content: 魚を捌くのは難しいですか？
  - messages:
      - role: user
        content: Où se trouve Shinjuku ?
  - messages:
      - role: user
        content: Bonjour!

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]))