Neo_7b-merge10

Neo_7b-merge10 is a merge of the following models using LazyMergekit:

🧩 Configuration

slices:
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [0, 0]
      - model: DewEfresh/neo_7b
        layer_range: [3, 3]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [1, 1]
      - model: DewEfresh/neo_7b
        layer_range: [3, 3]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [2, 2]
      - model: DewEfresh/neo_7b
        layer_range: [3, 3]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [4, 4]
      - model: DewEfresh/neo_7b
        layer_range: [7, 7]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [5, 5]
      - model: DewEfresh/neo_7b
        layer_range: [7, 7]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [6, 6]
      - model: DewEfresh/neo_7b
        layer_range: [7, 7]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [8, 8]
      - model: DewEfresh/neo_7b
        layer_range: [11, 11]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [9, 9]
      - model: DewEfresh/neo_7b
        layer_range: [11, 11]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [10, 10]
      - model: DewEfresh/neo_7b
        layer_range: [11, 11]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [12, 12]
      - model: DewEfresh/neo_7b
        layer_range: [15, 15]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [13, 13]
      - model: DewEfresh/neo_7b
        layer_range: [15, 15]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [14, 14]
      - model: DewEfresh/neo_7b
        layer_range: [15, 15]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [16, 16]
      - model: DewEfresh/neo_7b
        layer_range: [19, 19]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [17, 17]
      - model: DewEfresh/neo_7b
        layer_range: [19, 19]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [18, 18]
      - model: DewEfresh/neo_7b
        layer_range: [19, 19]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [20, 20]
      - model: DewEfresh/neo_7b
        layer_range: [23, 23]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [21, 21]
      - model: DewEfresh/neo_7b
        layer_range: [23, 23]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [22, 22]
      - model: DewEfresh/neo_7b
        layer_range: [23, 23]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [24, 24]
      - model: DewEfresh/neo_7b
        layer_range: [27, 27]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [25, 25]
      - model: DewEfresh/neo_7b
        layer_range: [27, 27]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [26, 26]
      - model: DewEfresh/neo_7b
        layer_range: [27, 27]
merge_method: slerp
base_model: DewEfresh/neo_7b
parameters:
  t: 0.5
dtype: bfloat16

πŸ’» Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "DewEfresh/Neo_7b-merge10"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
Downloads last month
128
Safetensors
Model size
395M params
Tensor type
BF16
Β·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for DewEfresh/Neo_7b-merge10

Base model

DewEfresh/neo_7b
Finetuned
(7)
this model