Quantization made by Richard Erkhov.

GetCode-slerp - GGUF

Model creator: https://huggingface.co/mavihsrr/
Original model: https://huggingface.co/mavihsrr/GetCode-slerp/

Name	Quant method	Size
GetCode-slerp.Q2_K.gguf	Q2_K	2.36GB
GetCode-slerp.IQ3_XS.gguf	IQ3_XS	2.6GB
GetCode-slerp.IQ3_S.gguf	IQ3_S	2.75GB
GetCode-slerp.Q3_K_S.gguf	Q3_K_S	2.75GB
GetCode-slerp.IQ3_M.gguf	IQ3_M	2.9GB
GetCode-slerp.Q3_K.gguf	Q3_K	3.07GB
GetCode-slerp.Q3_K_M.gguf	Q3_K_M	3.07GB
GetCode-slerp.Q3_K_L.gguf	Q3_K_L	3.35GB
GetCode-slerp.IQ4_XS.gguf	IQ4_XS	3.4GB
GetCode-slerp.Q4_0.gguf	Q4_0	3.56GB
GetCode-slerp.IQ4_NL.gguf	IQ4_NL	3.58GB
GetCode-slerp.Q4_K_S.gguf	Q4_K_S	3.59GB
GetCode-slerp.Q4_K.gguf	Q4_K	3.8GB
GetCode-slerp.Q4_K_M.gguf	Q4_K_M	3.8GB
GetCode-slerp.Q4_1.gguf	Q4_1	3.95GB
GetCode-slerp.Q5_0.gguf	Q5_0	4.33GB
GetCode-slerp.Q5_K_S.gguf	Q5_K_S	4.33GB
GetCode-slerp.Q5_K.gguf	Q5_K	4.45GB
GetCode-slerp.Q5_K_M.gguf	Q5_K_M	4.45GB
GetCode-slerp.Q5_1.gguf	Q5_1	4.72GB
GetCode-slerp.Q6_K.gguf	Q6_K	5.15GB
GetCode-slerp.Q8_0.gguf	Q8_0	6.67GB

Original model description:

license: apache-2.0 tags: - merge - mergekit - lazymergekit - codellama/CodeLlama-7b-Instruct-hf - Salesforce/codegen25-7b-multi

GetCode-slerp

GetCode-slerp is a merge of the following models using LazyMergekit:

🧩 Configuration

slices:
  - sources:
      - model: codellama/CodeLlama-7b-Instruct-hf
        layer_range: [0, 32]
      - model: Salesforce/codegen25-7b-multi
        layer_range: [0, 32]
merge_method: slerp
base_model: codellama/CodeLlama-7b-Instruct-hf
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mavihsrr/GetCode-slerp"
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"])