You can deploy this model and start earning money today!

RichardErkhov/
ludocomito_-_Minerva_3B_Ties_1.0-gguf

Name: ludocomito_-_Minerva_3B_Ties_1.0-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Minerva_3B_Ties_1.0 - GGUF

Model creator: https://huggingface.co/ludocomito/
Original model: https://huggingface.co/ludocomito/Minerva_3B_Ties_1.0/

Name	Quant method	Size
Minerva_3B_Ties_1.0.Q2_K.gguf	Q2_K	1.02GB
Minerva_3B_Ties_1.0.Q3_K_S.gguf	Q3_K_S	1.19GB
Minerva_3B_Ties_1.0.Q3_K.gguf	Q3_K	1.32GB
Minerva_3B_Ties_1.0.Q3_K_M.gguf	Q3_K_M	1.32GB
Minerva_3B_Ties_1.0.Q3_K_L.gguf	Q3_K_L	1.43GB
Minerva_3B_Ties_1.0.IQ4_XS.gguf	IQ4_XS	1.48GB
Minerva_3B_Ties_1.0.Q4_0.gguf	Q4_0	1.54GB
Minerva_3B_Ties_1.0.IQ4_NL.gguf	IQ4_NL	1.55GB
Minerva_3B_Ties_1.0.Q4_K_S.gguf	Q4_K_S	1.55GB
Minerva_3B_Ties_1.0.Q4_K.gguf	Q4_K	1.63GB
Minerva_3B_Ties_1.0.Q4_K_M.gguf	Q4_K_M	1.63GB
Minerva_3B_Ties_1.0.Q4_1.gguf	Q4_1	1.7GB
Minerva_3B_Ties_1.0.Q5_0.gguf	Q5_0	1.86GB
Minerva_3B_Ties_1.0.Q5_K_S.gguf	Q5_K_S	1.86GB
Minerva_3B_Ties_1.0.Q5_K.gguf	Q5_K	1.91GB
Minerva_3B_Ties_1.0.Q5_K_M.gguf	Q5_K_M	1.91GB
Minerva_3B_Ties_1.0.Q5_1.gguf	Q5_1	2.03GB
Minerva_3B_Ties_1.0.Q6_K.gguf	Q6_K	2.21GB
Minerva_3B_Ties_1.0.Q8_0.gguf	Q8_0	2.87GB

Original model description:

tags:

merge
mergekit
lazymergekit
mudler/Asinello-Minerva-3B-v0.1
mii-llm/minerva-chat-v0.1-alpha-sft base_model:
mudler/Asinello-Minerva-3B-v0.1
mii-llm/minerva-chat-v0.1-alpha-sft license: apache-2.0 language:
it

M_Moe_3x3B_TIES

M_Moe_3x3B_TIES is a merge of the following models using LazyMergekit:

🧩 Configuration

yaml

models:
  - model: sapienzanlp/Minerva-3B-base-v1.0
    # no parameters necessary for base model
  - model: mudler/Asinello-Minerva-3B-v0.1
    parameters:
      density: 0.5
      weight: 0.5
  - model: mii-llm/minerva-chat-v0.1-alpha-sft
    parameters:
      density: 0.5
      weight: 0.3
merge_method: ties
base_model: sapienzanlp/Minerva-3B-base-v1.0
parameters:
  normalize: true
dtype: bfloat16

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "ludocomito/M_Moe_3x3B_TIES"
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"])

RichardErkhov/ludocomito_-_Minerva_3B_Ties_1.0-gguf

Original model description:

M_Moe_3x3B_TIES

🧩 Configuration

💻 Usage

RichardErkhov/
ludocomito_-_Minerva_3B_Ties_1.0-gguf