Downloads · 30 days
57
3% of all-time downloads
RichardErkhov/RozGrov_-_NemoDori-v0.1-12B-MS-gguf
RozGrov_-_NemoDori-v0.1-12B-MS-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
57
3% of all-time downloads
All-time downloads
1.9K
Public
Repo size
141 GB
Likes
0
Public
Click a slice to open those files.
.gguf163 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
NemoDori-v0.1-12B-MS - GGUF
| Name | Quant method | Size |
|---|---|---|
| NemoDori-v0.1-12B-MS.Q2_K.gguf | Q2_K | 4.46GB |
| NemoDori-v0.1-12B-MS.IQ3_XS.gguf | IQ3_XS | 4.94GB |
| NemoDori-v0.1-12B-MS.IQ3_S.gguf | IQ3_S | 5.18GB |
| NemoDori-v0.1-12B-MS.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| NemoDori-v0.1-12B-MS.IQ3_M.gguf | IQ3_M | 5.33GB |
| NemoDori-v0.1-12B-MS.Q3_K.gguf | Q3_K | 5.67GB |
| NemoDori-v0.1-12B-MS.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| NemoDori-v0.1-12B-MS.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| NemoDori-v0.1-12B-MS.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| NemoDori-v0.1-12B-MS.Q4_0.gguf | Q4_0 | 6.59GB |
| NemoDori-v0.1-12B-MS.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| NemoDori-v0.1-12B-MS.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| NemoDori-v0.1-12B-MS.Q4_K.gguf | Q4_K | 6.96GB |
| NemoDori-v0.1-12B-MS.Q4_K_M.gguf | Q4_K_M | 6.96GB |
| NemoDori-v0.1-12B-MS.Q4_1.gguf | Q4_1 | 7.26GB |
| NemoDori-v0.1-12B-MS.Q5_0.gguf | Q5_0 | 7.93GB |
| NemoDori-v0.1-12B-MS.Q5_K_S.gguf | Q5_K_S | 7.93GB |
| NemoDori-v0.1-12B-MS.Q5_K.gguf | Q5_K | 8.13GB |
| NemoDori-v0.1-12B-MS.Q5_K_M.gguf | Q5_K_M | 8.13GB |
| NemoDori-v0.1-12B-MS.Q5_1.gguf | Q5_1 | 8.61GB |
| NemoDori-v0.1-12B-MS.Q6_K.gguf | Q6_K | 9.37GB |
| NemoDori-v0.1-12B-MS.Q8_0.gguf | Q8_0 | 12.13GB |
tags:
NemoDori-v0.1-12B-MS is a MODEL STOCK merge of the following models using LazyMergekit (see below for merge configuration. All credits to them.)
This is my 'first' merge model, just for testing purpose. I don't know what I'm doing, honestly...
My experience using this in SillyTavern:
ChatML works best so far. Llama3 and Mistral prompts work, but sometimes they speak for you. (ChatML may also speak for you, but not that often - simply re-generate.)
I use context and instruct from here (Credits to Virt-io.)
This is the preset I use for SillyTavern, it should be good enough. Tweak to your heart's content:
models:
- model: Sao10K/MN-12B-Lyra-v1
- model: Fizzarolli/MN-12b-Rosier-v1
- model: MarinaraSpaghetti/Nemomix-v4.0-12B
- model: aetherwiing/MN-12B-Starcannon-v2
merge_method: model_stock
base_model: aetherwiing/MN-12B-Starcannon-v2
dtype: bfloat16
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "RozGrov/NemoDori-v0.1-12B-MS"
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"])