output = llm(
"Once upon a time,",
max_tokens=512,
echo=True
)
print(output)
Made using Cultrix's Model, which can be found here.
NeuralTrix-7B-v1 is a merge of the following models using LazyMergekit:
It was then trained with DPO by Cultrix using:
I performed laser_snr_math on it afterwards to see if I could improve it.
🧩 Configuration
models:
- model: mistralai/Mistral-7B-v0.1
# no parameters necessary for base model
- model: mlabonne/OmniBeagle-7B
parameters:
density: 0.65
weight: 0.4
- model: flemmingmiguel/MBX-7B-v3
parameters:
density: 0.6
weight: 0.35
- model: AiMavenAi/AiMaven-Prometheus
parameters:
density: 0.6
weight: 0.35
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
dtype: float16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "CultriX/NeuralTrix-7B-v1"
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
- 96
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Kquant03/NeuralTrix-7B-dpo-laser-GGUF", filename="", )