Downloads · 30 days
84
4% of all-time downloads
RichardErkhov/arunb74_-_Luxeai-anu-1-bit-70M-gguf
arunb74_-_Luxeai-anu-1-bit-70M-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
84
4% of all-time downloads
All-time downloads
2.3K
Public
Repo size
930 MB
Likes
0
Public
Click a slice to open those files.
.gguf1.1 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Luxeai-anu-1-bit-70M - GGUF
| Name | Quant method | Size |
|---|---|---|
| Luxeai-anu-1-bit-70M.Q2_K.gguf | Q2_K | 0.04GB |
| Luxeai-anu-1-bit-70M.IQ3_XS.gguf | IQ3_XS | 0.04GB |
| Luxeai-anu-1-bit-70M.IQ3_S.gguf | IQ3_S | 0.04GB |
| Luxeai-anu-1-bit-70M.Q3_K_S.gguf | Q3_K_S | 0.04GB |
| Luxeai-anu-1-bit-70M.IQ3_M.gguf | IQ3_M | 0.04GB |
| Luxeai-anu-1-bit-70M.Q3_K.gguf | Q3_K | 0.04GB |
| Luxeai-anu-1-bit-70M.Q3_K_M.gguf | Q3_K_M | 0.04GB |
| Luxeai-anu-1-bit-70M.Q3_K_L.gguf | Q3_K_L | 0.04GB |
| Luxeai-anu-1-bit-70M.IQ4_XS.gguf | IQ4_XS | 0.04GB |
| Luxeai-anu-1-bit-70M.Q4_0.gguf | Q4_0 | 0.04GB |
| Luxeai-anu-1-bit-70M.IQ4_NL.gguf | IQ4_NL | 0.04GB |
| Luxeai-anu-1-bit-70M.Q4_K_S.gguf | Q4_K_S | 0.04GB |
| Luxeai-anu-1-bit-70M.Q4_K.gguf | Q4_K | 0.04GB |
| Luxeai-anu-1-bit-70M.Q4_K_M.gguf | Q4_K_M | 0.04GB |
| Luxeai-anu-1-bit-70M.Q4_1.gguf | Q4_1 | 0.05GB |
| Luxeai-anu-1-bit-70M.Q5_0.gguf | Q5_0 | 0.05GB |
| Luxeai-anu-1-bit-70M.Q5_K_S.gguf | Q5_K_S | 0.05GB |
| Luxeai-anu-1-bit-70M.Q5_K.gguf | Q5_K | 0.05GB |
| Luxeai-anu-1-bit-70M.Q5_K_M.gguf | Q5_K_M | 0.05GB |
| Luxeai-anu-1-bit-70M.Q5_1.gguf | Q5_1 | 0.05GB |
| Luxeai-anu-1-bit-70M.Q6_K.gguf | Q6_K | 0.06GB |
| Luxeai-anu-1-bit-70M.Q8_0.gguf | Q8_0 | 0.07GB |
license: apache-2.0 language:
Luxeai-anu-1-bit-70M
The Luxeai-anu-1-bit-70M Large Language Model (LLM) is my first trial to implement one-bit LLM based on the original paper - "The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits". I have taken the pre-trained Mistral-7B-v0.3 and abideen/Cosmopedia-100k-pretrain dataset. I used Microsoft Azure Standard_NC6s_v3 6 cores, 112GB RAM, 736GB storage 1 x NVIDIA Tesla V100 to train this initial model. I will be training on a much bigger dataset once I get a sponshorship for a 8x DGX System. I have tested on a sub-set of the same dataset.
Please follow the below code to run and test it in Python Jupyter Notebook
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
from transformers.models.llama.modeling_llama import *
# Load the model
model = "arunb74/Luxeai-anu-1-bit-70M"
tokenizer = AutoTokenizer.from_pretrained(model)
model = AutoModelForCausalLM.from_pretrained(model)
# Create a text generation pipeline
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
device_map="auto"
)
prompt = "The LISA Pathfinder scientific collaboration will meet in Trento"
sequences = pipe(
f"<s>[INST] {prompt} [/INST]",
do_sample=True,
max_new_tokens=100,
temperature=0.7,
top_k=50,
top_p=0.95,
num_return_sequences=1,
)
print(sequences[0]['generated_text'])
"""
The output will be as follows - <s>[INST] The LISA Pathfinder scientific collaboration will meet in Trento [/INST]
The LISA Pathfinder Biology, a leading provider of biochemistry and molecular biology, provides a comprehensive understanding of the mechanisms and mechanisms of the LISA pathways. The LISA Pathfinder Biology, a researcher specializing in molecular biology, is a clinical trial of the disease, and its pathophysiology, and a combination of the most commonly used and widely used treatments. It is a relatively simple procedure that involves two steps.
# I need community members to help me further for feedback, suitable dataset for further training, testing, evaluation.
"""