Downloads · 30 days
138
20% of all-time downloads
DeepMount00_-_Lexora-Lite-3B-gguf
RichardErkhov/DeepMount00_-_Lexora-Lite-3B-gguf
DeepMount00_-_Lexora-Lite-3B-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.
All-time downloads
703
Public
Repo size
36.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf42 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 27, 2024
- Updated
- Sep 27, 2024
- SHA
- 227eebb4
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Lexora-Lite-3B - GGUF
- Model creator: https://huggingface.co/DeepMount00/
- Original model: https://huggingface.co/DeepMount00/Lexora-Lite-3B/
| Name | Quant method | Size |
|---|---|---|
| Lexora-Lite-3B.Q2_K.gguf | Q2_K | 1.19GB |
| Lexora-Lite-3B.IQ3_XS.gguf | IQ3_XS | 1.3GB |
| Lexora-Lite-3B.IQ3_S.gguf | IQ3_S | 1.36GB |
| Lexora-Lite-3B.Q3_K_S.gguf | Q3_K_S | 1.35GB |
| Lexora-Lite-3B.IQ3_M.gguf | IQ3_M | 1.39GB |
| Lexora-Lite-3B.Q3_K.gguf | Q3_K | 1.48GB |
| Lexora-Lite-3B.Q3_K_M.gguf | Q3_K_M | 1.48GB |
| Lexora-Lite-3B.Q3_K_L.gguf | Q3_K_L | 1.59GB |
| Lexora-Lite-3B.IQ4_XS.gguf | IQ4_XS | 1.63GB |
| Lexora-Lite-3B.Q4_0.gguf | Q4_0 | 1.7GB |
| Lexora-Lite-3B.IQ4_NL.gguf | IQ4_NL | 1.71GB |
| Lexora-Lite-3B.Q4_K_S.gguf | Q4_K_S | 1.71GB |
| Lexora-Lite-3B.Q4_K.gguf | Q4_K | 1.8GB |
| Lexora-Lite-3B.Q4_K_M.gguf | Q4_K_M | 1.8GB |
| Lexora-Lite-3B.Q4_1.gguf | Q4_1 | 1.86GB |
| Lexora-Lite-3B.Q5_0.gguf | Q5_0 | 2.02GB |
| Lexora-Lite-3B.Q5_K_S.gguf | Q5_K_S | 2.02GB |
| Lexora-Lite-3B.Q5_K.gguf | Q5_K | 2.07GB |
| Lexora-Lite-3B.Q5_K_M.gguf | Q5_K_M | 2.07GB |
| Lexora-Lite-3B.Q5_1.gguf | Q5_1 | 2.18GB |
| Lexora-Lite-3B.Q6_K.gguf | Q6_K | 2.36GB |
| Lexora-Lite-3B.Q8_0.gguf | Q8_0 | 3.06GB |
Original model description:
library_name: transformers tags: []
How to Use
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "DeepMount00/Lexora-Lite-3B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
device_map="auto",
)
prompt = [{'role': 'user', 'content': """Marco ha comprato 5 scatole di cioccolatini. Ogni scatola contiene 12 cioccolatini. Ha deciso di dare 3 cioccolatini a ciascuno dei suoi 7 amici. Quanti cioccolatini gli rimarranno dopo averli distribuiti ai suoi amici?"""}]
inputs = tokenizer.apply_chat_template(
prompt,
add_generation_prompt=True,
return_tensors='pt'
)
tokens = model.generate(
inputs.to(model.device),
max_new_tokens=1024,
temperature=0.001,
do_sample=True
)
print(tokenizer.decode(tokens[0], skip_special_tokens=False))
- Created
- Sep 27, 2024
- Updated
- Sep 27, 2024