Downloads · 30 days
4
1% of all-time downloads
DeepMount00_-_Lexora-Medium-7B-gguf
RichardErkhov/DeepMount00_-_Lexora-Medium-7B-gguf
DeepMount00_-_Lexora-Medium-7B-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
584
Public
Repo size
88.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf102 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 3, 2024
- Updated
- Oct 4, 2024
- SHA
- 1157d199
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Lexora-Medium-7B - GGUF
- Model creator: https://huggingface.co/DeepMount00/
- Original model: https://huggingface.co/DeepMount00/Lexora-Medium-7B/
| Name | Quant method | Size |
|---|---|---|
| Lexora-Medium-7B.Q2_K.gguf | Q2_K | 2.81GB |
| Lexora-Medium-7B.IQ3_XS.gguf | IQ3_XS | 3.12GB |
| Lexora-Medium-7B.IQ3_S.gguf | IQ3_S | 3.26GB |
| Lexora-Medium-7B.Q3_K_S.gguf | Q3_K_S | 3.25GB |
| Lexora-Medium-7B.IQ3_M.gguf | IQ3_M | 3.33GB |
| Lexora-Medium-7B.Q3_K.gguf | Q3_K | 3.55GB |
| Lexora-Medium-7B.Q3_K_M.gguf | Q3_K_M | 3.55GB |
| Lexora-Medium-7B.Q3_K_L.gguf | Q3_K_L | 3.81GB |
| Lexora-Medium-7B.IQ4_XS.gguf | IQ4_XS | 3.96GB |
| Lexora-Medium-7B.Q4_0.gguf | Q4_0 | 4.13GB |
| Lexora-Medium-7B.IQ4_NL.gguf | IQ4_NL | 4.16GB |
| Lexora-Medium-7B.Q4_K_S.gguf | Q4_K_S | 4.15GB |
| Lexora-Medium-7B.Q4_K.gguf | Q4_K | 4.36GB |
| Lexora-Medium-7B.Q4_K_M.gguf | Q4_K_M | 4.36GB |
| Lexora-Medium-7B.Q4_1.gguf | Q4_1 | 4.54GB |
| Lexora-Medium-7B.Q5_0.gguf | Q5_0 | 4.95GB |
| Lexora-Medium-7B.Q5_K_S.gguf | Q5_K_S | 4.95GB |
| Lexora-Medium-7B.Q5_K.gguf | Q5_K | 5.07GB |
| Lexora-Medium-7B.Q5_K_M.gguf | Q5_K_M | 5.07GB |
| Lexora-Medium-7B.Q5_1.gguf | Q5_1 | 5.36GB |
| Lexora-Medium-7B.Q6_K.gguf | Q6_K | 5.82GB |
| Lexora-Medium-7B.Q8_0.gguf | Q8_0 | 7.54GB |
Original model description:
library_name: transformers license: apache-2.0 language:
- it
- en
How to Use
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "DeepMount00/Lexora-Medium-7B"
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
- Oct 3, 2024
- Updated
- Oct 4, 2024