You can deploy this model and start earning money today!

RichardErkhov/
deepnet_-_SN29-C00-llama-HK1-1-gguf

Name: deepnet_-_SN29-C00-llama-HK1-1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

SN29-C00-llama-HK1-1 - GGUF

Model creator: https://huggingface.co/deepnet/
Original model: https://huggingface.co/deepnet/SN29-C00-llama-HK1-1/

Name	Quant method	Size
SN29-C00-llama-HK1-1.Q2_K.gguf	Q2_K	2.72GB
SN29-C00-llama-HK1-1.IQ3_XS.gguf	IQ3_XS	2.99GB
SN29-C00-llama-HK1-1.IQ3_S.gguf	IQ3_S	3.12GB
SN29-C00-llama-HK1-1.Q3_K_S.gguf	Q3_K_S	3.11GB
SN29-C00-llama-HK1-1.IQ3_M.gguf	IQ3_M	3.2GB
SN29-C00-llama-HK1-1.Q3_K.gguf	Q3_K	3.38GB
SN29-C00-llama-HK1-1.Q3_K_M.gguf	Q3_K_M	3.38GB
SN29-C00-llama-HK1-1.Q3_K_L.gguf	Q3_K_L	3.54GB
SN29-C00-llama-HK1-1.IQ4_XS.gguf	IQ4_XS	3.62GB
SN29-C00-llama-HK1-1.Q4_0.gguf	Q4_0	3.71GB
SN29-C00-llama-HK1-1.IQ4_NL.gguf	IQ4_NL	3.75GB
SN29-C00-llama-HK1-1.Q4_K_S.gguf	Q4_K_S	3.91GB
SN29-C00-llama-HK1-1.Q4_K.gguf	Q4_K	4.2GB
SN29-C00-llama-HK1-1.Q4_K_M.gguf	Q4_K_M	4.2GB
SN29-C00-llama-HK1-1.Q4_1.gguf	Q4_1	4.09GB
SN29-C00-llama-HK1-1.Q5_0.gguf	Q5_0	4.46GB
SN29-C00-llama-HK1-1.Q5_K_S.gguf	Q5_K_S	4.56GB
SN29-C00-llama-HK1-1.Q5_K.gguf	Q5_K	4.8GB
SN29-C00-llama-HK1-1.Q5_K_M.gguf	Q5_K_M	4.8GB
SN29-C00-llama-HK1-1.Q5_1.gguf	Q5_1	4.84GB
SN29-C00-llama-HK1-1.Q6_K.gguf	Q6_K	5.63GB
SN29-C00-llama-HK1-1.Q8_0.gguf	Q8_0	6.82GB

Original model description:

library_name: transformers tags:

transformers.js
tokenizers

GPT-4 Tokenizer

A 🤗-compatible version of the GPT-4 tokenizer (adapted from openai/tiktoken). This means it can be used with Hugging Face libraries including Transformers, Tokenizers, and Transformers.js.

Example usage:

Transformers/Tokenizers

from transformers import GPT2TokenizerFast

tokenizer = GPT2TokenizerFast.from_pretrained('Xenova/gpt-4')
assert tokenizer.encode('hello world') == [15339, 1917]

Transformers.js

import { AutoTokenizer } from '@xenova/transformers';

const tokenizer = await AutoTokenizer.from_pretrained('Xenova/gpt-4');
const tokens = tokenizer.encode('hello world'); // [15339, 1917]

RichardErkhov/deepnet_-_SN29-C00-llama-HK1-1-gguf