You can deploy this model and start earning money today!

RichardErkhov/
yujiepan_-_TinyLlama-1.1B-gguf

Name: yujiepan_-_TinyLlama-1.1B-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

TinyLlama-1.1B - GGUF

Model creator: https://huggingface.co/yujiepan/
Original model: https://huggingface.co/yujiepan/TinyLlama-1.1B/

Name	Quant method	Size
TinyLlama-1.1B.Q2_K.gguf	Q2_K	0.4GB
TinyLlama-1.1B.Q3_K_S.gguf	Q3_K_S	0.47GB
TinyLlama-1.1B.Q3_K.gguf	Q3_K	0.51GB
TinyLlama-1.1B.Q3_K_M.gguf	Q3_K_M	0.51GB
TinyLlama-1.1B.Q3_K_L.gguf	Q3_K_L	0.55GB
TinyLlama-1.1B.IQ4_XS.gguf	IQ4_XS	0.57GB
TinyLlama-1.1B.Q4_0.gguf	Q4_0	0.59GB
TinyLlama-1.1B.IQ4_NL.gguf	IQ4_NL	0.6GB
TinyLlama-1.1B.Q4_K_S.gguf	Q4_K_S	0.6GB
TinyLlama-1.1B.Q4_K.gguf	Q4_K	0.62GB
TinyLlama-1.1B.Q4_K_M.gguf	Q4_K_M	0.62GB
TinyLlama-1.1B.Q4_1.gguf	Q4_1	0.65GB
TinyLlama-1.1B.Q5_0.gguf	Q5_0	0.71GB
TinyLlama-1.1B.Q5_K_S.gguf	Q5_K_S	0.71GB
TinyLlama-1.1B.Q5_K.gguf	Q5_K	0.73GB
TinyLlama-1.1B.Q5_K_M.gguf	Q5_K_M	0.73GB
TinyLlama-1.1B.Q5_1.gguf	Q5_1	0.77GB
TinyLlama-1.1B.Q6_K.gguf	Q6_K	0.84GB
TinyLlama-1.1B.Q8_0.gguf	Q8_0	1.09GB

Original model description:

library_name: transformers tags: []

yujiepan/TinyLlama-1.1B

This model is a float16 version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T.

Codes:

python

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T', torch_dtype=torch.float16)
model.push_to_hub('yujiepan/TinyLlama-1.1B')
tokenizer = AutoTokenizer.from_pretrained('TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T')
tokenizer.push_to_hub('yujiepan/TinyLlama-1.1B')

RichardErkhov/yujiepan_-_TinyLlama-1.1B-gguf

Original model description:

library_name: transformers tags: []

yujiepan/TinyLlama-1.1B

RichardErkhov/
yujiepan_-_TinyLlama-1.1B-gguf