RichardErkhov/devlocalhost_-_hi-tinylama-f16-3e-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

hi-tinylama-f16-3e - GGUF

• Model creator: https://huggingface.co/devlocalhost/
• Original model: https://huggingface.co/devlocalhost/hi-tinylama-f16-3e/

Name	Quant method	Size
hi-tinylama-f16-3e.Q2_K.gguf	Q2_K	0.4GB
hi-tinylama-f16-3e.IQ3_XS.gguf	IQ3_XS	0.44GB
hi-tinylama-f16-3e.IQ3_S.gguf	IQ3_S	0.47GB
hi-tinylama-f16-3e.Q3_K_S.gguf	Q3_K_S	0.47GB
hi-tinylama-f16-3e.IQ3_M.gguf	IQ3_M	0.48GB
hi-tinylama-f16-3e.Q3_K.gguf	Q3_K	0.51GB
hi-tinylama-f16-3e.Q3_K_M.gguf	Q3_K_M	0.51GB
hi-tinylama-f16-3e.Q3_K_L.gguf	Q3_K_L	0.55GB
hi-tinylama-f16-3e.IQ4_XS.gguf	IQ4_XS	0.57GB
hi-tinylama-f16-3e.Q4_0.gguf	Q4_0	0.59GB
hi-tinylama-f16-3e.IQ4_NL.gguf	IQ4_NL	0.6GB
hi-tinylama-f16-3e.Q4_K_S.gguf	Q4_K_S	0.6GB
hi-tinylama-f16-3e.Q4_K.gguf	Q4_K	0.62GB
hi-tinylama-f16-3e.Q4_K_M.gguf	Q4_K_M	0.62GB
hi-tinylama-f16-3e.Q4_1.gguf	Q4_1	0.65GB
hi-tinylama-f16-3e.Q5_0.gguf	Q5_0	0.71GB
hi-tinylama-f16-3e.Q5_K_S.gguf	Q5_K_S	0.71GB
hi-tinylama-f16-3e.Q5_K.gguf	Q5_K	0.73GB
hi-tinylama-f16-3e.Q5_K_M.gguf	Q5_K_M	0.73GB
hi-tinylama-f16-3e.Q5_1.gguf	Q5_1	0.77GB
hi-tinylama-f16-3e.Q6_K.gguf	Q6_K	0.84GB
hi-tinylama-f16-3e.Q8_0.gguf	Q8_0	1.09GB

Original model description:

language:

• en license: apache-2.0 tags:
• text-generation-inference
• transformers
• llama
• trl widget:
• text: "### Instruction: आपका नाम क्या है?

Input:

Response:"

example_title: "what is your name?" base_model: unsloth/tinyllama-bnb-4bit

Uploaded model

• Developed by: devlocalhost
• License: apache-2.0
• Finetuned from model : unsloth/tinyllama-bnb-4bit