README.md

metadata

base_model: Corianas/tiny-llama-miniguanaco-1.5T
inference: false
language:
  - en
model: PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T
model_creator: Corianas
model_name: tiny-llama-miniguanaco-1.5T
pipeline_tag: text-generation
quantized_by: afrideva
tags:
  - gguf
  - ggml
  - quantized
  - q2_k
  - q3_k_m
  - q4_k_m
  - q5_k_m
  - q6_k
  - q8_0

Corianas/tiny-llama-miniguanaco-1.5T-GGUF

Quantized GGUF model files for tiny-llama-miniguanaco-1.5T from Corianas

Name	Quant method	Size
tiny-llama-miniguanaco-1.5t.q2_k.gguf	q2_k	482.14 MB
tiny-llama-miniguanaco-1.5t.q3_k_m.gguf	q3_k_m	549.85 MB
tiny-llama-miniguanaco-1.5t.q4_k_m.gguf	q4_k_m	667.81 MB
tiny-llama-miniguanaco-1.5t.q5_k_m.gguf	q5_k_m	782.04 MB
tiny-llama-miniguanaco-1.5t.q6_k.gguf	q6_k	903.41 MB
tiny-llama-miniguanaco-1.5t.q8_0.gguf	q8_0	1.17 GB

Original Model Card:

TinyLLama 1.5T checkpoint trained to answer questions.

f"{'prompt'}\n{'completion'}\n<END>"

No input/output, just question, then newline to begin the answer.