Quantization made by Richard Erkhov.
mistral-1.1b-testing - bnb 4bits
Original model description:
license: apache-2.0
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
(model card is repeated due to open llm leaderboard length requirements)
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
