mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2025-09-11 01:24:36 +00:00
merge checkpoint 2 - functional merge without q4_0_4_4 (need regen shaders)
This commit is contained in:
commit
de64b9198c
218 changed files with 175736 additions and 49778 deletions
|
@ -49,9 +49,6 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
|
|||
{ "Q5_K_M", LLAMA_FTYPE_MOSTLY_Q5_K_M, " 5.33G, +0.0569 ppl @ Llama-3-8B", },
|
||||
{ "Q6_K", LLAMA_FTYPE_MOSTLY_Q6_K, " 6.14G, +0.0217 ppl @ Llama-3-8B", },
|
||||
{ "Q8_0", LLAMA_FTYPE_MOSTLY_Q8_0, " 7.96G, +0.0026 ppl @ Llama-3-8B", },
|
||||
{ "Q4_0_4_4", LLAMA_FTYPE_MOSTLY_Q4_0_4_4, " 4.34G, +0.4685 ppl @ Llama-3-8B", },
|
||||
{ "Q4_0_4_8", LLAMA_FTYPE_MOSTLY_Q4_0_4_8, " 4.34G, +0.4685 ppl @ Llama-3-8B", },
|
||||
{ "Q4_0_8_8", LLAMA_FTYPE_MOSTLY_Q4_0_8_8, " 4.34G, +0.4685 ppl @ Llama-3-8B", },
|
||||
{ "F16", LLAMA_FTYPE_MOSTLY_F16, "14.00G, +0.0020 ppl @ Mistral-7B", },
|
||||
{ "BF16", LLAMA_FTYPE_MOSTLY_BF16, "14.00G, -0.0050 ppl @ Mistral-7B", },
|
||||
{ "F32", LLAMA_FTYPE_ALL_F32, "26.00G @ 7B", },
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue