diff options
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/finetune/finetune.cpp | 2 | ||||
| -rw-r--r-- | examples/quantize/quantize.cpp | 3 |
2 files changed, 3 insertions, 2 deletions
diff --git a/examples/finetune/finetune.cpp b/examples/finetune/finetune.cpp index 3da5317b..22743b1b 100644 --- a/examples/finetune/finetune.cpp +++ b/examples/finetune/finetune.cpp @@ -575,7 +575,7 @@ static struct ggml_tensor * llama_build_lora_finetune_graphs( GGML_ASSERT(tokens_input->type == GGML_TYPE_I32); auto add_to_f32 = [] (struct ggml_context * ctx, struct ggml_tensor * a, struct ggml_tensor * b) { - if (ggml_is_quantized(a->type) || a->type == GGML_TYPE_F16) { + if (ggml_is_quantized(a->type) || a->type == GGML_TYPE_F16 || a->type == GGML_TYPE_BF16) { return ggml_add_cast(ctx, a, b, GGML_TYPE_F32); } else if (a->type == GGML_TYPE_F32) { return ggml_add(ctx, a, b); diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index 432cc2b4..909eab28 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -46,7 +46,8 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "Q5_K_M", LLAMA_FTYPE_MOSTLY_Q5_K_M, " 4.45G, +0.0122 ppl @ LLaMA-v1-7B", }, { "Q6_K", LLAMA_FTYPE_MOSTLY_Q6_K, " 5.15G, +0.0008 ppl @ LLaMA-v1-7B", }, { "Q8_0", LLAMA_FTYPE_MOSTLY_Q8_0, " 6.70G, +0.0004 ppl @ LLaMA-v1-7B", }, - { "F16", LLAMA_FTYPE_MOSTLY_F16, "13.00G @ 7B", }, + { "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", }, // Note: Ensure COPY comes after F32 to avoid ftype 0 from matching. { "COPY", LLAMA_FTYPE_ALL_F32, "only copy tensors, no quantizing", }, |