From 5dc9dd7152dedc6046b646855585bd070c91e8c8 Mon Sep 17 00:00:00 2001 From: Carolinabanana <140120812+Carolinabanana@users.noreply.github.com> Date: Tue, 9 Apr 2024 09:16:13 +0100 Subject: llama : add Command R Plus support (#6491) * Add Command R Plus GGUF * Add Command R Plus GGUF * Loading works up to LayerNorm2D * Export new tensors in 1D so they are not quantized. * Fix embedding layer based on Noeda's example * Whitespace * Add line * Fix unexpected tokens on MPS. Re-add F16 fix. ((Noeda) * dranger003: Fix block index overflow in CUDA dequantizing. * Reverted blocked multiplication code as it still has issues and could affect other Llama arches * export norms as f32 * fix overflow issues during quant and other cleanup * Type convention Co-authored-by: Georgi Gerganov * dranger003: Fix more int overflow during quant. --------- Co-authored-by: S Co-authored-by: S Co-authored-by: slaren Co-authored-by: Georgi Gerganov --- ggml.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'ggml.c') diff --git a/ggml.c b/ggml.c index c9b0a6a0..793b67f4 100644 --- a/ggml.c +++ b/ggml.c @@ -338,14 +338,14 @@ ggml_fp16_t ggml_fp32_to_fp16(float x) { return GGML_FP32_TO_FP16(x); } -void ggml_fp16_to_fp32_row(const ggml_fp16_t * x, float * y, int n) { - for (int i = 0; i < n; i++) { +void ggml_fp16_to_fp32_row(const ggml_fp16_t * x, float * y, int64_t n) { + for (int64_t i = 0; i < n; i++) { y[i] = GGML_FP16_TO_FP32(x[i]); } } -void ggml_fp32_to_fp16_row(const float * x, ggml_fp16_t * y, int n) { - int i = 0; +void ggml_fp32_to_fp16_row(const float * x, ggml_fp16_t * y, int64_t n) { + int64_t i = 0; #if defined(__F16C__) for (; i + 7 < n; i += 8) { __m256 x_vec = _mm256_loadu_ps(x + i); @@ -20331,11 +20331,11 @@ size_t ggml_quantize_chunk( enum ggml_type type, const float * src, void * dst, - int start, - int nrows, - int n_per_row, + int64_t start, + int64_t nrows, + int64_t n_per_row, const float * imatrix) { - const int n = nrows * n_per_row; + const int64_t n = (int64_t) nrows * n_per_row; if (ggml_quantize_requires_imatrix(type)) { GGML_ASSERT(imatrix != NULL); -- cgit v1.2.3