aboutsummaryrefslogtreecommitdiff
path: root/qwen_asr_tokenizer.c
diff options
context:
space:
mode:
authorOnur Gündüz <ogunduz@gmail.com>2026-03-28 21:27:58 +0100
committerOnur Gündüz <ogunduz@gmail.com>2026-03-28 23:10:03 +0100
commitc47e900b94d18cca1bf600e58f10dbcc2e34c1f7 (patch)
treebf7a4247c528841abe71bbbd408eda3ff71b1152 /qwen_asr_tokenizer.c
parent34e9eefde7870edcc318209738cabb17c71b50ed (diff)
downloadffwd-c47e900b94d18cca1bf600e58f10dbcc2e34c1f7.tar.gz
ffwd-c47e900b94d18cca1bf600e58f10dbcc2e34c1f7.zip
Refactor and enhance pplx_embed and pplx_embed_mlx for improved model support
- Updated `pplx_embed.h` to support new embedding models: `pplx-embed-v1-4b` and `pplx-embed-context-v1-4b`. - Simplified model configuration structure and constants for better maintainability. - Enhanced comments for clarity on model architecture and configuration. - Modified `pplx_embed_mlx.c` to streamline loading of model weights and configuration from `config.json`. - Improved memory management and error handling in the MLX backend. - Updated embedding computation to support dynamic hidden sizes based on model configuration. - Added `pplx_mlx_config` function to retrieve model configuration details. - Updated README.md - Added .gitignore
Diffstat (limited to 'qwen_asr_tokenizer.c')
-rw-r--r--qwen_asr_tokenizer.c8
1 files changed, 0 insertions, 8 deletions
diff --git a/qwen_asr_tokenizer.c b/qwen_asr_tokenizer.c
index 7bbc5db..0e6df38 100644
--- a/qwen_asr_tokenizer.c
+++ b/qwen_asr_tokenizer.c
@@ -1,11 +1,3 @@
-/*
- * qwen_asr_tokenizer.c - Qwen2/Qwen3 BPE tokenizer (GPT-2 byte-level)
- *
- * Supports:
- * - decode token IDs to UTF-8 text (for ASR output assembly)
- * - encode UTF-8 text to token IDs using vocab.json + merges.txt
- */
-
#include "qwen_asr_tokenizer.h"
#include "qwen_asr_kernels.h"
#include <limits.h>