Upload 2 files

main-ctx.cpp

@@ -20,7 +20,6 @@
 // default hparams (GPT-2 774M)
 struct gpt_hparams {
     int32_t n_vocab = 50257;   // Vocabulary size remains the same
-    //int32_t n_ctx   = 1024;     // Maximum context length (sequence length)
     int32_t n_embd  = 1024;     // Embedding dimensionality
     int32_t n_head  = 16;       // Number of attention heads
     int32_t n_layer = 24;       // Number of transformer layers
@@ -32,7 +31,7 @@ struct gpt_hparams {
     int32_t n_predict    = 200;  // new tokens to predict
     int32_t n_parallel   = 1;    // number of parallel streams
     int32_t n_batch      = 32;   // batch size for prompt processing
-    int32_t n_ctx        = 2048; // context size (this is the KV cache max size)
+    int32_t n_ctx        = 1024; // context size (this is the KV cache max size)
     int32_t n_gpu_layers = 0;    // number of layers to offlload to the GPU
 
     bool ignore_eos = false; // ignore EOS token when generating text