fix args with 2 values

common/common.cpp

@@ -603,6 +603,7 @@ std::string llama_arg::to_string() {
         }
     }
     if (!value_hint.empty()) ss << " " << value_hint;
+    if (!value_hint_2.empty()) ss << " " << value_hint_2;
     if (ss.tellp() > n_leading_spaces - 3) {
         // current line is too long, add new line
         ss << "\n" << leading_spaces;
@@ -850,7 +851,7 @@ std::vector<llama_arg> gpt_params_parser_init(gpt_params & params, llama_example
     ));
     add_opt(llama_arg(
         {"--poll-batch"}, "<0|1>",
-        "use polling to wait for work (default: same as --poll",
+        "use polling to wait for work (default: same as --poll)",
         [&params](int value) {
             params.cpuparams_batch.poll = value;
         }

examples/export-docs/export-docs.cpp

@@ -28,9 +28,16 @@ static void export_md(std::string fname, llama_example ex) {
             }
         }
         // value hint
+        if (!opt.value_hint.empty()) {
             std::string md_value_hint(opt.value_hint);
             string_replace_all(md_value_hint, "|", "\\|");
             file << " " << md_value_hint;
+        }
+        if (!opt.value_hint_2.empty()) {
+            std::string md_value_hint_2(opt.value_hint_2);
+            string_replace_all(md_value_hint_2, "|", "\\|");
+            file << " " << md_value_hint_2;
+        }
         // help text
         std::string md_help(opt.help);
         string_replace_all(md_help, "\n", "<br/>");

examples/server/README.md

@@ -36,11 +36,11 @@ The project is under active development, and we are [looking for feedback and co
 | `-Cb, --cpu-mask-batch M` | CPU affinity mask: arbitrarily long hex. Complements cpu-range-batch (default: same as --cpu-mask) |
 | `-Crb, --cpu-range-batch lo-hi` | ranges of CPUs for affinity. Complements --cpu-mask-batch |
 | `--cpu-strict-batch <0\|1>` | use strict CPU placement (default: same as --cpu-strict) |
-| `--poll-batch <0\|1>` | use polling to wait for work (default: same as --poll |
+| `--poll-batch <0\|1>` | use polling to wait for work (default: same as --poll) |
 | `-lcs, --lookup-cache-static FNAME` | path to static lookup cache to use for lookup decoding (not updated by generation) |
 | `-lcd, --lookup-cache-dynamic FNAME` | path to dynamic lookup cache to use for lookup decoding (updated by generation) |
 | `-c, --ctx-size N` | size of the prompt context (default: 0, 0 = loaded from model)<br/>(env: LLAMA_ARG_CTX_SIZE) |
-| `-n, --predict N` | number of tokens to predict (default: -1, -1 = infinity, -2 = until context filled)<br/>(env: LLAMA_ARG_N_PREDICT) |
+| `-n, --predict, --n-predict N` | number of tokens to predict (default: -1, -1 = infinity, -2 = until context filled)<br/>(env: LLAMA_ARG_N_PREDICT) |
 | `-b, --batch-size N` | logical maximum batch size (default: 2048)<br/>(env: LLAMA_ARG_BATCH) |
 | `-ub, --ubatch-size N` | physical maximum batch size (default: 512)<br/>(env: LLAMA_ARG_UBATCH) |
 | `--keep N` | number of tokens to keep from the initial prompt (default: 0, -1 = all) |
@@ -98,7 +98,6 @@ The project is under active development, and we are [looking for feedback and co
 | `-nocb, --no-cont-batching` | disable continuous batching<br/>(env: LLAMA_ARG_NO_CONT_BATCHING) |
 | `--mmproj FILE` | path to a multimodal projector file for LLaVA. see examples/llava/README.md |
 | `--image FILE` | path to an image file. use with multimodal models. Specify multiple times for batching |
-| `--rpc SERVERS` | comma separated list of RPC servers |
 | `--mlock` | force system to keep model in RAM rather than swapping or compressing |
 | `--no-mmap` | do not memory-map model (slower load but may reduce pageouts if not using mlock) |
 | `--numa TYPE` | attempt optimizations that help on some NUMA systems<br/>- distribute: spread execution evenly over all nodes<br/>- isolate: only spawn threads on CPUs on the node that execution started on<br/>- numactl: use the CPU map provided by numactl<br/>if run without this previously, it is recommended to drop the system page cache before using this<br/>see https://github.com/ggerganov/llama.cpp/issues/1437 |
@@ -110,10 +109,11 @@ The project is under active development, and we are [looking for feedback and co
 | `--check-tensors` | check model tensor data for invalid values (default: false) |
 | `--override-kv KEY=TYPE:VALUE` | advanced option to override model metadata by key. may be specified multiple times.<br/>types: int, float, bool, str. example: --override-kv tokenizer.ggml.add_bos_token=bool:false |
 | `--lora FNAME` | path to LoRA adapter (can be repeated to use multiple adapters) |
-| `--lora-scaled FNAME` | path to LoRA adapter with user defined scaling (can be repeated to use multiple adapters) |
+| `--lora-scaled FNAME SCALE` | path to LoRA adapter with user defined scaling (can be repeated to use multiple adapters) |
 | `--control-vector FNAME` | add a control vector<br/>note: this argument can be repeated to add multiple control vectors |
-| `--control-vector-scaled FNAME` | add a control vector with user defined scaling SCALE<br/>note: this argument can be repeated to add multiple scaled control vectors |
+| `--control-vector-scaled FNAME SCALE` | add a control vector with user defined scaling SCALE<br/>note: this argument can be repeated to add multiple scaled control vectors |
-| `--control-vector-layer-range START` | layer range to apply the control vector(s) to, start and end inclusive |
+| `--control-vector-layer-range START END` | layer range to apply the control vector(s) to, start and end inclusive |
+| `-a, --alias STRING` | set alias for model name (to be used by REST API)<br/>(env: LLAMA_ARG_MODEL) |
 | `-m, --model FNAME` | model path (default: `models/$filename` with filename from `--hf-file` or `--model-url` if set, otherwise models/7B/ggml-model-f16.gguf)<br/>(env: LLAMA_ARG_MODEL) |
 | `-md, --model-draft FNAME` | draft model for speculative decoding (default: unused) |
 | `-mu, --model-url MODEL_URL` | model download url (default: unused)<br/>(env: LLAMA_ARG_MODEL_URL) |