diff options
| -rw-r--r-- | README.md | 2 | ||||
| -rw-r--r-- | convert.py | 6 | ||||
| -rw-r--r-- | examples/embedding/embedding.cpp | 2 | ||||
| -rw-r--r-- | examples/main/main.cpp | 2 | ||||
| -rw-r--r-- | examples/perplexity/perplexity.cpp | 2 | ||||
| -rw-r--r-- | examples/server/README.md | 2 |
6 files changed, 11 insertions, 5 deletions
@@ -86,7 +86,7 @@ as the main playground for developing new features for the [ggml](https://github - [X] [OpenBuddy 🐶 (Multilingual)](https://github.com/OpenBuddy/OpenBuddy) - [X] [Pygmalion 7B / Metharme 7B](#using-pygmalion-7b--metharme-7b) - [X] [WizardLM](https://github.com/nlpxucan/WizardLM) -- [X] [Baichuan-7B](https://huggingface.co/baichuan-inc/baichuan-7B) +- [X] [Baichuan-7B](https://huggingface.co/baichuan-inc/baichuan-7B) and its derivations (such as [baichuan-7b-sft](https://huggingface.co/hiyouga/baichuan-7b-sft)) **Bindings:** @@ -154,9 +154,15 @@ class Params: # try transformer naming first if "model.layers.0.self_attn.q_proj.weight" in model: n_layer=next(i for i in itertools.count() if f"model.layers.{i}.self_attn.q_proj.weight" not in model) + elif "model.layers.0.self_attn.W_pack.weight" in model: # next: try baichuan naming + n_layer=next(i for i in itertools.count() if f"model.layers.{i}.self_attn.W_pack.weight" not in model) else: n_layer=next(i for i in itertools.count() if f"layers.{i}.attention.wq.weight" not in model) + if n_layer < 1: + raise Exception("failed to guess 'n_layer'. This model is unknown or unsupported.\n" + "Suggestion: provide 'config.json' of the model in the same directory containing model files.") + n_head=n_embd // 128 # guessed return Params( diff --git a/examples/embedding/embedding.cpp b/examples/embedding/embedding.cpp index 2b7eb39..03e801c 100644 --- a/examples/embedding/embedding.cpp +++ b/examples/embedding/embedding.cpp @@ -18,7 +18,7 @@ int main(int argc, char ** argv) { params.embedding = true; if (params.n_ctx > 2048) { - fprintf(stderr, "%s: warning: model does not support context sizes greater than 2048 tokens (%d specified);" + fprintf(stderr, "%s: warning: model might not support context sizes greater than 2048 tokens (%d specified);" "expect poor results\n", __func__, params.n_ctx); } diff --git a/examples/main/main.cpp b/examples/main/main.cpp index 3a17192..0f6391a 100644 --- a/examples/main/main.cpp +++ b/examples/main/main.cpp @@ -85,7 +85,7 @@ int main(int argc, char ** argv) { } if (params.n_ctx > 2048) { - fprintf(stderr, "%s: warning: model does not support context sizes greater than 2048 tokens (%d specified);" + fprintf(stderr, "%s: warning: model might not support context sizes greater than 2048 tokens (%d specified);" "expect poor results\n", __func__, params.n_ctx); } else if (params.n_ctx < 8) { fprintf(stderr, "%s: warning: minimum context size is 8, using minimum size.\n", __func__); diff --git a/examples/perplexity/perplexity.cpp b/examples/perplexity/perplexity.cpp index dd54ed3..fd4b03c 100644 --- a/examples/perplexity/perplexity.cpp +++ b/examples/perplexity/perplexity.cpp @@ -130,7 +130,7 @@ int main(int argc, char ** argv) { params.n_batch = std::min(params.n_batch, params.n_ctx); if (params.n_ctx > 2048) { - fprintf(stderr, "%s: warning: model does not support context sizes greater than 2048 tokens (%d specified);" + fprintf(stderr, "%s: warning: model might not support context sizes greater than 2048 tokens (%d specified);" "expect poor results\n", __func__, params.n_ctx); } diff --git a/examples/server/README.md b/examples/server/README.md index c5139c1..ad9b6bb 100644 --- a/examples/server/README.md +++ b/examples/server/README.md @@ -7,7 +7,7 @@ Command line options: - `--threads N`, `-t N`: Set the number of threads to use during computation. - `-m FNAME`, `--model FNAME`: Specify the path to the LLaMA model file (e.g., `models/7B/ggml-model.bin`). - `-m ALIAS`, `--alias ALIAS`: Set an alias for the model. The alias will be returned in API responses. -- `-c N`, `--ctx-size N`: Set the size of the prompt context. The default is 512, but LLaMA models were built with a context of 2048, which will provide better results for longer input/inference. +- `-c N`, `--ctx-size N`: Set the size of the prompt context. The default is 512, but LLaMA models were built with a context of 2048, which will provide better results for longer input/inference. The size may differ in other models, for example, baichuan models were build with a context of 4096. - `-ngl N`, `--n-gpu-layers N`: When compiled with appropriate support (currently CLBlast or cuBLAS), this option allows offloading some layers to the GPU for computation. Generally results in increased performance. - `-mg i, --main-gpu i`: When using multiple GPUs this option controls which GPU is used for small tensors for which the overhead of splitting the computation across all GPUs is not worthwhile. The GPU in question will use slightly more VRAM to store a scratch buffer for temporary results. By default GPU 0 is used. Requires cuBLAS. - `-ts SPLIT, --tensor-split SPLIT`: When using multiple GPUs this option controls how large tensors should be split across all GPUs. `SPLIT` is a comma-separated list of non-negative values that assigns the proportion of data that each GPU should get in order. For example, "3,2" will assign 60% of the data to GPU 0 and 40% to GPU 1. By default the data is split in proportion to VRAM but this may not be optimal for performance. Requires cuBLAS. |