llama : fix missing break in Persimmon arch case statements (#3535)

* Fix CI for publishing GGUF package

* Bump version

* fix

* bump version

* bump version

* bump version

.github/workflows/gguf-publish.yml

@@ -36,8 +36,9 @@ jobs:
         poetry install
 
     - name: Build package
-      run: poetry build
+      run: cd gguf-py && poetry build
     - name: Publish package
       uses: pypa/gh-action-pypi-publish@release/v1
       with:
         password: ${{ secrets.PYPI_API_TOKEN }}
+        packages-dir: gguf-py/dist

common/common.cpp

@@ -170,7 +170,7 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
             // store the external file name in params
             params.prompt_file = argv[i];
             std::copy(std::istreambuf_iterator<char>(file), std::istreambuf_iterator<char>(), back_inserter(params.prompt));
-            if (params.prompt.back() == '\n') {
+            if (!params.prompt.empty() && params.prompt.back() == '\n') {
                 params.prompt.pop_back();
             }
         } else if (arg == "-n" || arg == "--n-predict") {
@@ -295,7 +295,7 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
                 break;
             }
             std::copy(std::istreambuf_iterator<char>(file), std::istreambuf_iterator<char>(), back_inserter(params.cfg_negative_prompt));
-            if (params.cfg_negative_prompt.back() == '\n') {
+            if (!params.cfg_negative_prompt.empty() && params.cfg_negative_prompt.back() == '\n') {
                 params.cfg_negative_prompt.pop_back();
             }
         } else if (arg == "--cfg-scale") {

gguf-py/README.md

@@ -69,4 +69,3 @@ python -m twine upload dist/*
 ## TODO
 - [ ] Add tests
 - [ ] Include conversion scripts as command line entry points in this package.
-- Add CI workflow for releasing the package.

gguf-py/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "gguf"
-version = "0.4.0"
+version = "0.4.4"
 description = "Write ML models in GGUF for GGML"
 authors = ["GGML <ggml@ggml.ai>"]
 packages = [

llama.cpp

@@ -2047,7 +2047,7 @@ static void llm_load_hparams(
                 case 36: model.type = e_model::MODEL_8B; break;
                 default: model.type = e_model::MODEL_UNKNOWN;
             }
-        }
+        } break;
         case LLM_ARCH_REFACT:
             {
                 GGUF_GET_KEY(ctx, hparams.f_norm_rms_eps, gguf_get_val_f32, GGUF_TYPE_FLOAT32, true, kv(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS));
@@ -4926,7 +4926,7 @@ static struct ggml_cgraph * llama_build_graph(
         case LLM_ARCH_PERSIMMON:
             {
                 result = llm_build_persimmon(lctx, batch);
-            }
+            } break;
         case LLM_ARCH_REFACT:
             {
                 result = llm_build_refact(lctx, batch);
@@ -7194,6 +7194,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
     }
 
     std::ofstream fout(fname_out, std::ios::binary);
+    fout.exceptions(std::ofstream::failbit); // fail fast on write errors
 
     const size_t meta_size = gguf_get_meta_size(ctx_out);
 

requirements.txt

@@ -1,3 +1,3 @@
-numpy==1.24
+numpy==1.24.4
 sentencepiece==0.1.98
 gguf>=0.1.0