py : add "LLaMAForCausalLM" conversion support (#9485 )

Co-authored-by: Csaba Kecskemeti <csabakecskemeti@Csabas-Mac-Pro.local>
readme : update tools list (#9475 )
2026-08-02 16:08:38 +00:00 · 2024-09-15 10:48:25 +03:00 · 2024-09-15 10:36:53 +03:00
2 changed files with 2 additions and 1 deletions
@@ -173,6 +173,7 @@ Unless otherwise noted these projects are open-source with permissive licensing:
 - [akx/ggify](https://github.com/akx/ggify) – download PyTorch models from HuggingFace Hub and convert them to GGML
 - [crashr/gppm](https://github.com/crashr/gppm) – launch llama.cpp instances utilizing NVIDIA Tesla P40 or P100 GPUs with reduced idle power consumption
 - [gpustack/gguf-parser](https://github.com/gpustack/gguf-parser-go/tree/main/cmd/gguf-parser) - review/check the GGUF file and estimate the memory usage
+- [Styled Lines](https://marketplace.unity.com/packages/tools/generative-ai/styled-lines-llama-cpp-model-292902) (proprietary licensed, async wrapper of inference part for game development in Unity3d with prebuild Mobile and Web platform wrappers and a model example)

 **Infrastructure:**

@@ -1487,7 +1487,7 @@ class StableLMModel(Model):
                raise ValueError(f"Unprocessed norms: {norms}")


-@Model.register("LlamaForCausalLM", "MistralForCausalLM", "MixtralForCausalLM")
+@Model.register("LLaMAForCausalLM", "LlamaForCausalLM", "MistralForCausalLM", "MixtralForCausalLM")
 class LlamaModel(Model):
    model_arch = gguf.MODEL_ARCH.LLAMA