Update LlmMetadata for litert-lm 0.18.0: chat template with content parts, supports_thinking / supports_function_calling (weights unchanged)

MiniCPM5-1B_dynamic_wi8_afp32.litertlm

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b948cf44754111c574c9d6970a9311f1c07dc021323cf2d7076f76389313be
+oid sha256:13ec3c4372dd41720ecf62ba07557514d7d0fff92f5fb058295742b4b9c3786b
 size 1105464896

README.md

@@ -24,9 +24,9 @@ This repository hosts the [**LiteRT-LM**](https://ai.google.dev/edge/litert-lm)
 
 ## Available Models
 
-* **`minicpm_wi4b32_wi8_afp32.litertlm`**: This model features mixed INT4-block32(linear)/INT8(embed and lmhead) quantization (wi4b32_wi8) with FP32 activations (afp32).
-* **`minicpm_wi4b32_wi8_afp32_gpu_opt.litertlm`**: This model uses same quantization recipe with minicpm_wi4b32_wi8_afp32 but optimized for GPU execution.
-* **`MiniCPM5-1B_dynamic_wi8_afp32.litertlm`**: This model features dynamic weight-only INT8 quantization (wi8) with FP32 activations (afp32). It is configured with static prefill memory allocation.
+* **`minicpm_wi4b32_wi8_afp32.litertlm`**: This model features mixed INT4-block32(linear)/INT8(embed and lmhead) quantization (wi4b32_wi8) with FP32 activations (afp32). Needs litert-lm 0.18.0 or newer (tested on 0.18.0) and carries LiteRT-LM's official minicpm5 configuration, so thinking is off unless `enable_thinking` is true, the reasoning arrives on the thought channel, and tool calls are parsed by the runtime.
+* **`minicpm_wi4b32_wi8_afp32_gpu_opt.litertlm`**: This model uses same quantization recipe with minicpm_wi4b32_wi8_afp32 but optimized for GPU execution. Needs litert-lm 0.18.0 or newer (tested on 0.18.0) and carries LiteRT-LM's official minicpm5 configuration, so thinking is off unless `enable_thinking` is true, the reasoning arrives on the thought channel, and tool calls are parsed by the runtime.
+* **`MiniCPM5-1B_dynamic_wi8_afp32.litertlm`**: This model features dynamic weight-only INT8 quantization (wi8) with FP32 activations (afp32). It is configured with static prefill memory allocation. Needs litert-lm 0.18.0 or newer (tested on 0.18.0) and carries LiteRT-LM's official minicpm5 configuration, so thinking is off unless `enable_thinking` is true, the reasoning arrives on the thought channel, and tool calls are parsed by the runtime.
 
 ## Quantization Benchmark
 

minicpm_wi4b32_wi8_afp32.litertlm

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43f41a837c58408192d703a7cf7bb27a3f8b4f8cc1d34c7f79e54f058f966ccc
-size 792625152
+oid sha256:ee1b70697ef583c46d26df5772055946d4ca2a9a80b059149bb51f4ab9646863
+size 792619648

minicpm_wi4b32_wi8_afp32_gpu_opt.litertlm

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e15a7cc735ae36e9888d341d44bd53c0579153d7a3379aaf958620eea4816e3
-size 793034752
+oid sha256:40ffba999ca45223c1713f130299e69b798b72fd561ea420300beb0adb49e191
+size 793029040