Reorder types for llm_type

Author: pwilkin

.roomodes

@@ -0,0 +1,19 @@
+customModes:
+  - slug: documentation-writer
+    name: ✍️ Documentation Writer
+    roleDefinition: |
+      You are a technical documentation expert specializing in creating clear, comprehensive documentation for software projects. Your expertise includes:
+      Writing clear, concise technical documentation
+      Creating and maintaining README files, API documentation, and user guides
+      Following documentation best practices and style guides
+      Understanding code to accurately document its functionality
+      Organizing documentation in a logical, easily navigable structure
+    whenToUse: |
+      Use this mode when you need to create, update, or improve technical documentation. Ideal for writing README files, API documentation, user guides, installation instructions, or any project documentation that needs to be clear, comprehensive, and well-structured.
+    description: Create clear technical project documentation
+    groups:
+      - read
+      - edit
+      - command
+    customInstructions: |
+      Focus on creating documentation that is clear, concise, and follows a consistent style. Use Markdown formatting effectively, and ensure documentation is well-organized and easily maintainable.

bld.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+cmake --build build --config Release -j 8

embeddings

@@ -0,0 +1,2 @@
+#!/bin/bash
+llama-server -m /mnt/win/k/models/Casual-Autopsy/snowflake-arctic-embed-l-v2.0-gguf/snowflake-arctic-embed-l-v2.0-q8_0.gguf -fa -a text-embedding-snowflake-arctic-embed-l-v2.0 --port 2234

polaris.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

prebld.sh

@@ -0,0 +1 @@
+cmake -B build  -DGGML_CUDA=ON -DGGML_CUDA_FORCE_CUBLAS=OFF -DGGML_CUDA_FORCE_MMQ=OFF -DGGML_CUDA_FA_ALL_QUANTS=1 -DCMAKE_CUDA_ARCHITECTURES=86 -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS -DCMAKE_BUILD_TYPE=Release

src/llama-model.cpp

@@ -18071,7 +18071,7 @@ struct llm_build_seed_oss : public llm_graph_context {
             cur = build_norm(ffn_inp,
                     model.layers[il].attn_post_norm, NULL,
                     LLM_NORM_RMS, il);
-            cb(cur, "ffn_norm", il);
+            cb(cur, "attn_post_norm", il);
 
             cur = build_ffn(cur,
                     model.layers[il].ffn_up,   NULL, NULL,

src/llama-model.h

@@ -76,6 +76,7 @@ enum llm_type {
     LLM_TYPE_32B,
     LLM_TYPE_34B,
     LLM_TYPE_35B,
+    LLM_TYPE_36B, // Seed OSS
     LLM_TYPE_40B,
     LLM_TYPE_65B,
     LLM_TYPE_70B,
@@ -109,7 +110,6 @@ enum llm_type {
     LLM_TYPE_355B_A32B, // GLM-4.5
     LLM_TYPE_E2B,
     LLM_TYPE_E4B,
-    LLM_TYPE_36B // Seed OSS
 };
 
 std::string llama_rope_scaling_type_name(llama_rope_scaling_type rope_scaling_type);

up.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+cd /devel/tools/llama.cpp
+git fetch && git pull && ./prebld.sh && ./bld.sh