modify scripts

.gitignore

@@ -0,0 +1 @@
+.DS_Store

README_QUANTIZATION.md

@@ -0,0 +1,63 @@
+# Model Quantization with llama.cpp
+
+This README explains how to use the `quantize_models.sh` script to create quantized versions of your GGUF models.
+
+## Prerequisites
+
+- llama.cpp must be cloned and built in this directory
+- You need a base GGUF model (default is `osmosis-mcp-4B-BF16.gguf`)
+
+## How to Use
+
+1. Make sure your base model is in the current directory
+2. Run the script:
+
+```bash
+./quantize_models.sh
+```
+
+## Supported Quantization Formats
+
+The script will create the following quantized versions:
+
+| Format   | Description                                                     | Approximate Size   |
+|----------|-----------------------------------------------------------------|-------------------|
+| Q4_K_S   | 4-bit quantization, smaller size                                | ~29% of original  |
+| Q5_K_M   | 5-bit quantization, medium size                                 | ~34% of original  |
+| Q5_K_S   | 5-bit quantization, smaller size                                | ~33% of original  |
+| Q6_K     | 6-bit quantization, balanced quality and size                   | ~38% of original  |
+| IQ4_XS   | Improved 4-bit non-linear quantization, extra small             | ~27% of original  |
+| Q8_0     | 8-bit quantization, highest quality                             | ~50% of original  |
+| Q2_K     | 2-bit quantization, extremely small                             | ~18% of original  |
+| Q3_K_L   | 3-bit quantization, larger size                                 | ~25% of original  |
+| Q3_K_M   | 3-bit quantization, medium size                                 | ~23% of original  |
+| Q3_K_S   | 3-bit quantization, smaller size                                | ~21% of original  |
+| Q4_K_M   | 4-bit quantization, medium size                                 | ~28% of original  |
+
+## Customizing the Script
+
+If you want to quantize a different base model, edit the `INPUT_MODEL` variable in the script:
+
+```bash
+# Input model file
+INPUT_MODEL="your-model-file.gguf"
+```
+
+## Time and Space Requirements
+
+- Quantization can take from several minutes to an hour depending on your hardware
+- Make sure you have enough free disk space for all the output models
+- The total disk space required will be approximately 3x the size of the original model
+
+## Using the Quantized Models
+
+Each quantized model can be used with llama.cpp tools:
+
+```bash
+llama.cpp/build/bin/llama-cli -m osmosis-mcp-4b.Q4_K_S.gguf -p "Your prompt here"
+```
+
+Choose the quantization format based on your needs:
+- Smaller quantization (Q2_K, Q3_K_S) for limited hardware resources
+- Medium quantization (Q4_K_M, Q5_K_S) for balanced performance
+- Larger quantization (Q6_K, Q8_0) for highest quality with sufficient hardware 

pt.jinja

@@ -0,0 +1,102 @@
+{%- 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) %}
+ 
+{#— scan backward without using reverse filter —#}
+{%- for i in range(messages|length - 1, -1, -1) %}
+    {%- set message = messages[i] %}
+    {%- set index = i %}
+    {%- set tool_start = "<tool_response>" %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = message.content[:tool_start_length] %}
+    {%- set tool_end = "</tool_response>" %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (message.content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = message.content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not (start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- 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>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).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 %}

quantize_models.sh

@@ -0,0 +1,71 @@
+#!/bin/bash
+
+cd llama.cpp
+python3 convert_hf_to_gguf.py ../../osmosis-mcp-4b --outtype bf16
+cd ..
+
+# Input model file
+INPUT_MODEL="osmosis-mcp-4B-BF16.gguf"
+
+# Define quantization formats to generate
+QUANT_FORMATS=(
+    "Q4_K_S"
+    "Q5_K_M"
+    "Q5_K_S"
+    "Q6_K"
+    "IQ4_XS"
+    "Q8_0"
+    "Q2_K"
+    "Q3_K_L"
+    "Q3_K_M"
+    "Q3_K_S"
+    "Q4_K_M"
+)
+
+# Check if input model exists
+if [ ! -f "$INPUT_MODEL" ]; then
+    echo "Error: Input model file $INPUT_MODEL not found."
+    exit 1
+fi
+
+# Path to llama-quantize tool
+QUANTIZE_TOOL="llama.cpp/build/bin/llama-quantize"
+
+# Check if quantize tool exists
+if [ ! -f "$QUANTIZE_TOOL" ]; then
+    echo "Error: Quantize tool not found at $QUANTIZE_TOOL"
+    exit 1
+fi
+
+# Process each quantization format
+for format in "${QUANT_FORMATS[@]}"; do
+    echo "------------------------------------------------------"
+    echo "Starting quantization: $format"
+    echo "------------------------------------------------------"
+    
+    # Define output filename with the exact format requested
+    OUTPUT_MODEL="osmosis-mcp-4b.${format}.gguf"
+    
+    # Check if output model already exists
+    if [ -f "$OUTPUT_MODEL" ]; then
+        echo "Model $OUTPUT_MODEL already exists. Skipping..."
+        continue
+    fi
+    
+    # Run quantization
+    echo "Quantizing to $format..."
+    "$QUANTIZE_TOOL" "$INPUT_MODEL" "$OUTPUT_MODEL" "$format"
+    
+    # Check if quantization was successful
+    if [ $? -eq 0 ]; then
+        echo "Successfully created $OUTPUT_MODEL"
+    else
+        echo "Failed to create $OUTPUT_MODEL"
+    fi
+    
+    echo ""
+done
+
+echo "All quantizations completed!"
+echo "Generated models:"
+ls -lah osmosis-mcp-4b.*.gguf 

tokenizer_config.json

@@ -227,7 +227,7 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n \n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n \n{#— scan backward without using reverse filter —#}\n{%- for i in range(messages|length - 1, -1, -1) %}\n    {%- set message = messages[i] %}\n    {%- set index = i %}\n    {%- set tool_start = \"<tool_response>\" %}\n    {%- set tool_start_length = tool_start|length %}\n    {%- set start_of_message = message.content[:tool_start_length] %}\n    {%- set tool_end = \"</tool_response>\" %}\n    {%- set tool_end_length = tool_end|length %}\n    {%- set start_pos = (message.content|length) - tool_end_length %}\n    {%- if start_pos < 0 %}\n        {%- set start_pos = 0 %}\n    {%- endif %}\n    {%- set end_of_message = message.content[start_pos:] %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not (start_of_message == tool_start and end_of_message == tool_end) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = (message.content.split('</think>')|last).lstrip('\\n') %}\n                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\\n') %}\n                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",