Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,33 @@
----
-license: gemma
----
+---
+license: gemma
+tags:
+  - coding
+  - rag
+  - gemma
+  - chain-of-thought
+base_model: google/functiongemma-270m-it
+---
+
+# FunctionGemma Coding Assistant
+
+Production-ready coding assistant with:
+- Chain of Recursive Thoughts reasoning
+- Web search integration (optional)
+- Local knowledge base (SQLite + FAISS)
+- Fine-tuned on 20k diverse code samples
+
+## Usage
+from transformers import AutoModelForCausalLM, AutoTokenizermodel = AutoModelForCausalLM.from_pretrained("shaurya79/functiongemma-coding-assistant")
+tokenizer = AutoTokenizer.from_pretrained("shaurya79/functiongemma-coding-assistant")prompt = "Write a Python function to reverse a string"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=512)
+print(tokenizer.decode(outputs))
+
+## Features
+- Code generation (Python, JavaScript, etc.)
+- Detailed explanations
+- Bug fixing suggestions
+- Multi-language support
+
+## Size
+~250-300 MB (quantized)

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<end_of_image>": 262145,
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,282 @@
+{%- macro format_parameters(properties, required) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- if key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{- key }}:{description:<escape>{{ value['description'] }}<escape>
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    ,enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'OBJECT' -%}
+                ,properties:{
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                {%- elif value is mapping -%}
+                    {{- format_parameters(value, value['required'] | default([])) -}}
+                {%- endif -%}
+                }
+                {%- if value['required'] -%}
+                    ,required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <escape>{{- item -}}<escape>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    ,items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <escape>{{- req_item -}}<escape>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            ,type:<escape>{{ value['type'] | upper }}<escape>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{% macro format_function_declaration(tool_data) -%}
+declaration:{{- tool_data['function']['name'] -}}
+{description:<escape>{{- tool_data['function']['description'] -}}<escape>
+{%- set params = tool_data['function']['parameters'] -%}
+{%- if params -%}
+    ,parameters:{
+    {%- if params['properties'] -%}
+        properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+    {%- endif -%}
+    {%- if params['required'] -%}
+        required:[
+        {%- for item in params['required'] -%}
+            <escape>{{- item -}}<escape>
+            {{- ',' if not loop.last -}}
+        {%- endfor -%}
+        ],
+    {%- endif -%}
+    {%- if params['type'] -%}
+        type:<escape>{{- params['type'] | upper -}}<escape>}
+    {%- endif -%}
+{%- endif -%}
+}
+{%- endmacro -%}
+{% macro format_argument(argument, escape_keys=True) -%}
+{%- if argument is string -%}
+    {{- '<escape>' + argument + '<escape>' -}}
+{%- elif argument is boolean -%}
+    {%- if argument -%}
+        {{- 'true' -}}
+    {%- else -%}
+        {{- 'false' -}}
+    {%- endif -%}
+{%- elif argument is mapping -%}
+    {{- '{' -}}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in argument | dictsort -%}
+        {%- if ns.found_first %},{% endif -%}
+        {%- set ns.found_first = true -%}
+        {%- if escape_keys -%}
+            {{- '<escape>' + key + '<escape>' -}}
+        {%- else -%}
+            {{- key -}}
+        {%- endif -%}
+        :{{- format_argument(value, escape_keys=escape_keys) -}}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- elif argument is sequence -%}
+    {{- '[' -}}
+    {%- for item in argument -%}
+        {{- format_argument(item, escape_keys=escape_keys) -}}
+        {%- if not loop.last %},{% endif -%}
+    {%- endfor -%}
+    {{- ']' -}}
+{%- else -%}
+    {{- argument -}}
+{%- endif -%}
+{%- endmacro -%}
+{{ bos_token }}
+{%- set ns = namespace(prev_message_type=None) -%}
+{#- Tool Declarations -#}
+{%- set loop_messages = messages -%}
+{%- if tools or messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+    {{- '<start_of_turn>developer\n' -}}
+    {%- if messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {%- if item['type'] == 'text' -%}
+                    {{- item['text'] | trim -}}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- else -%}
+        {{- 'You are a model that can do function calling with the following functions' -}}
+        {%- set loop_messages = messages -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<start_function_declaration>' -}}
+            {{- format_function_declaration(tool) | trim }}
+            {{- '<end_function_declaration>' -}}
+        {%- endfor %}
+    {%- endif -%}
+    {{- '<end_of_turn>\n' }}
+{%- endif %}
+{#- Loop through messages. -#}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {#- Rename "assistant" to "model". -#}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {%- if role != 'tool' -%}
+        {%- if ns.prev_message_type != 'tool_response' -%}
+            {{- '<start_of_turn>' + role + '\n' }}
+        {%- endif -%}
+        {%- set ns.prev_message_type = None -%}
+        {%- if 'content' in message and message['content'] is not none -%}
+            {%- if message['content'] is string -%}
+                {{ message['content'] | trim }}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'image' -%}
+                        {{ '<start_of_image>' }}
+                    {%- elif item['type'] == 'text' -%}
+                        {{ item['text'] | trim }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in user/assistant message") }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'content' -%}
+        {%- endif -%}
+        {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls'] is iterable -%}
+            {#- Tool Calls -#}
+            {%- for tool_call in message['tool_calls'] -%}
+                {% set function = tool_call['function'] %}
+                {{-  '<start_function_call>call:' + function['name'] + '{' -}}
+                {%- if 'arguments' in function -%}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns.found_first %},{% endif -%}
+                            {%- set ns.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {# This handles string-JSON, just in case #}
+                    {{ function['arguments'] }}
+                    {%- endif %}
+                {%- endif -%}
+                {{- '}<end_function_call>' -}}
+            {%- endfor -%}
+            {%- if loop.last -%}
+                {{ '<start_function_response>' }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'tool_call' -%}
+        {%- endif -%}
+    {%- else -%}
+        {#- Tool Responses -#}
+        {%- if 'content' in message and message['content'] -%}
+            {%- if message['content'] is mapping -%}
+                {%- if 'name' in message['content'] and 'response' in message['content'] -%}
+                    {{ '<start_function_response>response:' + message['content']['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content']['response'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- elif 'name' in message -%}
+                    {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- else -%}
+                    {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                {%- endif -%}
+            {%- elif message['content'] is string -%}
+                {%- if 'name' in message -%}
+                     {{ '<start_function_response>response:' + message['name'] | trim + '{value:' + format_argument(message['content'], escape_keys=False) + '}<end_function_response>' }}
+                {%- else -%}
+                     {{ raise_exception("Invalid tool response: 'name' must be provided.") }}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item is mapping -%}
+                        {%- if 'name' in item and 'response' in item -%}
+                            {{ '<start_function_response>response:' + item['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item['response'] | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- elif 'name' in message -%}
+                            {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- else -%}
+                            {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                        {%- endif -%}
+                    {%- else -%}
+                        {{ raise_exception("Invalid tool response message: multiple responses must all be mappings") }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in tool message: must be mapping, sequence of mappings, or string.") }}
+            {%- endif -%}
+        {%- endif -%}
+        {%- set ns.prev_message_type = 'tool_response' -%}
+    {%- endif -%}
+    {%- if ns.prev_message_type not in ['tool_call', 'tool_response'] -%}
+        {{ '<end_of_turn>\n' }}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' -%}
+        {{- '<start_of_turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,7 @@
+{
+  "model_name": "FunctionGemma Coding Assistant",
+  "version": "1.0.0",
+  "base_model": "google/functiongemma-270m-it",
+  "training_steps": 1000,
+  "dataset_size": 9997
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c66c66c80dfc0661e17b54df7904c96c3b073d915cae9d82ae3e344bb711bb
+size 536223056

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sfr_token": "<start_function_response>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b09a0b4a803ad453063ca4bb49a784540e8120004e2450e025df2b27d41fb2
+size 33384899

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa009fcbc3589a9904d30d04834094fea4653c2ac6d2de2cd1262d4f7a50ceb3
+size 4689144