Upload GGUF model

.gitattributes

@@ -33,3 +33,5 @@ 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
+gemma3-270m-summarizer-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,49 @@
+FROM gemma3-270m-summarizer-Q4_K_M.gguf
+
+# Default system prompt (used when user doesn't provide one)
+SYSTEM """
+You are a careful assistant that generates task summaries and git branch names.
+
+Output EXACTLY two lines with no other text:
+Line 1: A 2-4 word summary (Title Case, no punctuation)
+Line 2: A git branch name (kebab-case, lowercase, [a-z0-9-] only, max 4 words, prefix with a category like bug/, feat/, etc.)
+
+Examples:
+Fix Login Bug
+bug/fix-login
+
+Add Dark Mode
+feat/add-dark-mode
+
+API Docs
+docs/api-polish
+
+Refactor User Service V2
+chore/user-service-v2-refactor
+
+Turn this request for code changes into:
+1) a 2-4 word summary (Title Case),
+2) a friendly git branch name (prefixed kebab-case).
+"""
+
+TEMPLATE """{{- $systemPromptAdded := false }}
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 }}
+{{- if eq .Role "user" }}<start_of_turn>user
+{{- if (and (not $systemPromptAdded) $.System) }}
+{{- $systemPromptAdded = true }}
+{{ $.System }}
+{{ end }}
+{{ .Content }}<end_of_turn>
+{{ if $last }}<start_of_turn>model
+{{ end }}
+{{- else if eq .Role "assistant" }}<start_of_turn>model
+{{ .Content }}{{ if not $last }}<end_of_turn>
+{{ end }}
+{{- end }}
+{{- end }}
+"""
+
+PARAMETER stop "<end_of_turn>"
+PARAMETER top_k 64
+PARAMETER top_p 0.95

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,47 @@
+
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- 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") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

config.json

@@ -0,0 +1,56 @@
+{
+    "_sliding_window_pattern": 6,
+    "architectures": [
+        "Gemma3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 106,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 640,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "layer_types": [
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 18,
+    "num_key_value_heads": 1,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": 512,
+    "transformers_version": "4.56.2",
+    "unsloth_fixed": true,
+    "unsloth_version": "2025.10.10",
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262144
+}

gemma3-270m-summarizer-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13f99933b0b41c0b2a9902d86c2f48d130f35eceb12de3b0c5326728fc14b12
+size 253114752

params

@@ -0,0 +1,7 @@
+{
+  "top_k": 64,
+  "top_p": 0.95,
+  "stop": [
+    "<end_of_turn>"
+  ]
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

system

@@ -0,0 +1,22 @@
+You are a careful assistant that generates task summaries and git branch names.
+
+Output EXACTLY two lines with no other text:
+Line 1: A 2-4 word summary (Title Case, no punctuation)
+Line 2: A git branch name (kebab-case, lowercase, [a-z0-9-] only, max 4 words, prefix with a category like bug/, feat/, etc.)
+
+Examples:
+Fix Login Bug
+bug/fix-login
+
+Add Dark Mode
+feat/add-dark-mode
+
+API Docs
+docs/api-polish
+
+Refactor User Service V2
+chore/user-service-v2-refactor
+
+Turn this request for code changes into:
+1) a 2-4 word summary (Title Case),
+2) a friendly git branch name (prefixed kebab-case).

template

@@ -0,0 +1,16 @@
+{{- $systemPromptAdded := false }}
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 }}
+{{- if eq .Role "user" }}<start_of_turn>user
+{{- if (and (not $systemPromptAdded) $.System) }}
+{{- $systemPromptAdded = true }}
+{{ $.System }}
+{{ end }}
+{{ .Content }}<end_of_turn>
+{{ if $last }}<start_of_turn>model
+{{ end }}
+{{- else if eq .Role "assistant" }}<start_of_turn>model
+{{ .Content }}{{ if not $last }}<end_of_turn>
+{{ end }}
+{{- end }}
+{{- end }}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074