Upload final Fermata merged model

chat_template.jinja

@@ -1,47 +1,4 @@
-{{ bos_token }}
-{%- 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 -%}
+{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in 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 + '
+' + message['content'] | trim + '<end_of_turn>
+' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
+'}}{% endif %}

config.json

@@ -1,62 +1,35 @@
 {
   "architectures": [
-    "Gemma3ForConditionalGeneration"
+    "Gemma2ForCausalLM"
   ],
-  "boi_token_index": 255999,
-  "eoi_token_index": 256000,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
   "eos_token_id": [
     1,
-    106
+    107
   ],
-  "image_token_index": 262144,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2304,
   "initializer_range": 0.02,
-  "mm_tokens_per_image": 256,
-  "model_type": "gemma3",
-  "text_config": {
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "attn_logit_softcapping": null,
-    "cache_implementation": "hybrid",
-    "final_logit_softcapping": null,
-    "head_dim": 256,
-    "hidden_activation": "gelu_pytorch_tanh",
-    "hidden_size": 2560,
-    "initializer_range": 0.02,
-    "intermediate_size": 10240,
-    "max_position_embeddings": 131072,
-    "model_type": "gemma3_text",
-    "num_attention_heads": 8,
-    "num_hidden_layers": 34,
-    "num_key_value_heads": 4,
-    "query_pre_attn_scalar": 256,
-    "rms_norm_eps": 1e-06,
-    "rope_local_base_freq": 10000.0,
-    "rope_scaling": {
-      "factor": 8.0,
-      "rope_type": "linear"
-    },
-    "rope_theta": 1000000.0,
-    "sliding_window": 1024,
-    "sliding_window_pattern": 6,
-    "torch_dtype": "float32",
-    "use_cache": true,
-    "vocab_size": 262208
-  },
+  "intermediate_size": 9216,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
   "torch_dtype": "float32",
   "transformers_version": "4.52.4",
-  "vision_config": {
-    "attention_dropout": 0.0,
-    "hidden_act": "gelu_pytorch_tanh",
-    "hidden_size": 1152,
-    "image_size": 896,
-    "intermediate_size": 4304,
-    "layer_norm_eps": 1e-06,
-    "model_type": "siglip_vision_model",
-    "num_attention_heads": 16,
-    "num_channels": 3,
-    "num_hidden_layers": 27,
-    "patch_size": 14,
-    "torch_dtype": "float32",
-    "vision_use_head": false
-  }
-}
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -1,13 +1,11 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "do_sample": true,
   "eos_token_id": [
     1,
-    106
+    107
   ],
   "pad_token_id": 0,
-  "top_k": 64,
-  "top_p": 0.95,
   "transformers_version": "4.52.4"
 }

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8339594916df49ff610af8375cd8c3a4db1ed963e69a8806ec2c66c983c971
+size 4992576136

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cef4f7bb067b77727fb1de968246c9f34d9996cfbf5825c62932a18946f03aa
+size 4983443424

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a4f55cec0827b32710551e5fb86a364b283db9cc780e12f98166e7b5f445a4
+size 481381384

special_tokens_map.json

@@ -1,5 +1,8 @@
 {
-  "boi_token": "<start_of_image>",
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
   "bos_token": {
     "content": "<bos>",
     "lstrip": false,
@@ -7,7 +10,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "eoi_token": "<end_of_image>",
   "eos_token": {
     "content": "<eos>",
     "lstrip": false,
@@ -15,7 +17,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "image_token": "<image_soft_token>",
   "pad_token": {
     "content": "<pad>",
     "lstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
-size 33384568
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
-size 4689074
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003