Upload folder using huggingface_hub
Browse files- .chat_template.jinja.swx +0 -0
- added_tokens.json +3 -0
- chat_template.jinja +94 -0
- chat_template.json +3 -0
- config.json +62 -0
- generation_config.json +13 -0
.chat_template.jinja.swx
ADDED
|
File without changes
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}
|
| 2 |
+
|
| 3 |
+
{%- if messages[0]['role'] == 'system' -%}
|
| 4 |
+
{%- set sys_content = (messages[0]['content'] if messages[0]['content'] is string else messages[0]['content'][0]['text']) -%}
|
| 5 |
+
{%- if tools is defined and tools is not none -%}
|
| 6 |
+
{%- set sys_content = sys_content + '\n\nTools (functions) are available. Respond with a python list *inside* a ```tool_code``` block when you decide to call them.\nExample:\n```tool_code\n[func_name(arg="value")]\n```\n\nAvailable tools (Schemas):\n' + tools | tojson(indent=4) -%}
|
| 7 |
+
{%- endif -%}
|
| 8 |
+
{%- set first_user_prefix = sys_content + '\n\n' -%}
|
| 9 |
+
{%- set loop_messages = messages[1:] -%}
|
| 10 |
+
{%- else -%}
|
| 11 |
+
{%- set first_user_prefix = '' -%}
|
| 12 |
+
{%- set loop_messages = messages -%}
|
| 13 |
+
{%- endif -%}
|
| 14 |
+
|
| 15 |
+
{%- for m in loop_messages -%}
|
| 16 |
+
{%- if not loop.first -%}
|
| 17 |
+
{%- set prev_msg = loop_messages[loop.index0-1] -%}
|
| 18 |
+
|
| 19 |
+
{%- if prev_msg['role'] == 'user' -%}
|
| 20 |
+
{%- if m['role'] != 'assistant' -%}
|
| 21 |
+
{{ raise_exception('User message must be followed by assistant') }}
|
| 22 |
+
{%- endif -%}
|
| 23 |
+
{%- elif prev_msg['role'] == 'assistant' and 'tool_calls' in prev_msg -%}
|
| 24 |
+
{%- if m['role'] != 'tool' -%}
|
| 25 |
+
{{ raise_exception('Assistant with tool_calls must be followed by tool') }}
|
| 26 |
+
{%- endif -%}
|
| 27 |
+
{%- elif prev_msg['role'] == 'assistant' and 'tool_calls' not in prev_msg -%}
|
| 28 |
+
{%- if m['role'] not in ['user', 'tool'] -%}
|
| 29 |
+
{{ raise_exception('Assistant without tool_calls must be followed by user or tool') }}
|
| 30 |
+
{%- endif -%}
|
| 31 |
+
{%- elif prev_msg['role'] == 'tool' -%}
|
| 32 |
+
{%- if m['role'] not in ['assistant', 'user'] -%}
|
| 33 |
+
{{ raise_exception('Tool message must be followed by assistant or user') }}
|
| 34 |
+
{%- endif -%}
|
| 35 |
+
{%- endif -%}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endfor -%}
|
| 38 |
+
|
| 39 |
+
{%- for message in loop_messages -%}
|
| 40 |
+
{%- set role = 'model' if message['role'] == 'assistant' else ('user' if message['role']=='tool' else message['role']) -%}
|
| 41 |
+
{{ '<start_of_turn>' ~ role ~ '\n' }}
|
| 42 |
+
|
| 43 |
+
{%- if loop.first -%}
|
| 44 |
+
{{ first_user_prefix }}
|
| 45 |
+
{%- endif -%}
|
| 46 |
+
|
| 47 |
+
{%- if message['role'] in ['user','assistant'] and 'tool_calls' not in message -%}
|
| 48 |
+
{%- if message['content'] is string -%}
|
| 49 |
+
{{ message['content'] | trim }}
|
| 50 |
+
{%- elif message['content'] is iterable -%}
|
| 51 |
+
{%- for item in message['content'] -%}
|
| 52 |
+
{%- if item['type']=='image' -%}<start_of_image>{%- elif item['type']=='text' -%}{{ item['text'] | trim }}{%- endif -%}
|
| 53 |
+
{%- endfor -%}
|
| 54 |
+
{%- endif -%}
|
| 55 |
+
{%- endif -%}
|
| 56 |
+
|
| 57 |
+
{%- if message['role'] == 'tool' -%}
|
| 58 |
+
```tool_response
|
| 59 |
+
{{ message['content'] | trim }}
|
| 60 |
+
```
|
| 61 |
+
{%- endif -%}
|
| 62 |
+
|
| 63 |
+
{%- if 'tool_calls' in message -%}
|
| 64 |
+
```tool_code
|
| 65 |
+
[
|
| 66 |
+
{%- for tc in message.tool_calls -%}
|
| 67 |
+
{%- set fc = tc.function if tc.function is defined else tc -%}
|
| 68 |
+
{{ fc.name }}(
|
| 69 |
+
{%- if fc.arguments is iterable and fc.arguments is mapping -%}
|
| 70 |
+
{%- set first=true -%}
|
| 71 |
+
{%- for k,v in fc.arguments.items() -%}
|
| 72 |
+
{%- if not first %}, {% endif -%}
|
| 73 |
+
{{ k }}={{ v | tojson }}{%- set first=false -%}
|
| 74 |
+
{%- endfor -%}
|
| 75 |
+
{%- elif fc.arguments is iterable -%}
|
| 76 |
+
{{ fc.arguments | map('tojson') | join(', ') }}
|
| 77 |
+
{%- else -%}
|
| 78 |
+
{{ fc.arguments | tojson }}
|
| 79 |
+
{%- endif -%}
|
| 80 |
+
)
|
| 81 |
+
{%- if not loop.last %},
|
| 82 |
+
{%- endif -%}
|
| 83 |
+
{%- endfor -%}
|
| 84 |
+
]
|
| 85 |
+
```
|
| 86 |
+
{%- endif -%}
|
| 87 |
+
|
| 88 |
+
{{ '<end_of_turn>\n' }}
|
| 89 |
+
{%- endfor -%}
|
| 90 |
+
|
| 91 |
+
{%- if add_generation_prompt -%}
|
| 92 |
+
<start_of_turn>model\n
|
| 93 |
+
{%- endif -%}
|
| 94 |
+
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"boi_token_index": 255999,
|
| 6 |
+
"eoi_token_index": 256000,
|
| 7 |
+
"eos_token_id": [
|
| 8 |
+
1,
|
| 9 |
+
106
|
| 10 |
+
],
|
| 11 |
+
"image_token_index": 262144,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"mm_tokens_per_image": 256,
|
| 14 |
+
"model_type": "gemma3",
|
| 15 |
+
"text_config": {
|
| 16 |
+
"attention_bias": false,
|
| 17 |
+
"attention_dropout": 0.0,
|
| 18 |
+
"attn_logit_softcapping": null,
|
| 19 |
+
"cache_implementation": "hybrid",
|
| 20 |
+
"final_logit_softcapping": null,
|
| 21 |
+
"head_dim": 128,
|
| 22 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 23 |
+
"hidden_size": 5376,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 21504,
|
| 26 |
+
"max_position_embeddings": 131072,
|
| 27 |
+
"model_type": "gemma3_text",
|
| 28 |
+
"num_attention_heads": 32,
|
| 29 |
+
"num_hidden_layers": 62,
|
| 30 |
+
"num_key_value_heads": 16,
|
| 31 |
+
"query_pre_attn_scalar": 168,
|
| 32 |
+
"rms_norm_eps": 1e-06,
|
| 33 |
+
"rope_local_base_freq": 10000.0,
|
| 34 |
+
"rope_scaling": {
|
| 35 |
+
"factor": 8.0,
|
| 36 |
+
"rope_type": "linear"
|
| 37 |
+
},
|
| 38 |
+
"rope_theta": 1000000.0,
|
| 39 |
+
"sliding_window": 1024,
|
| 40 |
+
"sliding_window_pattern": 6,
|
| 41 |
+
"torch_dtype": "float16",
|
| 42 |
+
"use_cache": true,
|
| 43 |
+
"vocab_size": 262208
|
| 44 |
+
},
|
| 45 |
+
"torch_dtype": "float16",
|
| 46 |
+
"transformers_version": "4.51.3",
|
| 47 |
+
"vision_config": {
|
| 48 |
+
"attention_dropout": 0.0,
|
| 49 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 50 |
+
"hidden_size": 1152,
|
| 51 |
+
"image_size": 896,
|
| 52 |
+
"intermediate_size": 4304,
|
| 53 |
+
"layer_norm_eps": 1e-06,
|
| 54 |
+
"model_type": "siglip_vision_model",
|
| 55 |
+
"num_attention_heads": 16,
|
| 56 |
+
"num_channels": 3,
|
| 57 |
+
"num_hidden_layers": 27,
|
| 58 |
+
"patch_size": 14,
|
| 59 |
+
"torch_dtype": "float16",
|
| 60 |
+
"vision_use_head": false
|
| 61 |
+
}
|
| 62 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"cache_implementation": "hybrid",
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
1,
|
| 7 |
+
106
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"top_k": 64,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.51.3"
|
| 13 |
+
}
|