SpaceGhost commited on
Commit
5410da1
·
verified ·
1 Parent(s): 53efac5

Release SpaceCode-E2B v2 Merged 16-bit (APROVADO PARA PRODUÇÃO EDUCACIONAL - 88% 50-MCQ, 95.2% composite)

Browse files
config.json CHANGED
@@ -64,7 +64,6 @@
64
  "eos_token_id": 1,
65
  "expert_intermediate_size": null,
66
  "final_logit_softcapping": 30.0,
67
- "global_head_dim": 512,
68
  "head_dim": 256,
69
  "hidden_activation": "gelu_pytorch_tanh",
70
  "hidden_size": 1536,
@@ -113,11 +112,33 @@
113
  "moe_intermediate_size": null,
114
  "num_attention_heads": 8,
115
  "num_experts": null,
116
- "num_global_key_value_heads": null,
117
  "num_hidden_layers": 35,
118
  "num_key_value_heads": 1,
119
  "num_kv_shared_layers": 20,
120
  "pad_token_id": 0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
121
  "rms_norm_eps": 1e-06,
122
  "rope_parameters": {
123
  "full_attention": {
@@ -140,7 +161,7 @@
140
  "vocab_size_per_layer_input": 262144
141
  },
142
  "tie_word_embeddings": true,
143
- "transformers_version": "5.5.0",
144
  "unsloth_fixed": true,
145
  "video_token_id": 258884,
146
  "vision_config": {
@@ -181,7 +202,7 @@
181
  "rms_norm_eps": 1e-06,
182
  "rope_parameters": {
183
  "rope_theta": 100.0,
184
- "rope_type": "default"
185
  },
186
  "standardize": false,
187
  "use_clipped_linears": true
 
64
  "eos_token_id": 1,
65
  "expert_intermediate_size": null,
66
  "final_logit_softcapping": 30.0,
 
67
  "head_dim": 256,
68
  "hidden_activation": "gelu_pytorch_tanh",
69
  "hidden_size": 1536,
 
112
  "moe_intermediate_size": null,
113
  "num_attention_heads": 8,
114
  "num_experts": null,
 
115
  "num_hidden_layers": 35,
116
  "num_key_value_heads": 1,
117
  "num_kv_shared_layers": 20,
118
  "pad_token_id": 0,
119
+ "per_layer_config": {
120
+ "04": {
121
+ "head_dim": 512
122
+ },
123
+ "09": {
124
+ "head_dim": 512
125
+ },
126
+ "14": {
127
+ "head_dim": 512
128
+ },
129
+ "19": {
130
+ "head_dim": 512
131
+ },
132
+ "24": {
133
+ "head_dim": 512
134
+ },
135
+ "29": {
136
+ "head_dim": 512
137
+ },
138
+ "34": {
139
+ "head_dim": 512
140
+ }
141
+ },
142
  "rms_norm_eps": 1e-06,
143
  "rope_parameters": {
144
  "full_attention": {
 
161
  "vocab_size_per_layer_input": 262144
162
  },
163
  "tie_word_embeddings": true,
164
+ "transformers_version": "5.17.0",
165
  "unsloth_fixed": true,
166
  "video_token_id": 258884,
167
  "vision_config": {
 
202
  "rms_norm_eps": 1e-06,
203
  "rope_parameters": {
204
  "rope_theta": 100.0,
205
+ "rope_type": "axial"
206
  },
207
  "standardize": false,
208
  "use_clipped_linears": true
generation_config.json CHANGED
@@ -2,6 +2,7 @@
2
  "bos_token_id": 2,
3
  "do_sample": true,
4
  "eos_token_id": [
 
5
  1,
6
  106,
7
  50
@@ -10,5 +11,5 @@
10
  "temperature": 1.0,
11
  "top_k": 64,
12
  "top_p": 0.95,
13
- "transformers_version": "5.5.0"
14
  }
 
2
  "bos_token_id": 2,
3
  "do_sample": true,
4
  "eos_token_id": [
5
+ 1,
6
  1,
7
  106,
8
  50
 
11
  "temperature": 1.0,
12
  "top_k": 64,
13
  "top_p": 0.95,
14
+ "transformers_version": "5.17.0"
15
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d230d43de9b5ea5470a64f738d308a07d74d5a3c41f669e5198bf6982b36c8fa
3
  size 10246621918
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc23d5f9c28db872956af6cc3ad2f9c78b2703cd630ccba311597dfc982deb59
3
  size 10246621918
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
3
- size 32169626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d8bced9d66859cd2c3f4dcd8ab427197d4d46af3d9598b72af9fcf80b8392e
3
+ size 32169781
tokenizer_config.json CHANGED
@@ -17,7 +17,8 @@
17
  "<|video|>"
18
  ],
19
  "image_token": "<|image|>",
20
- "is_local": true,
 
21
  "mask_token": "<mask>",
22
  "max_length": 2048,
23
  "model_max_length": 131072,
@@ -44,7 +45,7 @@
44
  "pad_to_multiple_of": null,
45
  "pad_token": "<pad>",
46
  "pad_token_type_id": 0,
47
- "padding_side": "left",
48
  "processor_class": "Gemma4Processor",
49
  "response_schema": {
50
  "properties": {
@@ -291,5 +292,6 @@
291
  "normalized": false,
292
  "special": true
293
  }
294
- }
295
- }
 
 
17
  "<|video|>"
18
  ],
19
  "image_token": "<|image|>",
20
+ "is_local": false,
21
+ "local_files_only": false,
22
  "mask_token": "<mask>",
23
  "max_length": 2048,
24
  "model_max_length": 131072,
 
45
  "pad_to_multiple_of": null,
46
  "pad_token": "<pad>",
47
  "pad_token_type_id": 0,
48
+ "padding_side": "right",
49
  "processor_class": "Gemma4Processor",
50
  "response_schema": {
51
  "properties": {
 
292
  "normalized": false,
293
  "special": true
294
  }
295
+ },
296
+ "chat_template": "{%- macro format_parameters(properties, required, filter_keys=false) -%}\n {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in properties | dictsort -%}\n {%- set add_comma = false -%}\n {%- if not filter_keys or key not in standard_keys -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {{ key }}:{\n {%- if value['description'] -%}\n description:<|\"|>{{ value['description'] }}<|\"|>\n {%- set add_comma = true -%}\n {%- endif -%}\n {%- if value['type'] | upper == 'STRING' -%}\n {%- if value['enum'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n enum:{{ format_argument(value['enum']) }}\n {%- endif -%}\n {%- elif value['type'] | upper == 'ARRAY' -%}\n {%- if value['items'] is mapping and value['items'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n items:{\n {%- set ns_items = namespace(found_first=false) -%}\n {%- for item_key, item_value in value['items'] | dictsort -%}\n {%- if item_value is not none -%}\n {%- if ns_items.found_first %},{% endif -%}\n {%- set ns_items.found_first = true -%}\n {%- if item_key == 'properties' -%}\n properties:{\n {%- if item_value is mapping -%}\n {{- format_parameters(item_value, value['items']['required'] | default([])) -}}\n {%- endif -%}\n }\n {%- elif item_key == 'required' -%}\n required:[\n {%- for req_item in item_value -%}\n <|\"|>{{- req_item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- elif item_key == 'type' -%}\n {%- if item_value is string -%}\n type:{{ format_argument(item_value | upper) }}\n {%- else -%}\n type:{{ format_argument(item_value | map('upper') | list) }}\n {%- endif -%}\n {%- else -%}\n {{ item_key }}:{{ format_argument(item_value) }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n }\n {%- endif -%}\n {%- endif -%}\n {%- if value['nullable'] %}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n nullable:true\n {%- endif -%}\n {%- if value['type'] | upper == 'OBJECT' -%}\n {%- if value['properties'] is defined and value['properties'] is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value['properties'], value['required'] | default([])) -}}\n }\n {%- elif value is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}\n }\n {%- endif -%}\n {%- if value['required'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n required:[\n {%- for item in value['required'] | default([]) -%}\n <|\"|>{{- item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- endif -%}\n {%- endif -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n type:<|\"|>{{ value['type'] | upper }}<|\"|>}\n {%- endif -%}\n {%- endfor -%}\n{%- endmacro -%}\n{%- macro format_function_declaration(tool_data) -%}\n declaration:{{- tool_data['function']['name'] -}}{description:<|\"|>{{- tool_data['function']['description'] -}}<|\"|>\n {%- set params = tool_data['function']['parameters'] -%}\n {%- if params -%}\n ,parameters:{\n {%- if params['properties'] -%}\n properties:{ {{- format_parameters(params['properties'], params['required']) -}} },\n {%- endif -%}\n {%- if params['required'] -%}\n required:[\n {%- for item in params['required'] -%}\n <|\"|>{{- item -}}<|\"|>\n {{- ',' if not loop.last -}}\n {%- endfor -%}\n ],\n {%- endif -%}\n {%- if params['type'] -%}\n type:<|\"|>{{- params['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n {%- if 'response' in tool_data['function'] -%}\n {%- set response_declaration = tool_data['function']['response'] -%}\n ,response:{\n {%- if response_declaration['description'] -%}\n description:<|\"|>{{- response_declaration['description'] -}}<|\"|>,\n {%- endif -%}\n {%- if response_declaration['type'] | upper == 'OBJECT' -%}\n type:<|\"|>{{- response_declaration['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n }\n{%- endmacro -%}\n{%- macro format_argument(argument, escape_keys=True) -%}\n {%- if argument is none -%}\n {{- 'null' -}}\n {%- elif argument is string -%}\n {{- '<|\"|>' + argument + '<|\"|>' -}}\n {%- elif argument is boolean -%}\n {{- 'true' if argument else 'false' -}}\n {%- elif argument is mapping -%}\n {{- '{' -}}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in argument | dictsort -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {%- if escape_keys -%}\n {{- '<|\"|>' + key + '<|\"|>' -}}\n {%- else -%}\n {{- key -}}\n {%- endif -%}\n :{{- format_argument(value, escape_keys=escape_keys) -}}\n {%- endfor -%}\n {{- '}' -}}\n {%- elif argument is sequence -%}\n {{- '[' -}}\n {%- for item in argument -%}\n {{- format_argument(item, escape_keys=escape_keys) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- ']' -}}\n {%- else -%}\n {{- argument -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro strip_thinking(text) -%}\n {%- set ns = namespace(result='') -%}\n {%- for part in text.split('<channel|>') -%}\n {%- if '<|channel>' in part -%}\n {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n {%- else -%}\n {%- set ns.result = ns.result + part -%}\n {%- endif -%}\n {%- endfor -%}\n {{- ns.result | trim -}}\n{%- endmacro -%}\n\n{%- macro format_tool_response_block(tool_name, response) -%}\n {{- '<|tool_response>' -}}\n {%- if response is mapping -%}\n {{- 'response:' + tool_name + '{' -}}\n {%- for key, value in response | dictsort -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- '}' -}}\n {%- else -%}\n {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}\n {%- endif -%}\n {{- '<tool_response|>' -}}\n{%- endmacro -%}\n\n{#- ===== SETUP ===== -#}\n{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}\n{%- set loop_messages = messages -%}\n{%- set enable_thinking = enable_thinking | default(false) -%}\n{%- set preserve_thinking = preserve_thinking | default(false) -%}\n{{- bos_token -}}\n{#- Handle System/Tool Definitions Block -#}\n{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}\n {{- '<|turn>system\\n' -}}\n {#- Inject Thinking token at the very top of the FIRST system turn -#}\n {%- if enable_thinking -%}\n {{- '<|think|>\\n' -}}\n {%- set ns.prev_message_type = 'think' -%}\n {%- endif -%}\n {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}\n {%- if messages[0]['content'] is string -%}\n {{- messages[0]['content'] | trim -}}\n {%- elif messages[0]['content'] is sequence -%}\n {%- for item in messages[0]['content'] -%}\n {{- item['text'] | trim + ' '-}}\n {%- endfor -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n {%- endif -%}\n {%- if tools -%}\n {%- for tool in tools %}\n {{- '<|tool>' -}}\n {{- format_function_declaration(tool) | trim -}}\n {{- '<tool|>' -}}\n {%- endfor %}\n {%- set ns.prev_message_type = 'tool' -%}\n {%- endif -%}\n {{- '<turn|>\\n' -}}\n{%- endif %}\n\n{#- Pre-scan: find last user message index for reasoning guard -#}\n{%- set ns_turn = namespace(last_user_idx=-1) -%}\n{%- for i in range(loop_messages | length) -%}\n {%- if loop_messages[i]['role'] == 'user' -%}\n {%- set ns_turn.last_user_idx = i -%}\n {%- endif -%}\n{%- endfor -%}\n\n{#- Loop through messages -#}\n{%- for message in loop_messages -%}\n {%- if message['role'] != 'tool' -%}\n {%- set ns.prev_message_type = None -%}\n {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}\n {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}\n {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}\n {%- if not continue_same_model_turn -%}\n {{- '<|turn>' + role + '\\n' }}\n {%- endif -%}\n\n {#- Render reasoning/reasoning_content as thinking channel -#}\n {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}\n {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}\n {%- if thinking_text and thinking_gate -%}\n {{- '<|channel>thought\\n' + thinking_text + '\\n<channel|>' -}}\n {%- endif -%}\n\n {%- if message.get('tool_calls') -%}\n {%- for tool_call in message.get('tool_calls') -%}\n {%- set function = tool_call['function'] -%}\n {{- '<|tool_call>call:' + function['name'] + '{' -}}\n {%- if function['arguments'] is mapping -%}\n {%- set ns_args = namespace(found_first=false) -%}\n {%- for key, value in function['arguments'] | dictsort -%}\n {%- if ns_args.found_first %},{% endif -%}\n {%- set ns_args.found_first = true -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- endfor -%}\n {%- elif function['arguments'] is none -%}\n {%- elif function['arguments'] is string -%}\n {#- Pre-serialized args (e.g. an OpenAI JSON string). We cannot JSON-parse\n portably in-template, so render non-fatally instead of erroring. Strip an\n outer {...} so it composes with the DSL braces rather than double-wrapping.\n Prefer passing arguments as a mapping for exact Gemma DSL. -#}\n {%- set argstr = function['arguments'] | trim -%}\n {%- if argstr[:1] == '{' and argstr[-1:] == '}' -%}\n {{- argstr[1:-1] -}}\n {%- else -%}\n {{- function['arguments'] -}}\n {%- endif -%}\n {%- endif -%}\n {{- '}<tool_call|>' -}}\n {%- endfor -%}\n {%- set ns.prev_message_type = 'tool_call' -%}\n {%- endif -%}\n\n {%- set ns_tr_out = namespace(flag=false) -%}\n {%- if message.get('tool_responses') -%}\n {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}\n {%- for tool_response in message.get('tool_responses') -%}\n {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endfor -%}\n {%- elif message.get('tool_calls') -%}\n {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}\n {%- set ns_tool_scan = namespace(stopped=false) -%}\n {%- for k in range(loop.index0 + 1, loop_messages | length) -%}\n {%- if ns_tool_scan.stopped -%}\n {%- elif loop_messages[k]['role'] != 'tool' -%}\n {%- set ns_tool_scan.stopped = true -%}\n {%- else -%}\n {%- set follow = loop_messages[k] -%}\n {#- Resolve tool_call_id to function name -#}\n {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}\n {%- for tc in message.get('tool_calls') -%}\n {%- if tc.get('id') == follow.get('tool_call_id') -%}\n {%- set ns_tname.name = tc['function']['name'] -%}\n {%- endif -%}\n {%- endfor -%}\n {#- Handle content as string or content-parts array -#}\n {%- set tool_body = follow.get('content') -%}\n {%- if tool_body is string -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- elif tool_body is sequence and tool_body is not string -%}\n {%- set ns_txt = namespace(s='') -%}\n {%- for part in tool_body -%}\n {%- if part.get('type') == 'text' -%}\n {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}\n {%- endif -%}\n {%- endfor -%}\n {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}\n {%- for part in tool_body -%}\n {%- if part.get('type') in ['image', 'image_url'] -%}\n {{- '<|image|>' -}}\n {%- elif part.get('type') in ['audio', 'input_audio'] -%}\n {{- '<|audio|>' -}}\n {%- elif part.get('type') == 'video' -%}\n {{- '<|video|>' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- endif -%}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n\n {%- set captured_content -%}\n {%- if message.get('content') is string -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(message['content']) -}}\n {%- else -%}\n {{- message['content'] | trim -}}\n {%- endif -%}\n {%- elif message.get('content') is sequence -%}\n {%- for item in message['content'] -%}\n {%- if item.get('type') == 'text' -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(item['text']) -}}\n {%- else -%}\n {{- item['text'] | trim -}}\n {%- endif -%}\n {%- elif item.get('type') in ['image', 'image_url'] -%}\n {{- '<|image|>' -}}\n {%- elif item.get('type') in ['audio', 'input_audio'] -%}\n {{- '<|audio|>' -}}\n {%- elif item.get('type') == 'video' -%}\n {{- '<|video|>' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endset -%}\n\n {{- captured_content -}}\n {%- set has_content = captured_content | trim | length > 0 -%}\n\n {#- Forward-scan: find next non-tool message role for continuation detection -#}\n {%- set next_nt = namespace(role=None, found=false) -%}\n {%- for j in range(loop.index0 + 1, loop_messages | length) -%}\n {%- if not next_nt.found -%}\n {%- if loop_messages[j]['role'] != 'tool' -%}\n {%- set next_nt.role = loop_messages[j]['role'] -%}\n {%- set next_nt.found = true -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n\n {%- set continues_into_next = (\n role == 'model'\n and next_nt.role == 'assistant'\n and (not message.get('tool_calls') or ns_tr_out.flag)\n ) -%}\n\n {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}\n {{- '<|tool_response>' -}}\n {%- elif continues_into_next -%}\n {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}\n {{- '<turn|>\\n' -}}\n {%- endif -%}\n\n {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}\n {%- set ns.prev_non_tool_role = message['role'] -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}\n {{- '<|turn>model\\n' -}}\n {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}\n {{- '<|channel>thought\\n' -}}\n {%- endif -%}\n{%- endif -%}\n"
297
+ }