hf-transformers-bot commited on
Commit
477b070
·
verified ·
1 Parent(s): b33337c

Update tiny models for Olmo3ForSequenceClassification

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set has_system = messages|selectattr('role', 'equalto', 'system')|list|length > 0 -%}{%- if not has_system -%}{{- '<|im_start|>system
2
+ You are a helpful function-calling AI assistant. ' -}}{%- if tools is none -%}{{- 'You do not currently have access to any functions. <functions></functions><|im_end|>
3
+ ' -}}{%- else -%}{{- 'You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Do not make assumptions about what values to plug into functions.' -}}{{- '<functions>' -}}{{- tools | tojson -}}{{- '</functions><|im_end|>
4
+ ' -}}{%- endif -%}{%- endif -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{{- '<|im_start|>system
5
+ ' + message['content'] -}}{%- if tools is not none -%}{{- '<functions>' -}}{{- tools | tojson -}}{{- '</functions>' -}}{%- elif message.get('functions', none) is not none -%}{{- ' <functions>' + message['functions'] + '</functions>' -}}{%- endif -%}{{- '<|im_end|>
6
+ ' -}}{%- elif message['role'] == 'user' -%}{{- '<|im_start|>user
7
+ ' + message['content'] + '<|im_end|>
8
+ ' -}}{%- elif message['role'] == 'assistant' -%}{{- '<|im_start|>assistant
9
+ ' -}}{%- if message.get('content', none) is not none -%}{{- message['content'] -}}{%- endif -%}{%- if message.get('function_calls', none) is not none -%}{{- '<function_calls>' + message['function_calls'] + '</function_calls>' -}}{% elif message.get('tool_calls', none) is not none %}{{- '<function_calls>' -}}{%- for tool_call in message['tool_calls'] %}{%- if tool_call is mapping and tool_call.get('function', none) is not none %}{%- set args = tool_call['function']['arguments'] -%}{%- set ns = namespace(arguments_list=[]) -%}{%- for key, value in args.items() -%}{%- set ns.arguments_list = ns.arguments_list + [key ~ '=' ~ (value | tojson)] -%}{%- endfor -%}{%- set arguments = ns.arguments_list | join(', ') -%}{{- tool_call['function']['name'] + '(' + arguments + ')' -}}{%- if not loop.last -%}{{ '
10
+ ' }}{%- endif -%}{% else %}{{- tool_call -}}{%- endif %}{%- endfor %}{{- '</function_calls>' -}}{%- endif -%}{%- if not loop.last -%}{{- '<|im_end|>' + '
11
+ ' -}}{%- else -%}{{- eos_token -}}{%- endif -%}{%- elif message['role'] == 'environment' -%}{{- '<|im_start|>environment
12
+ ' + message['content'] + '<|im_end|>
13
+ ' -}}{%- elif message['role'] == 'tool' -%}{{- '<|im_start|>environment
14
+ ' + message['content'] + '<|im_end|>
15
+ ' -}}{%- endif -%}{%- if loop.last and add_generation_prompt -%}{{- '<|im_start|>assistant
16
+ ' -}}{%- endif -%}{%- endfor -%}
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Olmo3ForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 100257,
8
+ "dtype": "float32",
9
+ "eos_token_id": 100257,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 32,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 32,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "sliding_attention"
17
+ ],
18
+ "max_position_embeddings": 512,
19
+ "model_type": "olmo3",
20
+ "num_attention_heads": 2,
21
+ "num_hidden_layers": 2,
22
+ "num_key_value_heads": 2,
23
+ "pad_token_id": 100277,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_parameters": {
26
+ "full_attention": {
27
+ "rope_theta": 500000.0,
28
+ "rope_type": "default"
29
+ },
30
+ "sliding_attention": {
31
+ "rope_theta": 500000.0,
32
+ "rope_type": "default"
33
+ }
34
+ },
35
+ "sliding_window": 4096,
36
+ "tie_word_embeddings": false,
37
+ "transformers_version": "5.16.0.dev0",
38
+ "use_cache": true,
39
+ "vocab_size": 100278
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5c766bc26c298d989f53ededf04256ca54aa04f06b6031a6d1c25bc0b826004
3
+ size 12897000
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
+ "model_max_length": 512,
10
+ "pad_token": "<|pad|>",
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "unk_token": "<|endoftext|>"
13
+ }