JonathanMiddleton commited on
Commit
ccd9a41
·
verified ·
1 Parent(s): 392e1d7

Add files using upload-large-folder tool

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {#- Daisy Chat Template v2 -#}
2
+ {#- Supports: ChatML format, tool calling, multipart content -#}
3
+
4
+ {#- Macro to render content (string or multipart) -#}
5
+ {%- macro render_content(content) -%}
6
+ {%- if content is string -%}
7
+ {{ content }}
8
+ {%- elif content is iterable -%}
9
+ {%- for part in content -%}
10
+ {%- if part.type == 'text' -%}
11
+ {{ part.text }}
12
+ {%- elif part.type == 'tool_call' -%}
13
+ <|tool_call|>{{ part.text }}<|/tool_call|>
14
+ {%- elif part.type == 'tool_result' -%}
15
+ <|tool_result|>{{ part.text }}<|/tool_result|>
16
+ {%- elif part.type == 'python' -%}
17
+ <|python|>{{ part.text }}<|/python|>
18
+ {%- elif part.type == 'output' -%}
19
+ <|output|>{{ part.text }}<|/output|>
20
+ {%- elif part.type == 'think' -%}
21
+ <|think|>{{ part.text }}<|/think|>
22
+ {%- endif -%}
23
+ {%- endfor -%}
24
+ {%- else -%}
25
+ {{ content }}
26
+ {%- endif -%}
27
+ {%- endmacro -%}
28
+
29
+ {#- Main message loop -#}
30
+ {%- for message in messages -%}
31
+ {%- if message.role == 'system' -%}
32
+ <|im_start|>system
33
+ {{ message.content }}<|im_end|>
34
+ {% elif message.role == 'user' -%}
35
+ <|im_start|>user
36
+ {{ message.content }}<|im_end|>
37
+ {% elif message.role == 'assistant' -%}
38
+ <|im_start|>assistant
39
+ {% generation %}{{ render_content(message.content) }}{% endgeneration %}<|im_end|>
40
+ {% elif message.role == 'tool' -%}
41
+ <|tool_result|>{{ message.content }}<|/tool_result|>
42
+ {%- endif -%}
43
+ {%- endfor -%}
44
+
45
+ {#- Generation prompt -#}
46
+ {%- if add_generation_prompt -%}
47
+ <|im_start|>assistant
48
+ {% generation %}{% endgeneration %}
49
+ {%- endif -%}
50
+
checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff3d6b2818545025044a1fdbf83d3463dceac353eae4b354c32ccc24269e896
3
+ size 12859945921
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DaisyForCausalLM"
4
+ ],
5
+ "attn_all_layers": true,
6
+ "attn_impl": "standard",
7
+ "bos_token_id": 49131,
8
+ "dtype": "float32",
9
+ "eos_token_id": 49131,
10
+ "head_dim": 128,
11
+ "max_position_embeddings": 131072,
12
+ "model_dim": 1792,
13
+ "model_type": "daisy",
14
+ "num_heads": 14,
15
+ "num_layers": 28,
16
+ "padded_embeddings": false,
17
+ "skip_mix_mode": "linear",
18
+ "tokenizer_name": "jonathanmiddleton/daisy",
19
+ "transformers_version": "5.0.0",
20
+ "use_tied_embeddings": false,
21
+ "use_value_embeddings": true,
22
+ "vocab_size": 49152,
23
+ "window_size": 2048
24
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 49131,
4
+ "eos_token_id": 49131,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.0.0"
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f0a16c330f43a7c134d7dfce5b84e0ead0143a59e76bf3d72f28ca730e9974d
3
+ size 3567272960
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "extra_special_tokens": [
8
+ "<|tool_call|>",
9
+ "<|/tool_call|>",
10
+ "<|tool_result|>",
11
+ "<|/tool_result|>",
12
+ "<|python|>",
13
+ "<|/python|>",
14
+ "<|output|>",
15
+ "<|/output|>",
16
+ "<|think|>",
17
+ "<|/think|>",
18
+ "<|system|>",
19
+ "<|user|>",
20
+ "<|assistant|>",
21
+ "<|reserved_0|>",
22
+ "<|reserved_1|>",
23
+ "<|reserved_2|>",
24
+ "<|reserved_3|>"
25
+ ],
26
+ "is_local": false,
27
+ "model_max_length": 131072,
28
+ "pad_token": "<|pad|>",
29
+ "tokenizer_class": "TokenizersBackend",
30
+ "unk_token": null
31
+ }