Jepoxy commited on
Commit
4c332ad
·
verified ·
1 Parent(s): 27d7448

Upload folder using huggingface_hub

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}{%- set system_prompt = "" -%}{%- set ns = namespace(system_prompt="") -%}{%- if messages[0]["role"] == "system" -%} {%- set ns.system_prompt = messages[0]["content"] -%} {%- set messages = messages[1:] -%}{%- endif -%}{%- if tools -%} {%- set ns.system_prompt = ns.system_prompt + ("
2
+ " if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%} {%- for tool in tools -%} {%- if tool is not string -%} {%- set tool = tool | tojson -%} {%- endif -%} {%- set ns.system_prompt = ns.system_prompt + tool -%} {%- if not loop.last -%} {%- set ns.system_prompt = ns.system_prompt + ", " -%} {%- endif -%} {%- endfor -%} {%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%}{%- endif -%}{%- if ns.system_prompt -%} {{- "<|im_start|>system
3
+ " + ns.system_prompt + "<|im_end|>
4
+ " -}}{%- endif -%}{%- for message in messages -%} {{- "<|im_start|>" + message["role"] + "
5
+ " -}} {%- set content = message["content"] -%} {%- if content is not string -%} {%- set content = content | tojson -%} {%- endif -%} {%- if message["role"] == "tool" -%} {%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%} {%- endif -%} {{- content + "<|im_end|>
6
+ " -}}{%- endfor -%}{%- if add_generation_prompt -%} {{- "<|im_start|>assistant
7
+ " -}}{%- endif -%}
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForCausalLM"
4
+ ],
5
+ "block_auto_adjust_ff_dim": true,
6
+ "block_dim": 1024,
7
+ "block_ffn_dim_multiplier": 1.0,
8
+ "block_mlp_init_scale": 1.0,
9
+ "block_multiple_of": 256,
10
+ "block_norm_eps": 1e-05,
11
+ "block_out_init_scale": 1.0,
12
+ "block_use_swiglu": true,
13
+ "block_use_xavier_init": true,
14
+ "bos_token_id": 1,
15
+ "conv_L_cache": 3,
16
+ "conv_bias": false,
17
+ "conv_dim": 1024,
18
+ "conv_use_xavier_init": true,
19
+ "dtype": "bfloat16",
20
+ "eos_token_id": 7,
21
+ "full_attn_idxs": null,
22
+ "hidden_size": 1024,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 6656,
25
+ "layer_types": [
26
+ "conv",
27
+ "conv",
28
+ "full_attention",
29
+ "conv",
30
+ "conv",
31
+ "full_attention",
32
+ "conv",
33
+ "conv",
34
+ "full_attention",
35
+ "conv",
36
+ "full_attention",
37
+ "conv",
38
+ "full_attention",
39
+ "conv",
40
+ "full_attention",
41
+ "conv"
42
+ ],
43
+ "max_position_embeddings": 128000,
44
+ "model_type": "lfm2",
45
+ "norm_eps": 1e-05,
46
+ "num_attention_heads": 16,
47
+ "num_heads": 16,
48
+ "num_hidden_layers": 16,
49
+ "num_key_value_heads": 8,
50
+ "pad_token_id": 0,
51
+ "rope_parameters": {
52
+ "rope_theta": 1000000.0,
53
+ "rope_type": "default"
54
+ },
55
+ "tie_word_embeddings": true,
56
+ "transformers_version": "5.9.0",
57
+ "use_cache": false,
58
+ "use_pos_enc": true,
59
+ "vocab_size": 65536
60
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 7
7
+ ],
8
+ "pad_token_id": 0,
9
+ "transformers_version": "5.9.0"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764b76a7db3f39b73afe8663fb47df6f16265b3401d582fa8bb3982b73364346
3
+ size 708984464
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|im_end|>",
6
+ "extra_special_tokens": [],
7
+ "is_local": false,
8
+ "legacy": false,
9
+ "local_files_only": false,
10
+ "model_input_names": [
11
+ "input_ids",
12
+ "attention_mask"
13
+ ],
14
+ "model_max_length": 1000000000000000019884624838656,
15
+ "pad_token": "<|pad|>",
16
+ "sp_model_kwargs": {},
17
+ "spaces_between_special_tokens": false,
18
+ "tokenizer_class": "TokenizersBackend",
19
+ "use_default_system_prompt": false,
20
+ "use_fast": true
21
+ }