brikdavies commited on
Commit
70537bb
·
verified ·
1 Parent(s): 8ee0732

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -76,3 +76,4 @@ gdpo_lambda0.005_from_lambda0.03_ckpt150/checkpoint-400/tokenizer.json filter=lf
76
  gdpo_lambda0.005_from_lambda0.03_ckpt150/final_adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
  gdpo_lambda0.005_from_lambda0.01/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
78
  gdpo_lambda0.005_from_lambda0.01/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
76
  gdpo_lambda0.005_from_lambda0.03_ckpt150/final_adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
  gdpo_lambda0.005_from_lambda0.01/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
78
  gdpo_lambda0.005_from_lambda0.01/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
79
+ gdpo_lambda0.01_from_lambda0.03_ckpt150/merged_init/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gdpo_lambda0.01_from_lambda0.03_ckpt150/merged_init/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\n'}}{% endif %}
gdpo_lambda0.01_from_lambda0.03_ckpt150/merged_init/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 21,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 2,
49
+ "pad_token_id": null,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 10000,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": false,
57
+ "transformers_version": "5.1.0",
58
+ "use_cache": true,
59
+ "use_mrope": false,
60
+ "use_sliding_window": false,
61
+ "vocab_size": 151936
62
+ }
gdpo_lambda0.01_from_lambda0.03_ckpt150/merged_init/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151646,
4
+ "do_sample": true,
5
+ "eos_token_id": 151643,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "5.1.0"
9
+ }
gdpo_lambda0.01_from_lambda0.03_ckpt150/merged_init/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65de2bcf941ad5223ba50f8a378faae55be2dd0b6cd8f382debbf05e41fbd54
3
+ size 3554214752
gdpo_lambda0.01_from_lambda0.03_ckpt150/merged_init/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:322664cdc3082b6eba003af5228a77ca1d7936d402e584ecde8f15d3d98bdb72
3
+ size 11421911
gdpo_lambda0.01_from_lambda0.03_ckpt150/merged_init/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|begin▁of▁sentence|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|end▁of▁sentence|>",
6
+ "is_local": true,
7
+ "legacy": true,
8
+ "model_max_length": 16384,
9
+ "pad_token": "<|end▁of▁sentence|>",
10
+ "sp_model_kwargs": {},
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "unk_token": null
13
+ }