ryota39 commited on
Commit
a6f6589
·
verified ·
1 Parent(s): 1a5ebed

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +1,145 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - ja
5
+ base_model:
6
+ - sbintuitions/sarashina2.2-3b-instruct-v0.1
7
+ pipeline_tag: text-classification
8
+ ---
9
+ # cyberagent/ca-reward-3b-ja
10
+
11
+ - 軽量な日本語報酬モデルの開発を目的として実装したモデルを公開する。
12
+ - 既存の指示文と新たに合成した指示文に対して、応答文を複数生成し、llm-as-a-judgeで疑似選好ラベルを付与することで疑似選好データセットを作成した。
13
+ - 上記の疑似選好データセットを分類するモデルを学習することで、指示文に対する応答文の好ましさを定量化する報酬モデルを作成した。
14
+
15
+ ## 評価
16
+
17
+ - 人手で選好ラベル(好ましい応答文か、好ましくない応答文)が付与された既存のデータセットを収集し、選好ラベルの分類精度(Accuracy)を評価した。
18
+ - 既存の報酬モデルによる分類精度と、`gpt-4o-2024-08-06`を用いたllm-as-a-judgeによる分類精度を記載した。
19
+
20
+ | | [HelpSteer3](https://huggingface.co/datasets/nvidia/HelpSteer3) | [llm-jp-chatbot-arena](https://huggingface.co/datasets/llm-jp/llm-jp-chatbot-arena-conversations) |
21
+ | --- | --- | --- |
22
+ | OpenAssistant/reward-model-deberta-v3-large-v2 | 0.5124 | 0.5610 |
23
+ | Skywork/Skywork-Reward-Gemma-2-27B-v0.2 | 0.6854 | 0.5166 |
24
+ | catlm-sarashina2.2-3b-reward-v0.1 | 0.7032 | 0.5366 |
25
+ | cyberagent/calm3-22b-chat-selfimprove-experimental | 0.7216 | 0.6075 |
26
+ | gpt-4o-2024-08-06 | 0.7845 | 0.6842 |
27
+
28
+
29
+ <details>
30
+ <summary>環境構築</summary>
31
+
32
+ - 開発環境: Ubuntu 24.04.2 LTS
33
+ - ライブラリのインストール
34
+
35
+ ```jsx
36
+ pip install -U -q pip
37
+ pip install -q torch==2.8.0
38
+ pip install -q transformers==4.51.3
39
+ pip install -q accelerate==0.29.3
40
+ pip install -q sentencepiece==0.2.0
41
+ ```
42
+
43
+ - バージョンの確認
44
+
45
+ ```jsx
46
+ import torch, transformers, accelerate, tokenizers, sentencepiece
47
+ print(torch.__version__)
48
+ print(transformers.__version__)
49
+ print(accelerate.__version__)
50
+ print(tokenizers.__version__)
51
+ print(sentencepiece.__version__)
52
+
53
+ # 2.8.0+cu128
54
+ # 4.51.3
55
+ # 0.29.3
56
+ # 0.21.4
57
+ # 0.2.0
58
+ ```
59
+
60
+ </details>
61
+
62
+ ## コードサンプル
63
+
64
+ ```python
65
+ import torch
66
+ from transformers import AutoModelForSequenceClassification, AutoTokenizer
67
+
68
+ model = AutoModelForSequenceClassification.from_pretrained(
69
+ "cyberagent/ca-reward-3b-ja",
70
+ device_map="auto",
71
+ num_labels=1,
72
+ )
73
+ tokenizer = AutoTokenizer.from_pretrained("cyberagent/ca-reward-3b-ja")
74
+
75
+ prompt = """手軽に栄養を補給できる食事を教えてください。"""
76
+ response1 = """栄養補給が手軽にできるものとしては、野菜たっぷりのスムージー、ゆで卵とサラダ、納豆ご飯などがおすすめです。特に納豆は手間なく良質なタンパク質が摂れますよ。お身体を大切にしてくださいね。"""
77
+ response2 = """手軽な栄養補給なら冷凍食品でいいと思います。レンジで温めるだけだし、時間がない時はコンビニ弁当でも悪くないですよ。"""
78
+
79
+ chat1 = [{"role": "user", "content": prompt}, {"role": "assistant", "content": response1}]
80
+ chat2 = [{"role": "user", "content": prompt}, {"role": "assistant", "content": response2}]
81
+
82
+ chat1_formatted = tokenizer.apply_chat_template(chat1, tokenize=False)
83
+ chat2_formatted = tokenizer.apply_chat_template(chat2, tokenize=False)
84
+ chat1_tokenized = tokenizer(chat1_formatted, return_tensors="pt", max_length=4096, truncation=True, padding="max_length",).to(model.device)
85
+ chat2_tokenized = tokenizer(chat2_formatted, return_tensors="pt", max_length=4096, truncation=True, padding="max_length",).to(model.device)
86
+
87
+ with torch.no_grad():
88
+ chat1_score = model(**chat1_tokenized).logits.item()
89
+ chat2_score = model(**chat2_tokenized).logits.item()
90
+
91
+ print(f"Score for response 1: {chat1_score}")
92
+ print(f"Score for response 2: {chat2_score}")
93
+
94
+ # Score for response 1: 1.2595189809799194
95
+ # Score for response 2: -2.917454242706299
96
+
97
+ ```
98
+
99
+ ## 学習モデル
100
+
101
+ - [sbintuitions/sarashina2.2-3b-instruct-v0.1](https://huggingface.co/sbintuitions/sarashina2.2-3b-instruct-v0.1)をベースモデルに用いた。
102
+
103
+ ## 学習データセット
104
+
105
+ - [ChatBotArena](https://huggingface.co/datasets/lmsys/chatbot_arena_conversations)のinstruction文と、社内で作成したデータセットを用いた。
106
+ - [cyberagent/calm3-22b-chat-selfimprove-experimental](https://huggingface.co/cyberagent/calm3-22b-chat-selfimprove-experimental)によるLLM-as-a-judgeを用いて、作成したデータセットに対して疑似選好ラベルを付与して、疑似選好データセットを作成した。
107
+
108
+ ## 報酬モデル単体の分類性能の評価に使用したデータセット
109
+
110
+ | 評価データセット名 | サンプル数 | 備考 |
111
+ | --- | --- | --- |
112
+ | [llm-jp/llm-jp-chatbot-arena-conversations](https://huggingface.co/datasets/llm-jp/llm-jp-chatbot-arena-conversations) | 448 | アノテーション結果がどちらも悪い、どち���も良い、同程度(winnerカラムがtie, tie(both good), tie(both bad))のサンプルは評価から除いた。シングルターンのみの学習データで訓練したため、評価にはシングルターンのサンプルのみ使用した。 |
113
+ | [nvidia/HelpSteer3](https://huggingface.co/datasets/nvidia/HelpSteer3) | 283 | 日本語性能を測るため、日本語サンプル(languageカラム=japanese)のみ評価に使用した。学習データセットにgemmaによって生成された応答文が含まれると記載されていたため、学習には用いず、train/validation split両方の分類性能の平均値を評価に使用した。シングルターンのみの学習データで訓練したため、評価にはシングルターンのサンプルのみ使用した。 |
114
+
115
+ ## 学習時のハイパーパラメータ
116
+
117
+ - learning_rateは[8e-07, 1e-06, 2.5e-06, 5e-06]で学習し、learning_rate=5e-06のモデルを採用した。
118
+
119
+ | | training type | batchsize | learning_rate | lr_scheduler | num_epoch | max_length | num_of_training_sample | num_of_validation_sample | hardware |
120
+ | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
121
+ | ca-reward-3b-ja | full parameter tuning | 32 | 5e-06 | linear | 1 | 4096 | 601,348 | 8,000 | NVIDIA_A100_80GB |
122
+
123
+ ## リリース
124
+
125
+ v0.1, 2025/08/12
126
+
127
+ ## Authors
128
+
129
+ - 三橋亮太(corresponding author)
130
+ - 開発中にフィードバックをいただいた皆様:陣内佑、坂本充生、森村哲郎、阿部拳之、蟻生開人、藤本悠雅、暮石航大
131
+
132
+ ## 引用
133
+
134
+ ```tex
135
+ @misc{cyberagent-ca-reward-3b-ja,
136
+ title={cyberagent/ca-reward-3b-ja},
137
+ url={https://huggingface.co/cyberagent/ca-reward-3b-ja},
138
+ author={Ryota Mitsuhashi},
139
+ year={2025},
140
+ }
141
+ ```
142
+
143
+ ## ライセンス
144
+
145
+ Apache-2.0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 160,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 8960,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "max_position_embeddings": 8192,
21
+ "mlp_bias": false,
22
+ "model_type": "llama",
23
+ "num_attention_heads": 16,
24
+ "num_hidden_layers": 32,
25
+ "num_key_value_heads": 8,
26
+ "pad_token_id": 3,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_scaling": null,
30
+ "rope_theta": 500000,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.51.3",
34
+ "use_cache": false,
35
+ "vocab_size": 102400
36
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6011a7c7fb45bbe7bdbc2e878fe70304f08c569c3d11766aa05f8d6969230caf
3
+ size 4987572280
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7046dec81706c1921359d8ad40c01a8f0afe8c0da64201fb010654ffba71edad
3
+ size 1199397688
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6186936320
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.norm.weight": "model-00002-of-00002.safetensors",
296
+ "score.weight": "model-00002-of-00002.safetensors"
297
+ }
298
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4aa5f142e26419c0313b75006c5ad7308aabd3eb589818b54e875dbea3034b
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da93414da416ac7fead07f53085cd83aabe22df42b5d7262b94ef35d508ed2e3
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<cls>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "<sep>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
3
+ size 1831879
tokenizer_config.json ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_dummy_prefix_space": false,
4
+ "add_eos_token": false,
5
+ "add_prefix_space": false,
6
+ "added_tokens_decoder": {
7
+ "0": {
8
+ "content": "<unk>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false,
13
+ "special": true
14
+ },
15
+ "1": {
16
+ "content": "<s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false,
21
+ "special": true
22
+ },
23
+ "2": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false,
29
+ "special": true
30
+ },
31
+ "3": {
32
+ "content": "<pad>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false,
37
+ "special": true
38
+ },
39
+ "4": {
40
+ "content": "<sep>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false,
45
+ "special": true
46
+ },
47
+ "5": {
48
+ "content": "<mask>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false,
53
+ "special": true
54
+ },
55
+ "6": {
56
+ "content": "<cls>",
57
+ "lstrip": false,
58
+ "normalized": false,
59
+ "rstrip": false,
60
+ "single_word": false,
61
+ "special": true
62
+ },
63
+ "7": {
64
+ "content": "<|system|>",
65
+ "lstrip": false,
66
+ "normalized": false,
67
+ "rstrip": false,
68
+ "single_word": false,
69
+ "special": false
70
+ },
71
+ "8": {
72
+ "content": "<|assistant|>",
73
+ "lstrip": false,
74
+ "normalized": false,
75
+ "rstrip": false,
76
+ "single_word": false,
77
+ "special": false
78
+ },
79
+ "9": {
80
+ "content": "<|user|>",
81
+ "lstrip": false,
82
+ "normalized": false,
83
+ "rstrip": false,
84
+ "single_word": false,
85
+ "special": false
86
+ },
87
+ "10": {
88
+ "content": "<|available_tools|>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false,
93
+ "special": false
94
+ },
95
+ "11": {
96
+ "content": "<|tool_calls|>",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": false,
100
+ "single_word": false,
101
+ "special": false
102
+ },
103
+ "12": {
104
+ "content": "<|tool_results|>",
105
+ "lstrip": false,
106
+ "normalized": false,
107
+ "rstrip": false,
108
+ "single_word": false,
109
+ "special": false
110
+ },
111
+ "13": {
112
+ "content": "<|code|>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false,
117
+ "special": false
118
+ },
119
+ "14": {
120
+ "content": "<|file|>",
121
+ "lstrip": false,
122
+ "normalized": false,
123
+ "rstrip": false,
124
+ "single_word": false,
125
+ "special": false
126
+ },
127
+ "102397": {
128
+ "content": "<|prefix|>",
129
+ "lstrip": false,
130
+ "normalized": false,
131
+ "rstrip": false,
132
+ "single_word": false,
133
+ "special": false
134
+ },
135
+ "102398": {
136
+ "content": "<|suffix|>",
137
+ "lstrip": false,
138
+ "normalized": false,
139
+ "rstrip": false,
140
+ "single_word": false,
141
+ "special": false
142
+ },
143
+ "102399": {
144
+ "content": "<|middle|>",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false,
149
+ "special": false
150
+ }
151
+ },
152
+ "bos_token": "<s>",
153
+ "chat_template": "\n{%- set user_messages = messages | selectattr('role', 'equalto', 'user') | list %}\n{%- macro output_available_tools(tools, message) %}\n{%- if tools and (message == user_messages[-1]) %}\n {{- '<|available_tools|>[' }}\n {%- for tool in tools %}\n {%- set tool = tool.function %}\n {{- \"{\" }}\n {%- for key, val in tool.items() if key != \"return\" %}\n {%- if val is string %}\n {{- \"'\" + key + \"': '\" + val + \"'\" }}\n {%- else %}\n {{- \"'\" + key + \"': \" + val|string }}\n {%- endif %}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- else %}\n {{- \"]\" }}\n {%- endif %}\n {%- endfor %}\n {{- eos_token -}}\n{%- endif %}\n{%- endmacro %}\n\n{%- macro output_tool_results(tool_results) %}\n{{- '<|tool_results|>[' }}\n{%- for tool_result in tool_results %}\n {{- \"{'content': \" + tool_result.content|string + \", 'call_id': '\" + tool_result.call_id + \"'}\" }}\n{%- endfor %}\n{{- ']' }}\n{{- eos_token -}}\n{%- endmacro %}\n\n{%- macro output_tool_calls(tool_calls) %}\n{{- '<|tool_calls|>[' }}\n{%- for tool_call in tool_calls %}\n {{- \"{'id': '\" + tool_call.id + \"', 'name': '\" + tool_call.name + \"', 'arguments': \" + tool_call.arguments|string + '}' }}\n{%- endfor %}\n{{- ']' }}\n{%- endmacro %}\n\n{%- for message in messages %}\n {%- if message['role'] == 'user' %}\n {%- if tools is defined %}\n {{- output_available_tools(tools, message) }}\n {%- endif %}\n {{- '<|user|>' + message['content'] + eos_token -}}\n {%- elif message['role'] == 'system' %}\n {{- '<|system|>' + message['content'] + eos_token -}}\n {%- elif message['role'] == 'assistant' %}\n {% set assistant_content = \"\" %}\n {%- if message.content is defined %}\n {% set assistant_content = message.content %}\n {%- endif %}\n {%- if message.tool_calls is defined and message.tool_calls -%}\n {{- '<|assistant|>' + assistant_content + output_tool_calls(message['tool_calls']) + eos_token -}}\n {%- else %}\n {{- '<|assistant|>' + assistant_content + eos_token }}\n {%- endif %}\n {%- elif message['role'] == 'tool_results' %}\n {{- output_tool_results(message.tool_results) }}\n {%- endif %}\n{%- if loop.last and add_generation_prompt -%}\n {{- '<|assistant|>' -}}\n{%- endif -%}\n{%- endfor %}\n",
154
+ "clean_up_tokenization_spaces": false,
155
+ "cls_token": "<cls>",
156
+ "do_lower_case": false,
157
+ "eos_token": "</s>",
158
+ "extra_ids": 0,
159
+ "extra_special_tokens": {},
160
+ "keep_accents": true,
161
+ "legacy": false,
162
+ "mask_token": "<mask>",
163
+ "model_max_length": 1000000000000000019884624838656,
164
+ "pad_token": "<pad>",
165
+ "padding_side": "right",
166
+ "sep_token": "<sep>",
167
+ "sp_model_kwargs": {},
168
+ "spaces_between_special_tokens": false,
169
+ "tokenizer_class": "LlamaTokenizer",
170
+ "unk_token": "<unk>",
171
+ "use_default_system_prompt": false
172
+ }