DrNicefellow commited on
Commit
7cfabb5
1 Parent(s): 92344a3

Upload 10 files

Browse files
README.md CHANGED
@@ -1,5 +1,75 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
3
  ---
4
 
5
- This is a 6.0bpw h6 quantized version of [xingyaoww/CodeActAgent-Mistral-7b-v0.1](https://huggingface.co/xingyaoww/CodeActAgent-Mistral-7b-v0.1). It is quantized with exllamav2.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ datasets:
4
+ - xingyaoww/code-act
5
+ language:
6
+ - en
7
+ pipeline_tag: text-generation
8
+ tags:
9
+ - llm-agent
10
  ---
11
 
12
+ <h1 align="center"> Executable Code Actions Elicit Better LLM Agents </h1>
13
+
14
+ <p align="center">
15
+ <a href="https://github.com/xingyaoww/code-act">💻 Code</a>
16
+
17
+ <a href="https://arxiv.org/abs/2402.01030">📃 Paper</a>
18
+
19
+ <a href="https://huggingface.co/datasets/xingyaoww/code-act" >🤗 Data (CodeActInstruct)</a>
20
+
21
+ <a href="https://huggingface.co/xingyaoww/CodeActAgent-Mistral-7b-v0.1" >🤗 Model (CodeActAgent-Mistral-7b-v0.1)</a>
22
+
23
+ <a href="https://chat.xwang.dev/">🤖 Chat with CodeActAgent!</a>
24
+ </p>
25
+
26
+ We propose to use executable Python **code** to consolidate LLM agents’ **act**ions into a unified action space (**CodeAct**).
27
+ Integrated with a Python interpreter, CodeAct can execute code actions and dynamically revise prior actions or emit new actions upon new observations (e.g., code execution results) through multi-turn interactions.
28
+
29
+ ![Overview](https://github.com/xingyaoww/code-act/blob/main/figures/overview.png?raw=true)
30
+
31
+ ## Why CodeAct?
32
+
33
+ Our extensive analysis of 17 LLMs on API-Bank and a newly curated benchmark [M<sup>3</sup>ToolEval](docs/EVALUATION.md) shows that CodeAct outperforms widely used alternatives like Text and JSON (up to 20% higher success rate). Please check our paper for more detailed analysis!
34
+
35
+ ![Comparison between CodeAct and Text/JSON](https://github.com/xingyaoww/code-act/blob/main/figures/codeact-comparison-table.png?raw=true)
36
+ *Comparison between CodeAct and Text / JSON as action.*
37
+
38
+ ![Comparison between CodeAct and Text/JSON](https://github.com/xingyaoww/code-act/blob/main/figures/codeact-comparison-perf.png?raw=true)
39
+ *Quantitative results comparing CodeAct and {Text, JSON} on M<sup>3</sup>ToolEval.*
40
+
41
+
42
+
43
+ ## 📁 CodeActInstruct
44
+
45
+ We collect an instruction-tuning dataset CodeActInstruct that consists of 7k multi-turn interactions using CodeAct. Dataset is release at [huggingface dataset 🤗](https://huggingface.co/datasets/xingyaoww/code-act). Please refer to the paper and [this section](#-data-generation-optional) for details of data collection.
46
+
47
+
48
+ ![Data Statistics](https://github.com/xingyaoww/code-act/blob/main/figures/data-stats.png?raw=true)
49
+ *Dataset Statistics. Token statistics are computed using Llama-2 tokenizer.*
50
+
51
+ ## 🪄 CodeActAgent
52
+
53
+ Trained on **CodeActInstruct** and general conversaions, **CodeActAgent** excels at out-of-domain agent tasks compared to open-source models of the same size, while not sacrificing generic performance (e.g., knowledge, dialog). We release two variants of CodeActAgent:
54
+ - **CodeActAgent-Mistral-7b-v0.1** (recommended, [model link](https://huggingface.co/xingyaoww/CodeActAgent-Mistral-7b-v0.1)): using Mistral-7b-v0.1 as the base model with 32k context window.
55
+ - **CodeActAgent-Llama-7b** ([model link](https://huggingface.co/xingyaoww/CodeActAgent-Llama-2-7b)): using Llama-2-7b as the base model with 4k context window.
56
+
57
+ ![Model Performance](https://github.com/xingyaoww/code-act/blob/main/figures/model-performance.png?raw=true)
58
+ *Evaluation results for CodeActAgent. ID and OD stand for in-domain and out-of-domain evaluation correspondingly. Overall averaged performance normalizes the MT-Bench score to be consistent with other tasks and excludes in-domain tasks for fair comparison.*
59
+
60
+
61
+ Please check out [our paper](TODO) and [code](https://github.com/xingyaoww/code-act) for more details about data collection, model training, and evaluation.
62
+
63
+
64
+ ## 📚 Citation
65
+
66
+ ```bibtex
67
+ @misc{wang2024executable,
68
+ title={Executable Code Actions Elicit Better LLM Agents},
69
+ author={Xingyao Wang and Yangyi Chen and Lifan Yuan and Yizhe Zhang and Yunzhu Li and Hao Peng and Heng Ji},
70
+ year={2024},
71
+ eprint={2402.01030},
72
+ archivePrefix={arXiv},
73
+ primaryClass={cs.CL}
74
+ }
75
+ ```
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32001,
3
+ "<|im_start|>": 32000
4
+ }
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 4096,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 14336,
11
+ "max_position_embeddings": 32768,
12
+ "model_type": "mistral",
13
+ "num_attention_heads": 32,
14
+ "num_hidden_layers": 32,
15
+ "num_key_value_heads": 8,
16
+ "rms_norm_eps": 1e-05,
17
+ "rope_theta": 10000.0,
18
+ "sliding_window": 4096,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "bfloat16",
21
+ "transformers_version": "4.35.0",
22
+ "use_cache": true,
23
+ "vocab_size": 32002
24
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.35.0"
6
+ }
output.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2859aad98475739dc2ce3b1fb32cba7977baeba41b1abf98eaebb6d9fd1ec7
3
+ size 5605280988
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_end|>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "unk_token": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ }
26
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<|im_start|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<|im_end|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [
45
+ "<|im_end|>"
46
+ ],
47
+ "bos_token": "<s>",
48
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
49
+ "clean_up_tokenization_spaces": false,
50
+ "eos_token": "</s>",
51
+ "legacy": true,
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": null,
54
+ "sp_model_kwargs": {},
55
+ "spaces_between_special_tokens": false,
56
+ "tokenizer_class": "LlamaTokenizer",
57
+ "unk_token": "<unk>",
58
+ "use_default_system_prompt": false
59
+ }