llm-reasoners
A library for advanced large language model reasoning
File Explorer
Download Latest Version (.zip)- figure2_reasoners_v5.png
- goal.png
- mcts_animation.gif
- Reasoners.pdf
- reasoners_icon.png
- cosmos.jsonl
- gsm8k.jsonl
- logical_deduction.jsonl
- multistep_arithmetic.jsonl
- strategyqa.jsonl
- word_sorting.jsonl
- autorace.py
- EXAMPLE_WRONG_CHAINS_AQUA.txt.txt
- prompt.json
- README.md
- misc.py
- parse.py
- prompts.py
- .gitignore
- gym_env.py
- inference_beam.py
- inference_dfs.py
- inference_mcts.py
- README.md
- search_config.py
- visualize.py
- COLD_attack_diagram.png
- harmful_behaviors.csv
- harmful_behaviors_custom.csv
- advbench.txt
- MaliciousInstruct.txt
- bleuloss.py
- inference.py
- opt_util.py
- README.md
- search_config.py
- task.py
- util.py
- CONTRIBUTING
- dev.json
- LICENSE
- README.md
- test.json
- train.json
- cot.json
- inference.py
- README.md
- utils.py
- step_10.json
- step_12.json
- step_14.json
- step_16.json
- step_2.json
- step_4.json
- step_6.json
- step_8.json
- split_v1_step_10_data.json
- split_v1_step_12_data.json
- split_v1_step_2_data.json
- split_v1_step_4_data.json
- split_v1_step_6_data.json
- split_v1_step_8_data.json
- split_v2_step_10_data.json
- split_v2_step_12_data.json
- split_v2_step_2_data.json
- split_v2_step_4_data.json
- split_v2_step_6_data.json
- split_v2_step_8_data.json
- bw_basic.json
- bw_basic_sup.json
- bw_config.yaml
- generated_domain.pddl
- pool_prompt.json
- pool_prompt_v0.json
- pool_prompt_v1.json
- pool_prompt_v2_step_10.json
- pool_prompt_v2_step_12.json
- pool_prompt_v2_step_2.json
- pool_prompt_v2_step_4.json
- pool_prompt_v2_step_6.json
- pool_prompt_v2_step_8.json
- prompt.json
- aggregate.py
- cot_inference.py
- README.md
- search_config.py
- test_cot_llama3.sh
- test_cot_mistral.sh
- world_model.py
- cot.json
- inference.py
- README.md
- utils.py
- 345hop_random_true.json
- create_example_pool.py
- create_next_step_example.py
- example_next_steps.json
- example_pool.json
- finish.py
- next_step.py
- next_step_shibo.py
- output.py
- transition.py
- valid_rap.py
- valid_tot.py
- cot_inference.py
- dataset.py
- README.md
- search_config.py
- world_model.py
- strategyqa_test-ori.json
- strategyqa_test.json
- strategyqa_train.json
- strategyqa_train_filtered.json
- strategyqa_train_paragraphs.json
- inference.py
- prompt.json
- README.md
- utils.py
- out_16_5.json
- alpaca_train.json
- icl_metrics_cache.json
- lima_subsample_train.json
- mal_train.txt
- metrics_cache.json
- queries_resp_train.json
- visualization.png
- __init__.py
- openai_model.py
- vllm_model.py
- __init__.py
- beam_search.py
- config.py
- icl_opti_prompts.py
- log_format.py
- offline_icl_opti.py
- prompt.py
- README.md
- search_config.py
- train.py
- utils.py
- visualize_log.py
- world_model.py
- inference.py
- README.md
- __init__.py
- datasets.py
- discriminator_dataset.py
- utils.py
- verifier_dataset.py
- __init__.py
- alignment_utils.py
- args.py
- discriminator_trainer.py
- electra_discriminator.py
- reason.py
- sampling_utils.py
- t5_discriminator.py
- demos.jsonl.sampling
- train.jsonl.sample
- __init__.py
- constants.py
- flan_t5.py
- inference.py
- README.md
- search_config.py
- test.py
- utils.py
- world_model.py
- prompts.json
- qwen_math_parser.py
- README.md
- run_math500_task.py
- search_config.py
- world_model.py
- AQuA_example_pool.json
- interactive_examples.json
- useful_examples.json
- __init__.py
- aggregate.py
- data.py
- inference.py
- README.md
- search_config.py
- utils.py
- world_model.py
- l2m.json
- l2m_standard.json
- __init__.py
- aggregate.py
- inference.py
- README.md
- search_config.py
- utils.py
- world_model.py
- __init__.py
- inference.py
- prompt.py
- README.md
- search_config.py
- utils.py
- world_model.py
- prosqa_test.json
- README.md
- run.py
- utils.py
- config.py
- inference.py
- README.md
- task.py
- interactive_examples.json
- prompt_pool.json
- score_examples.json
- useful_examples.json
- __init__.py
- aggregate.py
- inference.py
- inference_eval.py
- inference_rap_sc.py
- README.md
- search_config.py
- utils.py
- visualize.py
- world_model.py
- bw_config.yaml
- generated_domain.pddl
- aggregate.py
- rap_inference.py
- README.md
- search_config.py
- test_rap_llama2.sh
- test_rap_llama3.sh
- test_rap_v1_chain.sh
- world_model.py
- interactive_examples.json
- prompt_pool.json
- useful_examples.json
- __init__.py
- aggregate.py
- inference.py
- README.md
- search_config.py
- utils.py
- visualize.py
- world_model.py
- create_example_pool.py
- create_next_step_example.py
- finish.py
- next_step.py
- next_step_shibo.py
- output.py
- transition.py
- valid_rap.py
- valid_tot.py
- dataset.py
- rap_inference.py
- README.md
- search_config.py
- world_model.py
- followup_question_examples-1.json
- interactive_examples-1.json
- problem_decompose_examples-1.0.1.txt
- useful_examples-1.json
- __init__.py
- aggregate.py
- dataset.py
- inference.py
- README.md
- search_config.py
- utils.py
- world_model.py
- hotpot_dev_v1_simplified.json
- direct.json
- react.json
- direct_inference.py
- inference.py
- README.md
- utils.py
- wikienv.py
- wrappers.py
- __init__.py
- openhands_browsing_agent.py
- openhands_response_parser.py
- model_o1_config.json
- model_o3-mini_config.json
- model_r1_config.json
- fanout-final-dev.json
- flightqa_counterfactual.csv
- helpers.py
- models.py
- norm.py
- evaluator.py
- run.py
- evaluator.py
- generate_data.py
- run.py
- get_success_rate.py
- get_ttest.py
- run_inference.sh
- log_visualizer-example.png
- logo.png
- controller.py
- main.py
- session.py
- browser.py
- config.py
- datasets.py
- llm.py
- logger.py
- metrics.py
- singleton.py
- .gitignore
- main.py
- README.md
- requirements.txt
- __init__.py
- inference.py
- prompt.py
- README.md
- search_config.py
- utils.py
- world_model.py
- README.md
- blocksworld.py
- README.md
- method.png
- __init__.py
- inference.py
- prompt.py
- README.md
- search_config.py
- utils.py
- world_model.py
- bw_config.yaml
- generated_domain.pddl
- aggregate.py
- README.md
- search_config.py
- test_tot_v1_bfs.sh
- test_tot_v1_dfs.sh
- tot_inference.py
- world_model.py
- mini0505.json
- mini0505_0_100_5.json
- crosswords.py
- __init__.py
- inference.py
- README.md
- search_config.py
- utils.py
- world_model.py
- 24.csv
- game24.json
- game24.py
- __init__.py
- cot.py
- game24_data.py
- inference.py
- README.md
- search_config.py
- utils.py
- world_model.py
- create_example_pool.py
- create_next_step_example.py
- finish.py
- next_step.py
- next_step_shibo.py
- output.py
- transition.py
- valid_rap.py
- valid_tot.py
- dataset.py
- README.md
- tot_inference.py
- world_model.py
- __init__.py
- README.md
- __init__.py
- actor.py
- critic.py
- encoder.py
- planner.py
- planner_utils.py
- policy.py
- world_model.py
- __init__.py
- action_space.py
- identity.py
- memory.py
- observation_space.py
- __init__.py
- agent.py
- base.py
- configs.py
- llm.py
- prompts.py
- README.md
- utils.py
- __init__.py
- beam_search.py
- dfs.py
- greedy.py
- mcts.py
- random.py
- __init__.py
- aqua.py
- blocksworld.py
- bw_utils.py
- gsm8k.py
- hotpotqa.py
- prontoqa.py
- prosqa.py
- README.md
- __init__.py
- anthropic_model.py
- deepseek_model.py
- exllama_model.py
- gemini_model.py
- hf_model.py
- llama_2_model.py
- llama_3_model.py
- llama_cpp_model.py
- llama_model.py
- openai_model.py
- README.md
- sglang_model.py
- __init__.py
- tools.py
- wikiutils.py
- __init__.py
- __main__.py
- tree_log.py
- tree_snapshot.py
- visualizer_client.py
- __init__.py
- base.py
- utils.py
- .gitignore
- .gitmodules
- demo.ipynb
- exllama
- LICENSE
- LLMs-Planning
- MANIFEST.in
- pyproject.toml
- README.md
- setup.py
# Installation Guide
1. Get the code
git clone https://github.com/maitrix-org/llm-reasoners
Downloads the entire project code from GitHub to your computer.
cd llm-reasoners
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
- Python 3 Python is required to use pip.
pip install llm-reasoners
Installs the package published on PyPI directly β no need to clone the source.
After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.
Pulled directly from this repo's README.
3. Python
EasyPrerequisites
pip install llm-reasoners
Installs the package published on PyPI directly β no need to clone the source.
pip install -e .
Installs the Python libraries listed in requirements.txt (or similar).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)
