RichardErkhov/THUDM_-_agentlm-7b-gguf

Quantization made by Richard Erkhov.

agentlm-7b - GGUF

Model creator: https://huggingface.co/THUDM/
Original model: https://huggingface.co/THUDM/agentlm-7b/

Name	Quant method	Size
agentlm-7b.Q2_K.gguf	Q2_K	2.36GB
agentlm-7b.IQ3_XS.gguf	IQ3_XS	2.61GB
agentlm-7b.IQ3_S.gguf	IQ3_S	2.75GB
agentlm-7b.Q3_K_S.gguf	Q3_K_S	2.75GB
agentlm-7b.IQ3_M.gguf	IQ3_M	2.9GB
agentlm-7b.Q3_K.gguf	Q3_K	3.07GB
agentlm-7b.Q3_K_M.gguf	Q3_K_M	3.07GB
agentlm-7b.Q3_K_L.gguf	Q3_K_L	3.35GB
agentlm-7b.IQ4_XS.gguf	IQ4_XS	3.4GB
agentlm-7b.Q4_0.gguf	Q4_0	3.56GB
agentlm-7b.IQ4_NL.gguf	IQ4_NL	3.59GB
agentlm-7b.Q4_K_S.gguf	Q4_K_S	3.59GB
agentlm-7b.Q4_K.gguf	Q4_K	3.8GB
agentlm-7b.Q4_K_M.gguf	Q4_K_M	3.8GB
agentlm-7b.Q4_1.gguf	Q4_1	3.95GB
agentlm-7b.Q5_0.gguf	Q5_0	4.33GB
agentlm-7b.Q5_K_S.gguf	Q5_K_S	4.33GB
agentlm-7b.Q5_K.gguf	Q5_K	4.46GB
agentlm-7b.Q5_K_M.gguf	Q5_K_M	4.46GB
agentlm-7b.Q5_1.gguf	Q5_1	4.72GB
agentlm-7b.Q6_K.gguf	Q6_K	5.15GB
agentlm-7b.Q8_0.gguf	Q8_0	6.67GB

Original model description:

datasets: - THUDM/AgentInstruct

AgentLM-7B

🤗 [Dataset] • 💻 [Github Repo] • 📌 [Project Page] • 📃 [Paper]

AgentTuning represents the very first attempt to instruction-tune LLMs using interaction trajectories across multiple agent tasks. Evaluation results indicate that AgentTuning enables the agent capabilities of LLMs with robust generalization on unseen agent tasks while remaining good on general language abilities. We have open-sourced the AgentInstruct dataset and AgentLM.

Models

AgentLM models are produced by mixed training on AgentInstruct dataset and ShareGPT dataset from Llama-2-chat models.

The models follow the conversation format of Llama-2-chat, with system prompt fixed as

You are a helpful, respectful and honest assistant.

7B, 13B, and 70B models are available on Huggingface model hub.

Model	Huggingface Repo
AgentLM-7B	🤗Huggingface Repo
AgentLM-13B	🤗Huggingface Repo
AgentLM-70B	🤗Huggingface Repo

Citation

If you find our work useful, please consider citing AgentTuning:

@misc{zeng2023agenttuning,
      title={AgentTuning: Enabling Generalized Agent Abilities for LLMs}, 
      author={Aohan Zeng and Mingdao Liu and Rui Lu and Bowen Wang and Xiao Liu and Yuxiao Dong and Jie Tang},
      year={2023},
      eprint={2310.12823},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}