Hugging Face's logo

RichardErkhov
/
THUDM_-_agentlm-13b-gguf

GGUF
Model card Files Community
RichardErkhov commited on
Commit
331ad1d
·
verified ·
1 Parent(s): 36f4ef3

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +87 -0
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ agentlm-13b - GGUF
11
+ - Model creator: https://huggingface.co/THUDM/
12
+ - Original model: https://huggingface.co/THUDM/agentlm-13b/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [agentlm-13b.Q2_K.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q2_K.gguf) | Q2_K | 4.52GB |
18
+ | [agentlm-13b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q3_K_S.gguf) | Q3_K_S | 1.64GB |
19
+ | [agentlm-13b.Q3_K.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q3_K.gguf) | Q3_K | 5.9GB |
20
+ | [agentlm-13b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q3_K_M.gguf) | Q3_K_M | 5.9GB |
21
+ | [agentlm-13b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q3_K_L.gguf) | Q3_K_L | 6.46GB |
22
+ | [agentlm-13b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.IQ4_XS.gguf) | IQ4_XS | 3.88GB |
23
+ | [agentlm-13b.Q4_0.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q4_0.gguf) | Q4_0 | 6.86GB |
24
+ | [agentlm-13b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.IQ4_NL.gguf) | IQ4_NL | 3.53GB |
25
+ | [agentlm-13b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q4_K_S.gguf) | Q4_K_S | 0.49GB |
26
+ | [agentlm-13b.Q4_K.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q4_K.gguf) | Q4_K | 5.26GB |
27
+ | [agentlm-13b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q4_K_M.gguf) | Q4_K_M | 5.18GB |
28
+ | [agentlm-13b.Q4_1.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q4_1.gguf) | Q4_1 | 7.61GB |
29
+ | [agentlm-13b.Q5_0.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q5_0.gguf) | Q5_0 | 8.36GB |
30
+ | [agentlm-13b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q5_K_S.gguf) | Q5_K_S | 8.36GB |
31
+ | [agentlm-13b.Q5_K.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q5_K.gguf) | Q5_K | 8.6GB |
32
+ | [agentlm-13b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q5_K_M.gguf) | Q5_K_M | 8.6GB |
33
+ | [agentlm-13b.Q5_1.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q5_1.gguf) | Q5_1 | 9.11GB |
34
+ | [agentlm-13b.Q6_K.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q6_K.gguf) | Q6_K | 9.95GB |
35
+ | [agentlm-13b.Q8_0.gguf](https://huggingface.co/RichardErkhov/THUDM_-_agentlm-13b-gguf/blob/main/agentlm-13b.Q8_0.gguf) | Q8_0 | 12.88GB |
36
+
37
+
38
+
39
+
40
+ Original model description:
41
+ ---
42
+ datasets:
43
+ - THUDM/AgentInstruct
44
+ ---
45
+
46
+ ## AgentLM-13B
47
+
48
+ <p align="center">
49
+ 🤗 <a href="https://huggingface.co/datasets/THUDM/AgentInstruct" target="_blank">[Dataset] </a> • 💻 <a href="https://github.com/THUDM/AgentTuning" target="_blank">[Github Repo]</a> • 📌 <a href="https://THUDM.github.io/AgentTuning/" target="_blank">[Project Page]</a> • 📃 <a href="https://arxiv.org/abs/2310.12823" target="_blank">[Paper]</a>
50
+ </p>
51
+
52
+ **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.
53
+
54
+ ## Models
55
+
56
+ **AgentLM** models are produced by mixed training on AgentInstruct dataset and ShareGPT dataset from Llama-2-chat models.
57
+
58
+ The models follow the conversation format of [Llama-2-chat](https://huggingface.co/blog/llama2#how-to-prompt-llama-2), with system prompt fixed as
59
+
60
+ ```
61
+ You are a helpful, respectful and honest assistant.
62
+ ```
63
+
64
+ 7B, 13B, and 70B models are available on Huggingface model hub.
65
+
66
+ |Model|Huggingface Repo|
67
+ |---|---|
68
+ |AgentLM-7B| [🤗Huggingface Repo](https://huggingface.co/THUDM/agentlm-7b) |
69
+ |AgentLM-13B| [🤗Huggingface Repo](https://huggingface.co/THUDM/agentlm-13b) |
70
+ |AgentLM-70B| [🤗Huggingface Repo](https://huggingface.co/THUDM/agentlm-70b) |
71
+
72
+ ## Citation
73
+
74
+ If you find our work useful, please consider citing AgentTuning:
75
+
76
+ ```
77
+ @misc{zeng2023agenttuning,
78
+ title={AgentTuning: Enabling Generalized Agent Abilities for LLMs},
79
+ author={Aohan Zeng and Mingdao Liu and Rui Lu and Bowen Wang and Xiao Liu and Yuxiao Dong and Jie Tang},
80
+ year={2023},
81
+ eprint={2310.12823},
82
+ archivePrefix={arXiv},
83
+ primaryClass={cs.CL}
84
+ }
85
+ ```
86
+
87
+