Hugging Face's logo

RichardErkhov
/
USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf

GGUF
conversational
Model card Files Community
RichardErkhov commited on
Commit
4770e28
·
verified ·
1 Parent(s): 636f1b0

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +102 -0
README.md ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ Llama3-KALE-LM-Chem-1.5-8B - GGUF
11
+ - Model creator: https://huggingface.co/USTC-KnowledgeComputingLab/
12
+ - Original model: https://huggingface.co/USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q2_K.gguf) | Q2_K | 2.96GB |
18
+ | [Llama3-KALE-LM-Chem-1.5-8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
19
+ | [Llama3-KALE-LM-Chem-1.5-8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.IQ3_S.gguf) | IQ3_S | 3.43GB |
20
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
21
+ | [Llama3-KALE-LM-Chem-1.5-8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.IQ3_M.gguf) | IQ3_M | 3.52GB |
22
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q3_K.gguf) | Q3_K | 3.74GB |
23
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
24
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
25
+ | [Llama3-KALE-LM-Chem-1.5-8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
26
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q4_0.gguf) | Q4_0 | 4.34GB |
27
+ | [Llama3-KALE-LM-Chem-1.5-8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.IQ4_NL.gguf) | IQ4_NL | 1.49GB |
28
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
29
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q4_K.gguf) | Q4_K | 4.58GB |
30
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
31
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q4_1.gguf) | Q4_1 | 4.78GB |
32
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q5_0.gguf) | Q5_0 | 5.21GB |
33
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
34
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q5_K.gguf) | Q5_K | 5.34GB |
35
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
36
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q5_1.gguf) | Q5_1 | 5.65GB |
37
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q6_K.gguf) | Q6_K | 6.14GB |
38
+ | [Llama3-KALE-LM-Chem-1.5-8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/USTC-KnowledgeComputingLab_-_Llama3-KALE-LM-Chem-1.5-8B-gguf/blob/main/Llama3-KALE-LM-Chem-1.5-8B.Q8_0.gguf) | Q8_0 | 7.95GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ license: llama3
46
+ language:
47
+ - en
48
+ base_model:
49
+ - meta-llama/Meta-Llama-3-8B-Instruct
50
+ tags:
51
+ - KALE-LM
52
+ - science
53
+ - chemistry
54
+ pipeline_tag: text-generation
55
+ ---
56
+
57
+ # Llama3-KALE-LM-Chem-1.5-8B
58
+
59
+ ## Introduction
60
+
61
+ We are thrilled to present Llama3-KALE-LM-Chem-1.5-8B, a new version of our open-source KALE-LM for science, which specializes in chemistry.
62
+
63
+ We have trained our model with a larger amount of data.
64
+
65
+ ## Benchmarks
66
+
67
+ ### Open Benchmarks
68
+ | Models | ChemBench | MMLU | MMLU-Chem | SciQ | IE(Acc) | IE(LS) |
69
+ | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
70
+ | GPT-3.5 | 47.15 | 69.75 | 53.32 | 89.6 | 52.98 | 68.28 |
71
+ | GPT-4 | 53.72 | 78.67 | 63.70 | 94.10 | 54.20 | 69.74 |
72
+ | Llama3-8B-Instruct | 46.02 | 68.3 | 51.10 | 93.30 | 45.83 | 61.22 |
73
+ | LlaSMol | 28.47 | 54.47 | 33.24 | 72.30 | 2.16 | 3.23 |
74
+ | ChemDFM | 44.44 | 58.11 | 45.60 | 86.70 | 7.61 | 11.49 |
75
+ | ChemLLM-7B-Chat | 34.16 | 61.79 | 48.39 | 94.00 | 29.66 | 39.17 |
76
+ | ChemLLM-7B-Chat-1.5-SFT | 42.75 | 63.56 | 49.63 | **95.10** | 14.96 | 19.61 |
77
+ | **Llama3-KALE-LM-Chem-1.5-8B** | **57.01** | 68.06 | **54.83** | 91.60 | **57.53** | **64.16** |
78
+
79
+ #### ChemBench Details (Evaluated By OpenCompass)
80
+
81
+ | Models | NC | PP | M2C | C2M | PP | RS | YP | TP | SP | Average |
82
+ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ |
83
+ | GPT-3.5 | 46.93 | 56.98 | 85.28 | 38.25 | 43.67 | 42.33 | 30.33 | 42.57 | 38 | 47.15 |
84
+ | GPT-4 | 54.82 | 65.02 | 92.64 | 52.88 | 62.67 | 52.67 | 42.33 | 24.75 | 35.67 | 53.72 |
85
+ | Llama3-8B-Instruct | 51.31 | 27.79 | 90.30 | 40.88 | 34.00 | 30.00 | 45.33 | 60.89 | 33.67 | 46.02 |
86
+ | LlaSMol | 27.78 | 29.34 | 31.44 | 23.38 | 25.67 | 24.00 | 37.33 | 34.65 | 22.67 | 28.47 |
87
+ | ChemDFM | 36.92 | 55.57 | 83.95 | 42.00 | 40.00 | 37.33 | 39.00 | 33.17 | 32.00 | 44.44 |
88
+ | ChemLLM-7B-Chat | 41.05 | 29.76 | 85.28 | 26.12 | 26.00 | 24.00 | 20.00 | 24.26 | 31.00 | 34.16 |
89
+ | ChemLLM-7B-Chat-1.5-SFT | 50.06 | 49.51 | 85.28 | 38.75 | 38.00 | 26.67 | 28.33 | 31.68 | 33.67 | 42.44 |
90
+ | Llama3-KALE-LM-Chem-1.5-8B | 61.33 | 43.44 | 90.30 | 53.62 | 72.67 | 53.67 | 46.00 | 47.03 | 45.00 | 57.01 |
91
+
92
+ ## Cite This Work
93
+
94
+ ```
95
+ @article{dai2024kale,
96
+ title={KALE-LM: Unleash The Power Of AI For Science Via Knowledge And Logic Enhanced Large Model},
97
+ author={Dai, Weichen and Chen, Yezeng and Dai, Zijie and Huang, Zhijie and Liu, Yubo and Pan, Yixuan and Song, Baiyang and Zhong, Chengli and Li, Xinhe and Wang, Zeyu and others},
98
+ journal={arXiv preprint arXiv:2409.18695},
99
+ year={2024}
100
+ }
101
+ ```
102
+