DavidAU commited on
Commit
d2a2062
1 Parent(s): 32ae373

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +148 -0
README.md ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+ - not-for-all-audiences
8
+ - llama-cpp
9
+ - gguf-my-repo
10
+ base_model:
11
+ - Kooten/DaringMaid-20B
12
+ - TeeZee/DarkForest-20B-v2.0
13
+ - athirdpath/Iambe-RP-v3-20b
14
+ license_name: microsoft-research-license
15
+ model-index:
16
+ - name: StarDust_20B_v0.2
17
+ results:
18
+ - task:
19
+ type: text-generation
20
+ name: Text Generation
21
+ dataset:
22
+ name: AI2 Reasoning Challenge (25-Shot)
23
+ type: ai2_arc
24
+ config: ARC-Challenge
25
+ split: test
26
+ args:
27
+ num_few_shot: 25
28
+ metrics:
29
+ - type: acc_norm
30
+ value: 61.01
31
+ name: normalized accuracy
32
+ source:
33
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Evillain/StarDust_20B_v0.2
34
+ name: Open LLM Leaderboard
35
+ - task:
36
+ type: text-generation
37
+ name: Text Generation
38
+ dataset:
39
+ name: HellaSwag (10-Shot)
40
+ type: hellaswag
41
+ split: validation
42
+ args:
43
+ num_few_shot: 10
44
+ metrics:
45
+ - type: acc_norm
46
+ value: 83.76
47
+ name: normalized accuracy
48
+ source:
49
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Evillain/StarDust_20B_v0.2
50
+ name: Open LLM Leaderboard
51
+ - task:
52
+ type: text-generation
53
+ name: Text Generation
54
+ dataset:
55
+ name: MMLU (5-Shot)
56
+ type: cais/mmlu
57
+ config: all
58
+ split: test
59
+ args:
60
+ num_few_shot: 5
61
+ metrics:
62
+ - type: acc
63
+ value: 59.29
64
+ name: accuracy
65
+ source:
66
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Evillain/StarDust_20B_v0.2
67
+ name: Open LLM Leaderboard
68
+ - task:
69
+ type: text-generation
70
+ name: Text Generation
71
+ dataset:
72
+ name: TruthfulQA (0-shot)
73
+ type: truthful_qa
74
+ config: multiple_choice
75
+ split: validation
76
+ args:
77
+ num_few_shot: 0
78
+ metrics:
79
+ - type: mc2
80
+ value: 51.43
81
+ source:
82
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Evillain/StarDust_20B_v0.2
83
+ name: Open LLM Leaderboard
84
+ - task:
85
+ type: text-generation
86
+ name: Text Generation
87
+ dataset:
88
+ name: Winogrande (5-shot)
89
+ type: winogrande
90
+ config: winogrande_xl
91
+ split: validation
92
+ args:
93
+ num_few_shot: 5
94
+ metrics:
95
+ - type: acc
96
+ value: 77.27
97
+ name: accuracy
98
+ source:
99
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Evillain/StarDust_20B_v0.2
100
+ name: Open LLM Leaderboard
101
+ - task:
102
+ type: text-generation
103
+ name: Text Generation
104
+ dataset:
105
+ name: GSM8k (5-shot)
106
+ type: gsm8k
107
+ config: main
108
+ split: test
109
+ args:
110
+ num_few_shot: 5
111
+ metrics:
112
+ - type: acc
113
+ value: 24.03
114
+ name: accuracy
115
+ source:
116
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Evillain/StarDust_20B_v0.2
117
+ name: Open LLM Leaderboard
118
+ ---
119
+
120
+ # DavidAU/StarDust_20B_v0.2-Q5_K_S-GGUF
121
+ This model was converted to GGUF format from [`Evillain/StarDust_20B_v0.2`](https://huggingface.co/Evillain/StarDust_20B_v0.2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
122
+ Refer to the [original model card](https://huggingface.co/Evillain/StarDust_20B_v0.2) for more details on the model.
123
+ ## Use with llama.cpp
124
+
125
+ Install llama.cpp through brew.
126
+
127
+ ```bash
128
+ brew install ggerganov/ggerganov/llama.cpp
129
+ ```
130
+ Invoke the llama.cpp server or the CLI.
131
+
132
+ CLI:
133
+
134
+ ```bash
135
+ llama-cli --hf-repo DavidAU/StarDust_20B_v0.2-Q5_K_S-GGUF --model stardust_20b_v0.2.Q5_K_S.gguf -p "The meaning to life and the universe is"
136
+ ```
137
+
138
+ Server:
139
+
140
+ ```bash
141
+ llama-server --hf-repo DavidAU/StarDust_20B_v0.2-Q5_K_S-GGUF --model stardust_20b_v0.2.Q5_K_S.gguf -c 2048
142
+ ```
143
+
144
+ Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
145
+
146
+ ```
147
+ git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m stardust_20b_v0.2.Q5_K_S.gguf -n 128
148
+ ```