DavidAU commited on
Commit
76ec611
1 Parent(s): ffd8323

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +195 -0
README.md ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: other
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ - instruct
9
+ - finetune
10
+ - chatml
11
+ - gpt4
12
+ - synthetic data
13
+ - science
14
+ - physics
15
+ - chemistry
16
+ - biology
17
+ - math
18
+ - llama
19
+ - llama3
20
+ - llama-cpp
21
+ - gguf-my-repo
22
+ base_model: meta-llama/Meta-Llama-3-8B
23
+ datasets:
24
+ - allenai/ai2_arc
25
+ - camel-ai/physics
26
+ - camel-ai/chemistry
27
+ - camel-ai/biology
28
+ - camel-ai/math
29
+ - metaeval/reclor
30
+ - openbookqa
31
+ - mandyyyyii/scibench
32
+ - derek-thomas/ScienceQA
33
+ - TIGER-Lab/ScienceEval
34
+ - jondurbin/airoboros-3.2
35
+ - LDJnr/Capybara
36
+ - Cot-Alpaca-GPT4-From-OpenHermes-2.5
37
+ - STEM-AI-mtl/Electrical-engineering
38
+ - knowrohit07/saraswati-stem
39
+ - sablo/oasst2_curated
40
+ - lmsys/lmsys-chat-1m
41
+ - TIGER-Lab/MathInstruct
42
+ - bigbio/med_qa
43
+ - meta-math/MetaMathQA-40K
44
+ - openbookqa
45
+ - piqa
46
+ - metaeval/reclor
47
+ - derek-thomas/ScienceQA
48
+ - scibench
49
+ - sciq
50
+ - Open-Orca/SlimOrca
51
+ - migtissera/Synthia-v1.3
52
+ - TIGER-Lab/ScienceEval
53
+ - allenai/WildChat
54
+ - microsoft/orca-math-word-problems-200k
55
+ - openchat/openchat_sharegpt4_dataset
56
+ - teknium/GPTeacher-General-Instruct
57
+ - m-a-p/CodeFeedback-Filtered-Instruction
58
+ - totally-not-an-llm/EverythingLM-data-V3
59
+ - HuggingFaceH4/no_robots
60
+ - OpenAssistant/oasst_top1_2023-08-25
61
+ - WizardLM/WizardLM_evol_instruct_70k
62
+ model-index:
63
+ - name: Einstein-v6.1-Llama3-8B
64
+ results:
65
+ - task:
66
+ type: text-generation
67
+ name: Text Generation
68
+ dataset:
69
+ name: AI2 Reasoning Challenge (25-Shot)
70
+ type: ai2_arc
71
+ config: ARC-Challenge
72
+ split: test
73
+ args:
74
+ num_few_shot: 25
75
+ metrics:
76
+ - type: acc_norm
77
+ value: 62.46
78
+ name: normalized accuracy
79
+ source:
80
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
81
+ name: Open LLM Leaderboard
82
+ - task:
83
+ type: text-generation
84
+ name: Text Generation
85
+ dataset:
86
+ name: HellaSwag (10-Shot)
87
+ type: hellaswag
88
+ split: validation
89
+ args:
90
+ num_few_shot: 10
91
+ metrics:
92
+ - type: acc_norm
93
+ value: 82.41
94
+ name: normalized accuracy
95
+ source:
96
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
97
+ name: Open LLM Leaderboard
98
+ - task:
99
+ type: text-generation
100
+ name: Text Generation
101
+ dataset:
102
+ name: MMLU (5-Shot)
103
+ type: cais/mmlu
104
+ config: all
105
+ split: test
106
+ args:
107
+ num_few_shot: 5
108
+ metrics:
109
+ - type: acc
110
+ value: 66.19
111
+ name: accuracy
112
+ source:
113
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
114
+ name: Open LLM Leaderboard
115
+ - task:
116
+ type: text-generation
117
+ name: Text Generation
118
+ dataset:
119
+ name: TruthfulQA (0-shot)
120
+ type: truthful_qa
121
+ config: multiple_choice
122
+ split: validation
123
+ args:
124
+ num_few_shot: 0
125
+ metrics:
126
+ - type: mc2
127
+ value: 55.1
128
+ source:
129
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
130
+ name: Open LLM Leaderboard
131
+ - task:
132
+ type: text-generation
133
+ name: Text Generation
134
+ dataset:
135
+ name: Winogrande (5-shot)
136
+ type: winogrande
137
+ config: winogrande_xl
138
+ split: validation
139
+ args:
140
+ num_few_shot: 5
141
+ metrics:
142
+ - type: acc
143
+ value: 79.32
144
+ name: accuracy
145
+ source:
146
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
147
+ name: Open LLM Leaderboard
148
+ - task:
149
+ type: text-generation
150
+ name: Text Generation
151
+ dataset:
152
+ name: GSM8k (5-shot)
153
+ type: gsm8k
154
+ config: main
155
+ split: test
156
+ args:
157
+ num_few_shot: 5
158
+ metrics:
159
+ - type: acc
160
+ value: 66.11
161
+ name: accuracy
162
+ source:
163
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
164
+ name: Open LLM Leaderboard
165
+ ---
166
+
167
+ # DavidAU/Einstein-v6.1-Llama3-8B-Q8_0-GGUF
168
+ This model was converted to GGUF format from [`Weyaxi/Einstein-v6.1-Llama3-8B`](https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
169
+ Refer to the [original model card](https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B) for more details on the model.
170
+ ## Use with llama.cpp
171
+
172
+ Install llama.cpp through brew.
173
+
174
+ ```bash
175
+ brew install ggerganov/ggerganov/llama.cpp
176
+ ```
177
+ Invoke the llama.cpp server or the CLI.
178
+
179
+ CLI:
180
+
181
+ ```bash
182
+ llama-cli --hf-repo DavidAU/Einstein-v6.1-Llama3-8B-Q8_0-GGUF --model einstein-v6.1-llama3-8b.Q8_0.gguf -p "The meaning to life and the universe is"
183
+ ```
184
+
185
+ Server:
186
+
187
+ ```bash
188
+ llama-server --hf-repo DavidAU/Einstein-v6.1-Llama3-8B-Q8_0-GGUF --model einstein-v6.1-llama3-8b.Q8_0.gguf -c 2048
189
+ ```
190
+
191
+ 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.
192
+
193
+ ```
194
+ git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m einstein-v6.1-llama3-8b.Q8_0.gguf -n 128
195
+ ```