victorbur commited on
Commit
3f4e874
1 Parent(s): 5a1f49a

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +219 -0
README.md ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: LeroyDyer/LCARS_AI_DeepMind
3
+ datasets:
4
+ - gretelai/synthetic_text_to_sql
5
+ - HuggingFaceTB/cosmopedia
6
+ - teknium/OpenHermes-2.5
7
+ - Open-Orca/SlimOrca
8
+ - Open-Orca/OpenOrca
9
+ - cognitivecomputations/dolphin-coder
10
+ - databricks/databricks-dolly-15k
11
+ - yahma/alpaca-cleaned
12
+ - uonlp/CulturaX
13
+ - mwitiderrick/SwahiliPlatypus
14
+ - swahili
15
+ - Rogendo/English-Swahili-Sentence-Pairs
16
+ - ise-uiuc/Magicoder-Evol-Instruct-110K
17
+ - meta-math/MetaMathQA
18
+ - abacusai/ARC_DPO_FewShot
19
+ - abacusai/MetaMath_DPO_FewShot
20
+ - abacusai/HellaSwag_DPO_FewShot
21
+ - HaltiaAI/Her-The-Movie-Samantha-and-Theodore-Dataset
22
+ - gretelai/synthetic_text_to_sql
23
+ - HuggingFaceTB/cosmopedia
24
+ - teknium/OpenHermes-2.5
25
+ - cognitivecomputations/dolphin-coder
26
+ - databricks/databricks-dolly-15k
27
+ - yahma/alpaca-cleaned
28
+ - uonlp/CulturaX
29
+ - mwitiderrick/SwahiliPlatypus
30
+ - swahili
31
+ - Rogendo/English-Swahili-Sentence-Pairs
32
+ - ise-uiuc/Magicoder-Evol-Instruct-110K
33
+ - meta-math/MetaMathQA
34
+ language:
35
+ - en
36
+ license: apache-2.0
37
+ metrics:
38
+ - accuracy
39
+ - bertscore
40
+ - bleu
41
+ - brier_score
42
+ - cer
43
+ - character
44
+ - charcut_mt
45
+ - chrf
46
+ - code_eval
47
+ tags:
48
+ - text-generation-inference
49
+ - transformers
50
+ - leaderboard
51
+ - mistral
52
+ - trl
53
+ - llama-cpp
54
+ - gguf-my-repo
55
+ y-Gene:
56
+ - LeroyDyer/Mixtral_AI_DeepMind
57
+ - LeroyDyer/Mixtral_AI_CyberUltron_DPO
58
+ - LeroyDyer/Mixtral_AI_Chat_2.0
59
+ - LeroyDyer/Mixtral_AI_DeepMedicalMind
60
+ - LeroyDyer/Mixtral_AI_Samantha
61
+ x-Gene:
62
+ - LeroyDyer/Mixtral_AI_Chat_2.0
63
+ - LeroyDyer/Mixtral_BioMedical
64
+ - LeroyDyer/Mixtral_AI_Medic
65
+ - LeroyDyer/Mixtral_Cyber_BioMedic
66
+ - LeroyDyer/Mixtral_AI_DeepMedicalMind
67
+ Variant:
68
+ - LeroyDyer/MetaMath_LLM
69
+ - LeroyDyer/TruthfulQA_LLM
70
+ - LeroyDyer/HellaSwag_LLM
71
+ - LeroyDyer/Mixtral_AI_DeepMedicalMind
72
+ model-index:
73
+ - name: Mixtral_AI_CyberTron_DeepMind_III_UFT
74
+ results:
75
+ - task:
76
+ type: text-generation
77
+ name: Text Generation
78
+ dataset:
79
+ name: AI2 Reasoning Challenge (25-Shot)
80
+ type: ai2_arc
81
+ config: ARC-Challenge
82
+ split: test
83
+ args:
84
+ num_few_shot: 25
85
+ metrics:
86
+ - type: acc_norm
87
+ value: 61.86
88
+ name: normalized accuracy
89
+ source:
90
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=LeroyDyer/Mixtral_AI_CyberTron_DeepMind_III_UFT
91
+ name: Open LLM Leaderboard
92
+ - task:
93
+ type: text-generation
94
+ name: Text Generation
95
+ dataset:
96
+ name: HellaSwag (10-Shot)
97
+ type: hellaswag
98
+ split: validation
99
+ args:
100
+ num_few_shot: 10
101
+ metrics:
102
+ - type: acc_norm
103
+ value: 83.15
104
+ name: normalized accuracy
105
+ source:
106
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=LeroyDyer/Mixtral_AI_CyberTron_DeepMind_III_UFT
107
+ name: Open LLM Leaderboard
108
+ - task:
109
+ type: text-generation
110
+ name: Text Generation
111
+ dataset:
112
+ name: MMLU (5-Shot)
113
+ type: cais/mmlu
114
+ config: all
115
+ split: test
116
+ args:
117
+ num_few_shot: 5
118
+ metrics:
119
+ - type: acc
120
+ value: 61.95
121
+ name: accuracy
122
+ source:
123
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=LeroyDyer/Mixtral_AI_CyberTron_DeepMind_III_UFT
124
+ name: Open LLM Leaderboard
125
+ - task:
126
+ type: text-generation
127
+ name: Text Generation
128
+ dataset:
129
+ name: TruthfulQA (0-shot)
130
+ type: truthful_qa
131
+ config: multiple_choice
132
+ split: validation
133
+ args:
134
+ num_few_shot: 0
135
+ metrics:
136
+ - type: mc2
137
+ value: 49.41
138
+ source:
139
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=LeroyDyer/Mixtral_AI_CyberTron_DeepMind_III_UFT
140
+ name: Open LLM Leaderboard
141
+ - task:
142
+ type: text-generation
143
+ name: Text Generation
144
+ dataset:
145
+ name: Winogrande (5-shot)
146
+ type: winogrande
147
+ config: winogrande_xl
148
+ split: validation
149
+ args:
150
+ num_few_shot: 5
151
+ metrics:
152
+ - type: acc
153
+ value: 77.98
154
+ name: accuracy
155
+ source:
156
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=LeroyDyer/Mixtral_AI_CyberTron_DeepMind_III_UFT
157
+ name: Open LLM Leaderboard
158
+ - task:
159
+ type: text-generation
160
+ name: Text Generation
161
+ dataset:
162
+ name: GSM8k (5-shot)
163
+ type: gsm8k
164
+ config: main
165
+ split: test
166
+ args:
167
+ num_few_shot: 5
168
+ metrics:
169
+ - type: acc
170
+ value: 51.86
171
+ name: accuracy
172
+ source:
173
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=LeroyDyer/Mixtral_AI_CyberTron_DeepMind_III_UFT
174
+ name: Open LLM Leaderboard
175
+ ---
176
+
177
+ # victorbur/LCARS_AI_DeepMind-Q5_K_M-GGUF
178
+ This model was converted to GGUF format from [`LeroyDyer/LCARS_AI_DeepMind`](https://huggingface.co/LeroyDyer/LCARS_AI_DeepMind) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
179
+ Refer to the [original model card](https://huggingface.co/LeroyDyer/LCARS_AI_DeepMind) for more details on the model.
180
+
181
+ ## Use with llama.cpp
182
+ Install llama.cpp through brew (works on Mac and Linux)
183
+
184
+ ```bash
185
+ brew install llama.cpp
186
+
187
+ ```
188
+ Invoke the llama.cpp server or the CLI.
189
+
190
+ ### CLI:
191
+ ```bash
192
+ llama-cli --hf-repo victorbur/LCARS_AI_DeepMind-Q5_K_M-GGUF --hf-file lcars_ai_deepmind-q5_k_m.gguf -p "The meaning to life and the universe is"
193
+ ```
194
+
195
+ ### Server:
196
+ ```bash
197
+ llama-server --hf-repo victorbur/LCARS_AI_DeepMind-Q5_K_M-GGUF --hf-file lcars_ai_deepmind-q5_k_m.gguf -c 2048
198
+ ```
199
+
200
+ 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.
201
+
202
+ Step 1: Clone llama.cpp from GitHub.
203
+ ```
204
+ git clone https://github.com/ggerganov/llama.cpp
205
+ ```
206
+
207
+ Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
208
+ ```
209
+ cd llama.cpp && LLAMA_CURL=1 make
210
+ ```
211
+
212
+ Step 3: Run inference through the main binary.
213
+ ```
214
+ ./llama-cli --hf-repo victorbur/LCARS_AI_DeepMind-Q5_K_M-GGUF --hf-file lcars_ai_deepmind-q5_k_m.gguf -p "The meaning to life and the universe is"
215
+ ```
216
+ or
217
+ ```
218
+ ./llama-server --hf-repo victorbur/LCARS_AI_DeepMind-Q5_K_M-GGUF --hf-file lcars_ai_deepmind-q5_k_m.gguf -c 2048
219
+ ```