Triangle104 commited on
Commit
8325ec1
1 Parent(s): fd67190

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +150 -0
README.md ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: flammenai/Flammades-Mistral-Nemo-12B
3
+ datasets:
4
+ - flammenai/Date-DPO-NoAsterisks
5
+ - jondurbin/truthy-dpo-v0.1
6
+ library_name: transformers
7
+ license: apache-2.0
8
+ tags:
9
+ - llama-cpp
10
+ - gguf-my-repo
11
+ model-index:
12
+ - name: Flammades-Mistral-Nemo-12B
13
+ results:
14
+ - task:
15
+ type: text-generation
16
+ name: Text Generation
17
+ dataset:
18
+ name: IFEval (0-Shot)
19
+ type: HuggingFaceH4/ifeval
20
+ args:
21
+ num_few_shot: 0
22
+ metrics:
23
+ - type: inst_level_strict_acc and prompt_level_strict_acc
24
+ value: 38.42
25
+ name: strict accuracy
26
+ source:
27
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Flammades-Mistral-Nemo-12B
28
+ name: Open LLM Leaderboard
29
+ - task:
30
+ type: text-generation
31
+ name: Text Generation
32
+ dataset:
33
+ name: BBH (3-Shot)
34
+ type: BBH
35
+ args:
36
+ num_few_shot: 3
37
+ metrics:
38
+ - type: acc_norm
39
+ value: 32.39
40
+ name: normalized accuracy
41
+ source:
42
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Flammades-Mistral-Nemo-12B
43
+ name: Open LLM Leaderboard
44
+ - task:
45
+ type: text-generation
46
+ name: Text Generation
47
+ dataset:
48
+ name: MATH Lvl 5 (4-Shot)
49
+ type: hendrycks/competition_math
50
+ args:
51
+ num_few_shot: 4
52
+ metrics:
53
+ - type: exact_match
54
+ value: 6.19
55
+ name: exact match
56
+ source:
57
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Flammades-Mistral-Nemo-12B
58
+ name: Open LLM Leaderboard
59
+ - task:
60
+ type: text-generation
61
+ name: Text Generation
62
+ dataset:
63
+ name: GPQA (0-shot)
64
+ type: Idavidrein/gpqa
65
+ args:
66
+ num_few_shot: 0
67
+ metrics:
68
+ - type: acc_norm
69
+ value: 7.16
70
+ name: acc_norm
71
+ source:
72
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Flammades-Mistral-Nemo-12B
73
+ name: Open LLM Leaderboard
74
+ - task:
75
+ type: text-generation
76
+ name: Text Generation
77
+ dataset:
78
+ name: MuSR (0-shot)
79
+ type: TAUR-Lab/MuSR
80
+ args:
81
+ num_few_shot: 0
82
+ metrics:
83
+ - type: acc_norm
84
+ value: 20.31
85
+ name: acc_norm
86
+ source:
87
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Flammades-Mistral-Nemo-12B
88
+ name: Open LLM Leaderboard
89
+ - task:
90
+ type: text-generation
91
+ name: Text Generation
92
+ dataset:
93
+ name: MMLU-PRO (5-shot)
94
+ type: TIGER-Lab/MMLU-Pro
95
+ config: main
96
+ split: test
97
+ args:
98
+ num_few_shot: 5
99
+ metrics:
100
+ - type: acc
101
+ value: 29.57
102
+ name: accuracy
103
+ source:
104
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Flammades-Mistral-Nemo-12B
105
+ name: Open LLM Leaderboard
106
+ ---
107
+
108
+ # Triangle104/Flammades-Mistral-Nemo-12B-Q5_K_M-GGUF
109
+ This model was converted to GGUF format from [`flammenai/Flammades-Mistral-Nemo-12B`](https://huggingface.co/flammenai/Flammades-Mistral-Nemo-12B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
110
+ Refer to the [original model card](https://huggingface.co/flammenai/Flammades-Mistral-Nemo-12B) for more details on the model.
111
+
112
+ ## Use with llama.cpp
113
+ Install llama.cpp through brew (works on Mac and Linux)
114
+
115
+ ```bash
116
+ brew install llama.cpp
117
+
118
+ ```
119
+ Invoke the llama.cpp server or the CLI.
120
+
121
+ ### CLI:
122
+ ```bash
123
+ llama-cli --hf-repo Triangle104/Flammades-Mistral-Nemo-12B-Q5_K_M-GGUF --hf-file flammades-mistral-nemo-12b-q5_k_m.gguf -p "The meaning to life and the universe is"
124
+ ```
125
+
126
+ ### Server:
127
+ ```bash
128
+ llama-server --hf-repo Triangle104/Flammades-Mistral-Nemo-12B-Q5_K_M-GGUF --hf-file flammades-mistral-nemo-12b-q5_k_m.gguf -c 2048
129
+ ```
130
+
131
+ 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.
132
+
133
+ Step 1: Clone llama.cpp from GitHub.
134
+ ```
135
+ git clone https://github.com/ggerganov/llama.cpp
136
+ ```
137
+
138
+ 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).
139
+ ```
140
+ cd llama.cpp && LLAMA_CURL=1 make
141
+ ```
142
+
143
+ Step 3: Run inference through the main binary.
144
+ ```
145
+ ./llama-cli --hf-repo Triangle104/Flammades-Mistral-Nemo-12B-Q5_K_M-GGUF --hf-file flammades-mistral-nemo-12b-q5_k_m.gguf -p "The meaning to life and the universe is"
146
+ ```
147
+ or
148
+ ```
149
+ ./llama-server --hf-repo Triangle104/Flammades-Mistral-Nemo-12B-Q5_K_M-GGUF --hf-file flammades-mistral-nemo-12b-q5_k_m.gguf -c 2048
150
+ ```