Triangle104 commited on
Commit
f802104
1 Parent(s): 8e8a012

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +165 -0
README.md ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: leafspark/Llama-3.1-8B-MultiReflection-Instruct
3
+ datasets:
4
+ - leafspark/DetailedReflection-Claude-v3_5-Sonnet
5
+ language:
6
+ - en
7
+ - de
8
+ - fr
9
+ - it
10
+ - pt
11
+ - hi
12
+ - es
13
+ - th
14
+ library_name: transformers
15
+ license: llama3.1
16
+ metrics:
17
+ - accuracy
18
+ pipeline_tag: text-generation
19
+ tags:
20
+ - reflection
21
+ - unsloth
22
+ - peft
23
+ - llama
24
+ - llama-cpp
25
+ - gguf-my-repo
26
+ model-index:
27
+ - name: Llama-3.1-8B-MultiReflection-Instruct
28
+ results:
29
+ - task:
30
+ type: text-generation
31
+ name: Text Generation
32
+ dataset:
33
+ name: IFEval (0-Shot)
34
+ type: HuggingFaceH4/ifeval
35
+ args:
36
+ num_few_shot: 0
37
+ metrics:
38
+ - type: inst_level_strict_acc and prompt_level_strict_acc
39
+ value: 71.25
40
+ name: strict accuracy
41
+ source:
42
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
43
+ name: Open LLM Leaderboard
44
+ - task:
45
+ type: text-generation
46
+ name: Text Generation
47
+ dataset:
48
+ name: BBH (3-Shot)
49
+ type: BBH
50
+ args:
51
+ num_few_shot: 3
52
+ metrics:
53
+ - type: acc_norm
54
+ value: 28.45
55
+ name: normalized accuracy
56
+ source:
57
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
58
+ name: Open LLM Leaderboard
59
+ - task:
60
+ type: text-generation
61
+ name: Text Generation
62
+ dataset:
63
+ name: MATH Lvl 5 (4-Shot)
64
+ type: hendrycks/competition_math
65
+ args:
66
+ num_few_shot: 4
67
+ metrics:
68
+ - type: exact_match
69
+ value: 12.54
70
+ name: exact match
71
+ source:
72
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
73
+ name: Open LLM Leaderboard
74
+ - task:
75
+ type: text-generation
76
+ name: Text Generation
77
+ dataset:
78
+ name: GPQA (0-shot)
79
+ type: Idavidrein/gpqa
80
+ args:
81
+ num_few_shot: 0
82
+ metrics:
83
+ - type: acc_norm
84
+ value: 5.7
85
+ name: acc_norm
86
+ source:
87
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
88
+ name: Open LLM Leaderboard
89
+ - task:
90
+ type: text-generation
91
+ name: Text Generation
92
+ dataset:
93
+ name: MuSR (0-shot)
94
+ type: TAUR-Lab/MuSR
95
+ args:
96
+ num_few_shot: 0
97
+ metrics:
98
+ - type: acc_norm
99
+ value: 8.52
100
+ name: acc_norm
101
+ source:
102
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
103
+ name: Open LLM Leaderboard
104
+ - task:
105
+ type: text-generation
106
+ name: Text Generation
107
+ dataset:
108
+ name: MMLU-PRO (5-shot)
109
+ type: TIGER-Lab/MMLU-Pro
110
+ config: main
111
+ split: test
112
+ args:
113
+ num_few_shot: 5
114
+ metrics:
115
+ - type: acc
116
+ value: 30.27
117
+ name: accuracy
118
+ source:
119
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
120
+ name: Open LLM Leaderboard
121
+ ---
122
+
123
+ # Triangle104/Llama-3.1-8B-MultiReflection-Instruct-Q4_K_M-GGUF
124
+ This model was converted to GGUF format from [`leafspark/Llama-3.1-8B-MultiReflection-Instruct`](https://huggingface.co/leafspark/Llama-3.1-8B-MultiReflection-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
125
+ Refer to the [original model card](https://huggingface.co/leafspark/Llama-3.1-8B-MultiReflection-Instruct) for more details on the model.
126
+
127
+ ## Use with llama.cpp
128
+ Install llama.cpp through brew (works on Mac and Linux)
129
+
130
+ ```bash
131
+ brew install llama.cpp
132
+
133
+ ```
134
+ Invoke the llama.cpp server or the CLI.
135
+
136
+ ### CLI:
137
+ ```bash
138
+ llama-cli --hf-repo Triangle104/Llama-3.1-8B-MultiReflection-Instruct-Q4_K_M-GGUF --hf-file llama-3.1-8b-multireflection-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
139
+ ```
140
+
141
+ ### Server:
142
+ ```bash
143
+ llama-server --hf-repo Triangle104/Llama-3.1-8B-MultiReflection-Instruct-Q4_K_M-GGUF --hf-file llama-3.1-8b-multireflection-instruct-q4_k_m.gguf -c 2048
144
+ ```
145
+
146
+ 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.
147
+
148
+ Step 1: Clone llama.cpp from GitHub.
149
+ ```
150
+ git clone https://github.com/ggerganov/llama.cpp
151
+ ```
152
+
153
+ 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).
154
+ ```
155
+ cd llama.cpp && LLAMA_CURL=1 make
156
+ ```
157
+
158
+ Step 3: Run inference through the main binary.
159
+ ```
160
+ ./llama-cli --hf-repo Triangle104/Llama-3.1-8B-MultiReflection-Instruct-Q4_K_M-GGUF --hf-file llama-3.1-8b-multireflection-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
161
+ ```
162
+ or
163
+ ```
164
+ ./llama-server --hf-repo Triangle104/Llama-3.1-8B-MultiReflection-Instruct-Q4_K_M-GGUF --hf-file llama-3.1-8b-multireflection-instruct-q4_k_m.gguf -c 2048
165
+ ```