matrixportal
commited on
Commit
•
0e4522f
1
Parent(s):
cccefb7
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- de
|
5 |
+
- fr
|
6 |
+
- it
|
7 |
+
- pt
|
8 |
+
- hi
|
9 |
+
- es
|
10 |
+
- th
|
11 |
+
license: llama3.1
|
12 |
+
library_name: transformers
|
13 |
+
tags:
|
14 |
+
- llama-3.1
|
15 |
+
- conversational
|
16 |
+
- instruction following
|
17 |
+
- reasoning
|
18 |
+
- function calling
|
19 |
+
- mergekit
|
20 |
+
- finetuning
|
21 |
+
- axolotl
|
22 |
+
- llama-cpp
|
23 |
+
- gguf-my-repo
|
24 |
+
pipeline_tag: text-generation
|
25 |
+
base_model: akjindal53244/Llama-3.1-Storm-8B
|
26 |
+
model-index:
|
27 |
+
- name: Llama-3.1-Storm-8B
|
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: 80.51
|
40 |
+
name: strict accuracy
|
41 |
+
source:
|
42 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=akjindal53244/Llama-3.1-Storm-8B
|
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: 31.49
|
55 |
+
name: normalized accuracy
|
56 |
+
source:
|
57 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=akjindal53244/Llama-3.1-Storm-8B
|
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: 16.62
|
70 |
+
name: exact match
|
71 |
+
source:
|
72 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=akjindal53244/Llama-3.1-Storm-8B
|
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: 10.18
|
85 |
+
name: acc_norm
|
86 |
+
source:
|
87 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=akjindal53244/Llama-3.1-Storm-8B
|
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: 9.12
|
100 |
+
name: acc_norm
|
101 |
+
source:
|
102 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=akjindal53244/Llama-3.1-Storm-8B
|
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: 31.15
|
117 |
+
name: accuracy
|
118 |
+
source:
|
119 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=akjindal53244/Llama-3.1-Storm-8B
|
120 |
+
name: Open LLM Leaderboard
|
121 |
+
---
|
122 |
+
|
123 |
+
# matrixportal/Llama-3.1-Storm-8B-Q4_0-GGUF
|
124 |
+
This model was converted to GGUF format from [`akjindal53244/Llama-3.1-Storm-8B`](https://huggingface.co/akjindal53244/Llama-3.1-Storm-8B) 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/akjindal53244/Llama-3.1-Storm-8B) 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 matrixportal/Llama-3.1-Storm-8B-Q4_0-GGUF --hf-file llama-3.1-storm-8b-q4_0.gguf -p "The meaning to life and the universe is"
|
139 |
+
```
|
140 |
+
|
141 |
+
### Server:
|
142 |
+
```bash
|
143 |
+
llama-server --hf-repo matrixportal/Llama-3.1-Storm-8B-Q4_0-GGUF --hf-file llama-3.1-storm-8b-q4_0.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 matrixportal/Llama-3.1-Storm-8B-Q4_0-GGUF --hf-file llama-3.1-storm-8b-q4_0.gguf -p "The meaning to life and the universe is"
|
161 |
+
```
|
162 |
+
or
|
163 |
+
```
|
164 |
+
./llama-server --hf-repo matrixportal/Llama-3.1-Storm-8B-Q4_0-GGUF --hf-file llama-3.1-storm-8b-q4_0.gguf -c 2048
|
165 |
+
```
|