DavidAU commited on
Commit
ed68005
1 Parent(s): 03d7611

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +87 -0
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ library_name: transformers
6
+ tags:
7
+ - transformers
8
+ - llama-cpp
9
+ - gguf-my-repo
10
+ base_model: openlm-research/open_llama_3b
11
+ datasets:
12
+ - mwitiderrick/AlpacaCode
13
+ inference: true
14
+ model_type: llama
15
+ prompt_template: '### Instruction:\n
16
+
17
+ {prompt}
18
+
19
+ ### Response:
20
+
21
+ '
22
+ created_by: mwitiderrick
23
+ pipeline_tag: text-generation
24
+ model-index:
25
+ - name: mwitiderrick/open_llama_3b_instruct_v_0.2
26
+ results:
27
+ - task:
28
+ type: text-generation
29
+ dataset:
30
+ name: hellaswag
31
+ type: hellaswag
32
+ metrics:
33
+ - type: hellaswag (0-Shot)
34
+ value: 0.6581
35
+ name: hellaswag(0-Shot)
36
+ - task:
37
+ type: text-generation
38
+ dataset:
39
+ name: winogrande
40
+ type: winogrande
41
+ metrics:
42
+ - type: winogrande (0-Shot)
43
+ value: 0.6267
44
+ name: winogrande(0-Shot)
45
+ - task:
46
+ type: text-generation
47
+ dataset:
48
+ name: arc_challenge
49
+ type: arc_challenge
50
+ metrics:
51
+ - type: arc_challenge (0-Shot)
52
+ value: 0.3712
53
+ name: arc_challenge(0-Shot)
54
+ source:
55
+ url: https://huggingface.co/mwitiderrick/open_llama_3b_instruct_v_0.2
56
+ name: open_llama_3b_instruct_v_0.2 model card
57
+ ---
58
+
59
+ # DavidAU/open_llama_3b_code_instruct_0.1-Q8_0-GGUF
60
+ This model was converted to GGUF format from [`mwitiderrick/open_llama_3b_code_instruct_0.1`](https://huggingface.co/mwitiderrick/open_llama_3b_code_instruct_0.1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
61
+ Refer to the [original model card](https://huggingface.co/mwitiderrick/open_llama_3b_code_instruct_0.1) for more details on the model.
62
+ ## Use with llama.cpp
63
+
64
+ Install llama.cpp through brew.
65
+
66
+ ```bash
67
+ brew install ggerganov/ggerganov/llama.cpp
68
+ ```
69
+ Invoke the llama.cpp server or the CLI.
70
+
71
+ CLI:
72
+
73
+ ```bash
74
+ llama-cli --hf-repo DavidAU/open_llama_3b_code_instruct_0.1-Q8_0-GGUF --model open_llama_3b_code_instruct_0.1.Q8_0.gguf -p "The meaning to life and the universe is"
75
+ ```
76
+
77
+ Server:
78
+
79
+ ```bash
80
+ llama-server --hf-repo DavidAU/open_llama_3b_code_instruct_0.1-Q8_0-GGUF --model open_llama_3b_code_instruct_0.1.Q8_0.gguf -c 2048
81
+ ```
82
+
83
+ 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.
84
+
85
+ ```
86
+ git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m open_llama_3b_code_instruct_0.1.Q8_0.gguf -n 128
87
+ ```