BallisticAI commited on
Commit
776828a
·
1 Parent(s): 9824e87

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +85 -0
README.md CHANGED
@@ -1,3 +1,88 @@
1
  ---
2
  license: llama2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: llama2
3
+ tags:
4
+ - code llama
5
+ base_model: BallisticAI/Ballistic-CodeLlama-34B-v1
6
+ inference: false
7
+ model_creator: BallisticAI
8
+ model_type: llama
9
+ prompt_template: '### System Prompt
10
+
11
+ {system_message}
12
+
13
+
14
+ ### User Message
15
+
16
+ {prompt}
17
+
18
+
19
+ ### Assistant
20
+
21
+ '
22
+ quantized_by: BallisticAI
23
+ model-index:
24
+ - name: Ballistic-CodeLlama-34B-v1
25
+ results:
26
+ - task:
27
+ type: text-generation
28
+ dataset:
29
+ name: HumanEval
30
+ type: openai_humaneval
31
+ metrics:
32
+ - type: n/a
33
+ value: n/a
34
+ name: n/a
35
+ verified: false
36
  ---
37
+
38
+ # CodeLlama 34B v1
39
+ - Model creator: [BallisticAI](https://huggingface.co/BallisticAI)
40
+ - Base model: [CodeLlama 34B hf](https://huggingface.co/codellama/CodeLlama-34b-hf)
41
+ - Merged with: [CodeLlama 34B v2](https://huggingface.co/Phind/Phind-CodeLlama-34B-v2) && [speechless-codellama-34b-v2](https://huggingface.co/uukuguy/speechless-codellama-34b-v2.0)
42
+ - Additional training with: [jondurbin/airoboros-2.2](https://huggingface.co/datasets/jondurbin/airoboros-2.2)
43
+
44
+
45
+ <!-- description start -->
46
+ ## Description
47
+
48
+ This repo contains GGUF format model files for [Ballistic-CodeLlama-34B-v1](https://huggingface.co/BallisticAI/Ballistic-CodeLlama-34B-v1).
49
+
50
+ <!-- description end -->
51
+
52
+ <!-- prompt-template start -->
53
+ ## How to Prompt the Model
54
+ This model accepts the Alpaca/Vicuna instruction format.
55
+
56
+ For example:
57
+
58
+ ```
59
+ ### System Prompt
60
+ You are an intelligent programming assistant.
61
+
62
+ ### User Message
63
+ Implement a linked list in C++
64
+
65
+ ### Assistant
66
+ ...
67
+ ```
68
+
69
+ <!-- prompt-template end -->
70
+
71
+
72
+ ## Bias, Risks, and Limitations
73
+
74
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
75
+ This model has undergone very limited testing. Additional safety testing should be performed before any real-world deployments.
76
+
77
+
78
+
79
+ ## Thanks
80
+
81
+ Thanks to:
82
+
83
+ - The Original Llama team
84
+ - [Phind](https://huggingface.co/phind)
85
+ - [uukuguy](https://huggingface.co/uukuguy)
86
+ - [jondurbin](https://huggingface.co/jondurbin)
87
+ - And everyone else who's involved in the Open Source AI/ML Community.
88
+