Hugging Face's logo

second-state
/
CodeLlama-13B-Instruct-GGUF

Text Generation
Transformers
GGUF
code
llama
llama-2
text-generation-inference
Model card Files Community
Xin Liu commited on
Commit
060d0c9
•
1 Parent(s): d428853

Update

Browse files

Signed-off-by: Xin Liu <sam@secondstate.io>

Files changed (1) hide show
  1. README.md +64 -6
README.md CHANGED
@@ -1,9 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  # CodeLlama-13B-Instruct
2
 
3
- ## Prompt Template
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
 
5
- ```text
6
- [INST] Write code to solve the following coding problem that obeys the constraints and passes the example test cases. Please wrap your code answer using ```:
7
- {prompt}
8
- [/INST]
9
- ```
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - code
4
+ license: llama2
5
+ tags:
6
+ - llama-2
7
+ model_name: CodeLlama 13B Instruct
8
+ base_model: codellama/CodeLlama-13b-Instruct-hf
9
+ inference: false
10
+ model_creator: Meta
11
+ model_type: llama
12
+ pipeline_tag: text-generation
13
+ quantized_by: Second State Inc.
14
+ ---
15
+
16
+ <!-- header start -->
17
+ <!-- 200823 -->
18
+ <div style="width: auto; margin-left: auto; margin-right: auto">
19
+ <img src="https://github.com/second-state/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
20
+ </div>
21
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
22
+ <!-- header end -->
23
+
24
  # CodeLlama-13B-Instruct
25
 
26
+ ## Original Model
27
+
28
+ [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf)
29
+
30
+ ## Run with LlamaEdge
31
+
32
+ - LlamaEdge version: [v0.2.4](https://github.com/second-state/LlamaEdge/releases/tag/0.2.4)
33
+
34
+ - Prompt template
35
+
36
+ - Prompt type: `codellama-instruct`
37
+
38
+ - Prompt string
39
+
40
+ ```text
41
+ [INST] Write code to solve the following coding problem that obeys the constraints and passes the example test cases. Please wrap your code answer using ```:
42
+ {prompt}
43
+ [/INST]
44
+ ```
45
+
46
+ - Run as LlamaEdge command app
47
+
48
+ ```bash
49
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:codellama-13b-instruct.Q4_0.gguf llama-chat.wasm -p codellama-instruct
50
+ ```
51
+
52
+ ## Quantized GGUF Models
53
 
54
+ | Name | Quant method | Bits | Size | Use case |
55
+ | ---- | ---- | ---- | ---- | ----- |
56
+ | [CodeLlama-13b-Instruct-hf-Q2_K.gguf](https://huggingface.co/second-state/CodeLlama-13B-Instruct-GGUF/blob/main/CodeLlama-13b-Instruct-hf-Q2_K.gguf) | Q2_K | 2 | 5.43 GB| smallest, significant quality loss - not recommended for most purposes |
57
+ | [CodeLlama-13b-Instruct-hf-Q3_K_L.gguf](https://huggingface.co/second-state/CodeLlama-13B-Instruct-GGUF/blob/main/CodeLlama-13b-Instruct-hf-Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| small, substantial quality loss |
58
+ | [CodeLlama-13b-Instruct-hf-Q3_K_M.gguf](https://huggingface.co/second-state/CodeLlama-13B-Instruct-GGUF/blob/main/CodeLlama-13b-Instruct-hf-Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| very small, high quality loss |
59
+ | [CodeLlama-13b-Instruct-hf-Q3_K_S.gguf](https://huggingface.co/second-state/CodeLlama-13B-Instruct-GGUF/blob/main/CodeLlama-13b-Instruct-hf-Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| very small, high quality loss |
60
+ | [CodeLlama-13b-Instruct-hf-Q4_0.gguf](https://huggingface.co/second-state/CodeLlama-13B-Instruct-GGUF/blob/main/CodeLlama-13b-Instruct-hf-Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
61
+ | [CodeLlama-13b-Instruct-hf-Q4_K_M.gguf](https://huggingface.co/second-state/CodeLlama-13B-Instruct-GGUF/blob/main/CodeLlama-13b-Instruct-hf-Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| medium, balanced quality - recommended |
62
+ | [CodeLlama-13b-Instruct-hf-Q4_K_S.gguf](https://huggingface.co/second-state/CodeLlama-13B-Instruct-GGUF/blob/main/CodeLlama-13b-Instruct-hf-Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| small, greater quality loss |
63
+ | [CodeLlama-13b-Instruct-hf-Q5_0.gguf](https://huggingface.co/second-state/CodeLlama-13B-Instruct-GGUF/blob/main/CodeLlama-13b-Instruct-hf-Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
64
+ | [CodeLlama-13b-Instruct-hf-Q5_K_M.gguf](https://huggingface.co/second-state/CodeLlama-13B-Instruct-GGUF/blob/main/CodeLlama-13b-Instruct-hf-Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| large, very low quality loss - recommended |
65
+ | [CodeLlama-13b-Instruct-hf-Q5_K_S.gguf](https://huggingface.co/second-state/CodeLlama-13B-Instruct-GGUF/blob/main/CodeLlama-13b-Instruct-hf-Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| large, low quality loss - recommended |
66
+ | [CodeLlama-13b-Instruct-hf-Q6_K.gguf](https://huggingface.co/second-state/CodeLlama-13B-Instruct-GGUF/blob/main/CodeLlama-13b-Instruct-hf-Q6_K.gguf) | Q6_K | 6 | 10.7 GB| very large, extremely low quality loss |
67
+ | [CodeLlama-13b-Instruct-hf-Q8_0.gguf](https://huggingface.co/second-state/CodeLlama-13B-Instruct-GGUF/blob/main/CodeLlama-13b-Instruct-hf-Q8_0.gguf) | Q8_0 | 8 | 13.8 GB| very large, extremely low quality loss - not recommended |