Zack Zhiyuan Li commited on
Commit
ad56bbf
1 Parent(s): c103f91
Files changed (1) hide show
  1. README.md +22 -10
README.md CHANGED
@@ -2,22 +2,36 @@
2
  language:
3
  - en
4
  license: apache-2.0
5
- model_name: Octopus-V2-2B
6
  base_model: NexaAIDev/Octopus-v4
7
  inference: false
8
  model_creator: NexaAIDev
9
- quantized_by: Second State Inc.
10
  tags:
11
  - function calling
12
  - on-device language model
13
- - android
 
14
  ---
15
 
16
- # Octopus-v4-GGUF
17
 
18
- ## Original Model
19
 
20
- [NexaAIDev/Octopus-v4](https://huggingface.co/NexaAIDev/Octopus-v4)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
 
22
  ## Run with [Ollama](https://github.com/ollama/ollama)
23
 
@@ -30,10 +44,10 @@ Input example:
30
  ```json
31
  Query: Tell me the result of derivative of x^3 when x is 2?
32
 
33
- # <nexa_4> represents the math gpt.
34
  Response: <nexa_4> ('Determine the derivative of the function f(x) = x^3 at the point where x equals 2, and interpret the result within the context of rate of change and tangent slope.')<nexa_end>
35
 
36
  ```
 
37
 
38
  ### Dataset and Benchmark
39
 
@@ -65,6 +79,4 @@ Response: <nexa_4> ('Determine the derivative of the function f(x) = x^3 at the
65
  | Octopus-v4-Q8_0.gguf | Q8_0 | 8 | 3.78 GB | 50.10 | very large, good quality |
66
  | Octopus-v4-f16.gguf | f16 | 16 | 7.20 GB | 30.61 | extremely large |
67
 
68
- _Quantized with llama.cpp_
69
-
70
-
 
2
  language:
3
  - en
4
  license: apache-2.0
5
+ model_name: Octopus-V4-GGUF
6
  base_model: NexaAIDev/Octopus-v4
7
  inference: false
8
  model_creator: NexaAIDev
9
+ quantized_by: Nexa AI, Inc.
10
  tags:
11
  - function calling
12
  - on-device language model
13
+ - gguf
14
+ - llama cpp
15
  ---
16
 
17
+ # Octopus V4-GGUF: Graph of language models
18
 
 
19
 
20
+ <p align="center">
21
+ - <a href="https://huggingface.co/NexaAIDev/Octopus-v4" target="_blank">Original Model</a>
22
+ - <a href="https://www.nexa4ai.com/" target="_blank">Nexa AI Website</a>
23
+ - <a href="https://github.com/NexaAI/octopus-v4" target="_blank">Octopus-v4 Github</a>
24
+ - <a href="https://arxiv.org/abs/2404.19296" target="_blank">ArXiv</a>
25
+ - <a href="https://huggingface.co/spaces/NexaAIDev/domain_llm_leaderboard" target="_blank">Domain LLM Leaderbaord</a>
26
+ </p>
27
+
28
+ <p align="center" width="100%">
29
+ <a><img src="octopus-v4-logo.png" alt="nexa-octopus" style="width: 40%; min-width: 300px; display: block; margin: auto;"></a>
30
+ </p>
31
+
32
+ **Acknowledgement**:
33
+ We sincerely thank our community members, [ThunderBeee](https://huggingface.co/ThunderBeee) and [ZY6](https://huggingface.co/ZY6), for their extraordinary contributions to this quantization effort. Please explore [Octopus-v4](https://huggingface.co/NexaAIDev/Octopus-v4) for our original huggingface model.
34
+
35
 
36
  ## Run with [Ollama](https://github.com/ollama/ollama)
37
 
 
44
  ```json
45
  Query: Tell me the result of derivative of x^3 when x is 2?
46
 
 
47
  Response: <nexa_4> ('Determine the derivative of the function f(x) = x^3 at the point where x equals 2, and interpret the result within the context of rate of change and tangent slope.')<nexa_end>
48
 
49
  ```
50
+ Note that `<nexa_4>` represents the math gpt.
51
 
52
  ### Dataset and Benchmark
53
 
 
79
  | Octopus-v4-Q8_0.gguf | Q8_0 | 8 | 3.78 GB | 50.10 | very large, good quality |
80
  | Octopus-v4-f16.gguf | f16 | 16 | 7.20 GB | 30.61 | extremely large |
81
 
82
+ _Quantized with llama.cpp_