Xin Liu commited on
Commit
517bb16
1 Parent(s): 495c907

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

Files changed (1) hide show
  1. README.md +47 -1
README.md CHANGED
@@ -1,3 +1,49 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: bigcode/starcoder2-7b
3
+ inference: false
4
+ license: bigcode-openrail-m
5
+ library_name: transformers
6
+ model_creator: bigcode
7
+ model_name: StarCoder2 7B
8
+ pipeline_tag: text-generation
9
+ quantized_by: Second State Inc.
10
+ tags:
11
+ - code
12
  ---
13
+
14
+ <!-- header start -->
15
+ <!-- 200823 -->
16
+ <div style="width: auto; margin-left: auto; margin-right: auto">
17
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
18
+ </div>
19
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
20
+ <!-- header end -->
21
+
22
+ # StarCoder2-7B-GGUF
23
+
24
+ ## Original Model
25
+
26
+ [bigcode/starcoder2-7b](https://huggingface.co/bigcode/starcoder2-7b)
27
+
28
+ ## Run with LlamaEdge
29
+
30
+ - LlamaEdge version: coming soon
31
+
32
+ ## Quantized GGUF Models
33
+
34
+ | Name | Quant method | Bits | Size | Use case |
35
+ | ---- | ---- | ---- | ---- | ----- |
36
+ | [starcoder2-7b-Q2_K.gguf](https://huggingface.co/second-state/StarCoder2-7B-GGUF/blob/main/starcoder2-7b-Q2_K.gguf) | Q2_K | 2 | 2.72 GB| smallest, significant quality loss - not recommended for most purposes |
37
+ | [starcoder2-7b-Q3_K_L.gguf](https://huggingface.co/second-state/StarCoder2-7B-GGUF/blob/main/starcoder2-7b-Q3_K_L.gguf) | Q3_K_L | 3 | 3.99 GB| small, substantial quality loss |
38
+ | [starcoder2-7b-Q3_K_M.gguf](https://huggingface.co/second-state/StarCoder2-7B-GGUF/blob/main/starcoder2-7b-Q3_K_M.gguf) | Q3_K_M | 3 | 3.59 GB| very small, high quality loss |
39
+ | [starcoder2-7b-Q3_K_S.gguf](https://huggingface.co/second-state/StarCoder2-7B-GGUF/blob/main/starcoder2-7b-Q3_K_S.gguf) | Q3_K_S | 3 | 3.09 GB| very small, high quality loss |
40
+ | [starcoder2-7b-Q4_0.gguf](https://huggingface.co/second-state/StarCoder2-7B-GGUF/blob/main/starcoder2-7b-Q4_0.gguf) | Q4_0 | 4 | 4.04 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
41
+ | [starcoder2-7b-Q4_K_M.gguf](https://huggingface.co/second-state/StarCoder2-7B-GGUF/blob/main/starcoder2-7b-Q4_K_M.gguf) | Q4_K_M | 4 | 4.4 GB| medium, balanced quality - recommended |
42
+ | [starcoder2-7b-Q4_K_S.gguf](https://huggingface.co/second-state/StarCoder2-7B-GGUF/blob/main/starcoder2-7b-Q4_K_S.gguf) | Q4_K_S | 4 | 4.13 GB| small, greater quality loss |
43
+ | [starcoder2-7b-Q5_0.gguf](https://huggingface.co/second-state/StarCoder2-7B-GGUF/blob/main/starcoder2-7b-Q5_0.gguf) | Q5_0 | 5 | 4.94 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
44
+ | [starcoder2-7b-Q5_K_M.gguf](https://huggingface.co/second-state/StarCoder2-7B-GGUF/blob/main/starcoder2-7b-Q5_K_M.gguf) | Q5_K_M | 5 | 5.12 GB| large, very low quality loss - recommended |
45
+ | [starcoder2-7b-Q5_K_S.gguf](https://huggingface.co/second-state/StarCoder2-7B-GGUF/blob/main/starcoder2-7b-Q5_K_S.gguf) | Q5_K_S | 5 | 4.94 GB| large, low quality loss - recommended |
46
+ | [starcoder2-7b-Q6_K.gguf](https://huggingface.co/second-state/StarCoder2-7B-GGUF/blob/main/starcoder2-7b-Q6_K.gguf) | Q6_K | 6 | 5.89 GB| very large, extremely low quality loss |
47
+ | [starcoder2-7b-Q8_0.gguf](https://huggingface.co/second-state/StarCoder2-7B-GGUF/blob/main/starcoder2-7b-Q8_0.gguf) | Q8_0 | 8 | 7.63 GB| very large, extremely low quality loss - not recommended |
48
+
49
+ *Quantized with llama.cpp b2308*