mradermacher commited on
Commit
0785a4c
·
verified ·
1 Parent(s): ca23e3a

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +69 -0
README.md CHANGED
@@ -1,6 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: -->
6
  static quants of https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-15b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: cognitivecomputations/dolphincoder-starcoder2-15b
3
+ datasets:
4
+ - cognitivecomputations/dolphin
5
+ - jondurbin/airoboros-2.2.1
6
+ - cognitivecomputations/dolphin-coder
7
+ - teknium/openhermes
8
+ - ise-uiuc/Magicoder-OSS-Instruct-75K
9
+ - ise-uiuc/Magicoder-Evol-Instruct-110K
10
+ - m-a-p/Code-Feedback
11
+ - m-a-p/CodeFeedback-Filtered-Instruction
12
+ language:
13
+ - en
14
+ library_name: transformers
15
+ license: bigcode-openrail-m
16
+ quantized_by: mradermacher
17
+ ---
18
+ ## About
19
+
20
  <!-- ### quantize_version: 2 -->
21
  <!-- ### output_tensor_quantised: 1 -->
22
  <!-- ### convert_type: hf -->
23
  <!-- ### vocab_type: -->
24
  <!-- ### tags: -->
25
  static quants of https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-15b
26
+
27
+ <!-- provided-files -->
28
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-i1-GGUF
29
+ ## Usage
30
+
31
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
32
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
33
+ more details, including on how to concatenate multi-part files.
34
+
35
+ ## Provided Quants
36
+
37
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
38
+
39
+ | Link | Type | Size/GB | Notes |
40
+ |:-----|:-----|--------:|:------|
41
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.Q2_K.gguf) | Q2_K | 6.3 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.IQ3_XS.gguf) | IQ3_XS | 6.8 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.Q3_K_S.gguf) | Q3_K_S | 7.1 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.IQ3_S.gguf) | IQ3_S | 7.1 | beats Q3_K* |
45
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.IQ3_M.gguf) | IQ3_M | 7.4 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.Q3_K_M.gguf) | Q3_K_M | 8.1 | lower quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.IQ4_XS.gguf) | IQ4_XS | 8.8 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.Q3_K_L.gguf) | Q3_K_L | 9.1 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.Q4_K_S.gguf) | Q4_K_S | 9.3 | fast, recommended |
50
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.Q4_K_M.gguf) | Q4_K_M | 10.0 | fast, recommended |
51
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.Q5_K_S.gguf) | Q5_K_S | 11.1 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.Q5_K_M.gguf) | Q5_K_M | 11.5 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.Q6_K.gguf) | Q6_K | 13.2 | very good quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/dolphincoder-starcoder2-15b-GGUF/resolve/main/dolphincoder-starcoder2-15b.Q8_0.gguf) | Q8_0 | 17.1 | fast, best quality |
55
+
56
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
57
+ types (lower is better):
58
+
59
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
60
+
61
+ And here are Artefact2's thoughts on the matter:
62
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
63
+
64
+ ## FAQ / Model Request
65
+
66
+ See https://huggingface.co/mradermacher/model_requests for some answers to
67
+ questions you might have and/or if you want some other model quantized.
68
+
69
+ ## Thanks
70
+
71
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
72
+ me use its servers and providing upgrades to my workstation to enable
73
+ this work in my free time.
74
+
75
+ <!-- end -->