mradermacher commited on
Commit
e433e66
1 Parent(s): d8ee677

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +64 -0
README.md CHANGED
@@ -1,6 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: nicoboss -->
6
  weighted/imatrix quants of https://huggingface.co/zzzmahesh/starcoder2-3b-instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: zzzmahesh/starcoder2-3b-instruct
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: bigcode-openrail-m
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - code
10
+ - starcoder2
11
+ ---
12
+ ## About
13
+
14
  <!-- ### quantize_version: 2 -->
15
  <!-- ### output_tensor_quantised: 1 -->
16
  <!-- ### convert_type: hf -->
17
  <!-- ### vocab_type: -->
18
  <!-- ### tags: nicoboss -->
19
  weighted/imatrix quants of https://huggingface.co/zzzmahesh/starcoder2-3b-instruct
20
+
21
+ <!-- provided-files -->
22
+ static quants are available at https://huggingface.co/mradermacher/starcoder2-3b-instruct-GGUF
23
+ ## Usage
24
+
25
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
26
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
27
+ more details, including on how to concatenate multi-part files.
28
+
29
+ ## Provided Quants
30
+
31
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
32
+
33
+ | Link | Type | Size/GB | Notes |
34
+ |:-----|:-----|--------:|:------|
35
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 0.9 | mostly desperate |
36
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.2 | very low quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.3 | lower quality |
41
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 1.3 | IQ3_XXS probably better |
42
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.5 | IQ3_XS probably better |
43
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 1.5 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.7 | IQ3_S probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.8 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.8 | IQ3_M probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.0 | fast, recommended |
49
+ | [GGUF](https://huggingface.co/mradermacher/starcoder2-3b-instruct-i1-GGUF/resolve/main/starcoder2-3b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 2.6 | practically like static Q6_K |
50
+
51
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
52
+ types (lower is better):
53
+
54
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
55
+
56
+ And here are Artefact2's thoughts on the matter:
57
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
58
+
59
+ ## FAQ / Model Request
60
+
61
+ See https://huggingface.co/mradermacher/model_requests for some answers to
62
+ questions you might have and/or if you want some other model quantized.
63
+
64
+ ## Thanks
65
+
66
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
67
+ me use its servers and providing upgrades to my workstation to enable
68
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
69
+
70
+ <!-- end -->