ZeroFLN commited on
Commit
004531b
1 Parent(s): 91c41f4

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +66 -0
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Sao10K/L3-8B-Niitama-v1
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ quantized_by: mradermacher
7
+ ---
8
+ ## About
9
+
10
+ <!-- ### quantize_version: 2 -->
11
+ <!-- ### output_tensor_quantised: 1 -->
12
+ <!-- ### convert_type: hf -->
13
+ <!-- ### vocab_type: -->
14
+ <!-- ### tags: -->
15
+ static quants of https://huggingface.co/Sao10K/L3-8B-Niitama-v1
16
+
17
+ <!-- provided-files -->
18
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3-8B-Niitama-v1-i1-GGUF
19
+ ## Usage
20
+
21
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
22
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
23
+ more details, including on how to concatenate multi-part files.
24
+
25
+ ## Provided Quants
26
+
27
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
28
+
29
+ | Link | Type | Size/GB | Notes |
30
+ |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.Q2_K.gguf) | Q2_K | 3.3 | |
32
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
35
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.IQ3_M.gguf) | IQ3_M | 3.9 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
37
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
40
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Niitama-v1-GGUF/resolve/main/L3-8B-Niitama-v1.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
46
+
47
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
48
+ types (lower is better):
49
+
50
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
51
+
52
+ And here are Artefact2's thoughts on the matter:
53
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
54
+
55
+ ## FAQ / Model Request
56
+
57
+ See https://huggingface.co/mradermacher/model_requests for some answers to
58
+ questions you might have and/or if you want some other model quantized.
59
+
60
+ ## Thanks
61
+
62
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
63
+ me use its servers and providing upgrades to my workstation to enable
64
+ this work in my free time.
65
+
66
+ <!-- end -->