Hugging Face's logo

aitorrent
/
dolphin-2.9.3-qwen2-0.5b-GGUF-torrent

torrent
Model card Files Community
zerroug commited on
Commit
3e804bb
•
1 Parent(s): e85dcdd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -3
README.md CHANGED
@@ -1,3 +1,52 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - torrent
5
+ ---
6
+
7
+ ## About
8
+
9
+ <!-- ### quantize_version: 2 -->
10
+ <!-- ### output_tensor_quantised: 1 -->
11
+ <!-- ### convert_type: hf -->
12
+ <!-- ### vocab_type: -->
13
+ <!-- ### tags: -->
14
+ static quants of https://huggingface.co/cognitivecomputations/dolphin-2.9.3-qwen2-0.5b
15
+
16
+ <!-- provided-files -->
17
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-i1-GGUF
18
+ ## Usage
19
+
20
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
21
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
22
+ more details, including on how to concatenate multi-part files.
23
+
24
+ ## Provided Quants
25
+
26
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
27
+
28
+ | Link | Type | Size/GB | Notes |
29
+ |:-----|:-----|--------:|:------|
30
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.Q3_K_S.gguf) | Q3_K_S | 0.4 | |
31
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.IQ3_S.gguf) | IQ3_S | 0.4 | beats Q3_K* |
32
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.IQ3_XS.gguf) | IQ3_XS | 0.4 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.Q2_K.gguf) | Q2_K | 0.4 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.IQ3_M.gguf) | IQ3_M | 0.4 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.IQ4_XS.gguf) | IQ4_XS | 0.5 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality |
37
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.Q3_K_L.gguf) | Q3_K_L | 0.5 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended |
39
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended |
40
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.Q5_K_S.gguf) | Q5_K_S | 0.5 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.Q5_K_M.gguf) | Q5_K_M | 0.5 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.Q6_K.gguf) | Q6_K | 0.6 | very good quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-GGUF/resolve/main/dolphin-2.9.3-qwen2-0.5b.f16.gguf) | f16 | 1.1 | 16 bpw, overkill |
45
+
46
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
47
+ types (lower is better):
48
+
49
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
50
+
51
+ And here are Artefact2's thoughts on the matter:
52
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9