Transformers
GGUF
English
Inference Endpoints
imatrix
mradermacher commited on
Commit
50c5665
1 Parent(s): 44f9d0d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +70 -0
README.md CHANGED
@@ -1,6 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
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/SenseLLM/ReflectionCoder-CL-34B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: SenseLLM/ReflectionCoder-CL-34B
3
+ datasets:
4
+ - SenseLLM/ReflectionSeq-GPT
5
+ - SenseLLM/ReflectionSeq-DS
6
+ language:
7
+ - en
8
+ library_name: transformers
9
+ license: apache-2.0
10
+ quantized_by: mradermacher
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/SenseLLM/ReflectionCoder-CL-34B
20
+
21
+ <!-- provided-files -->
22
+ static quants are available at https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-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/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |
36
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
37
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.7 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.6 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-Q2_K.gguf) | i1-Q2_K | 12.6 | IQ3_XXS probably better |
42
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.1 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.0 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.7 | IQ3_XS probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.8 | beats Q3_K* |
46
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-IQ3_M.gguf) | i1-IQ3_M | 15.3 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.4 | IQ3_S probably better |
48
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.9 | IQ3_M probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.2 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-Q4_0.gguf) | i1-Q4_0 | 19.2 | fast, low quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 19.3 | optimal size/speed/quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.3 | fast, recommended |
53
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 23.3 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.9 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/ReflectionCoder-CL-34B-i1-GGUF/resolve/main/ReflectionCoder-CL-34B.i1-Q6_K.gguf) | i1-Q6_K | 27.8 | practically like static Q6_K |
56
+
57
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
58
+ types (lower is better):
59
+
60
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
61
+
62
+ And here are Artefact2's thoughts on the matter:
63
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
64
+
65
+ ## FAQ / Model Request
66
+
67
+ See https://huggingface.co/mradermacher/model_requests for some answers to
68
+ questions you might have and/or if you want some other model quantized.
69
+
70
+ ## Thanks
71
+
72
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
73
+ me use its servers and providing upgrades to my workstation to enable
74
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.
75
+
76
+ <!-- end -->