README.md
5.9 KB · 94 lines · markdown Raw
1 ---
2 base_model: DATEXIS/DeepICD-R1-zero-32B
3 language:
4 - en
5 library_name: transformers
6 license: other
7 mradermacher:
8 readme_rev: 1
9 quantized_by: mradermacher
10 tags:
11 - clinical-nlp
12 - medical-coding
13 - icd10
14 - icd-10-cm
15 - reasoning
16 - reinforcement-learning
17 - grpo
18 - healthcare
19 ---
20 ## About
21
22 <!-- ### quantize_version: 2 -->
23 <!-- ### output_tensor_quantised: 1 -->
24 <!-- ### convert_type: hf -->
25 <!-- ### vocab_type: -->
26 <!-- ### tags: nicoboss -->
27 <!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->
28 <!-- ### quants_skip: -->
29 <!-- ### skip_mmproj: -->
30 weighted/imatrix quants of https://huggingface.co/DATEXIS/DeepICD-R1-zero-32B
31
32 <!-- provided-files -->
33
34 ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepICD-R1-zero-32B-i1-GGUF).***
35
36 static quants are available at https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-GGUF
37 ## Usage
38
39 If you are unsure how to use GGUF files, refer to one of [TheBloke's
40 READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
41 more details, including on how to concatenate multi-part files.
42
43 ## Provided Quants
44
45 (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
46
47 | Link | Type | Size/GB | Notes |
48 |:-----|:-----|--------:|:------|
49 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |
50 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |
51 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
52 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
53 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
54 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | |
55 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
56 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
57 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
58 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
59 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
60 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
61 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* |
62 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
63 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
64 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
65 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
66 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
67 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
68 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
69 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | |
70 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
71 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
72 | [GGUF](https://huggingface.co/mradermacher/DeepICD-R1-zero-32B-i1-GGUF/resolve/main/DeepICD-R1-zero-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
73
74 Here is a handy graph by ikawrakow comparing some lower-quality quant
75 types (lower is better):
76
77 ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
78
79 And here are Artefact2's thoughts on the matter:
80 https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
81
82 ## FAQ / Model Request
83
84 See https://huggingface.co/mradermacher/model_requests for some answers to
85 questions you might have and/or if you want some other model quantized.
86
87 ## Thanks
88
89 I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
90 me use its servers and providing upgrades to my workstation to enable
91 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.
92
93 <!-- end -->
94