mradermacher commited on
Commit
c9ce7fb
·
verified ·
1 Parent(s): dbb80ef

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +87 -0
README.md CHANGED
@@ -1,3 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
@@ -7,3 +30,67 @@
7
  <!-- ### quants_skip: -->
8
  <!-- ### skip_mmproj: -->
9
  weighted/imatrix quants of https://huggingface.co/lastmass/Qwen3_Medical_GRPO
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: lastmass/Qwen3_Medical_GRPO
3
+ datasets:
4
+ - FreedomIntelligence/medical-o1-reasoning-SFT
5
+ - lastmass/medical-o1-reasoning-SFT-keywords
6
+ language:
7
+ - en
8
+ - zh
9
+ library_name: transformers
10
+ license: apache-2.0
11
+ mradermacher:
12
+ readme_rev: 1
13
+ quantized_by: mradermacher
14
+ tags:
15
+ - text-generation-inference
16
+ - transformers
17
+ - unsloth
18
+ - qwen3
19
+ - vllm
20
+ - medical
21
+ ---
22
+ ## About
23
+
24
  <!-- ### quantize_version: 2 -->
25
  <!-- ### output_tensor_quantised: 1 -->
26
  <!-- ### convert_type: hf -->
 
30
  <!-- ### quants_skip: -->
31
  <!-- ### skip_mmproj: -->
32
  weighted/imatrix quants of https://huggingface.co/lastmass/Qwen3_Medical_GRPO
33
+
34
+ <!-- provided-files -->
35
+
36
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3_Medical_GRPO-i1-GGUF).***
37
+
38
+ static quants are available at https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-GGUF
39
+ ## Usage
40
+
41
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
42
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
43
+ more details, including on how to concatenate multi-part files.
44
+
45
+ ## Provided Quants
46
+
47
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
48
+
49
+ | Link | Type | Size/GB | Notes |
50
+ |:-----|:-----|--------:|:------|
51
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
52
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate |
53
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate |
54
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality |
59
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better |
60
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality |
61
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better |
63
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* |
64
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better |
66
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better |
67
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | |
68
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality |
69
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS |
70
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality |
71
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended |
72
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | |
73
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | |
74
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | |
75
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3_Medical_GRPO-i1-GGUF/resolve/main/Qwen3_Medical_GRPO.i1-Q6_K.gguf) | i1-Q6_K | 3.4 | practically like static Q6_K |
76
+
77
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
78
+ types (lower is better):
79
+
80
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
81
+
82
+ And here are Artefact2's thoughts on the matter:
83
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
84
+
85
+ ## FAQ / Model Request
86
+
87
+ See https://huggingface.co/mradermacher/model_requests for some answers to
88
+ questions you might have and/or if you want some other model quantized.
89
+
90
+ ## Thanks
91
+
92
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
93
+ me use its servers and providing upgrades to my workstation to enable
94
+ 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.
95
+
96
+ <!-- end -->