commit 8a224bb48e98248ff81abb8796164496603907c6 Author: ModelHub XC Date: Sat Apr 11 18:04:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Diagnose-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0b16b53 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Diagnose.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Diagnose.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Diagnose.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Diagnose.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Diagnose.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Diagnose.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Diagnose.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Diagnose.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Diagnose.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Diagnose.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Diagnose.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Diagnose.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Diagnose.IQ4_XS.gguf b/Qwen3-0.6B-Diagnose.IQ4_XS.gguf new file mode 100644 index 0000000..6ab524a --- /dev/null +++ b/Qwen3-0.6B-Diagnose.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:557f4f94e7907027146b580b0b70dc453549c13a73565358e03a7cada9749be0 +size 369279360 diff --git a/Qwen3-0.6B-Diagnose.Q2_K.gguf b/Qwen3-0.6B-Diagnose.Q2_K.gguf new file mode 100644 index 0000000..df83820 --- /dev/null +++ b/Qwen3-0.6B-Diagnose.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ceae07dc479beec1fe60c8e4df0ea843dd1284ca03af35c4c961661dab689d +size 296239488 diff --git a/Qwen3-0.6B-Diagnose.Q3_K_L.gguf b/Qwen3-0.6B-Diagnose.Q3_K_L.gguf new file mode 100644 index 0000000..3e0353e --- /dev/null +++ b/Qwen3-0.6B-Diagnose.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78dc4b94d8998fc9c83a9e89a2103ce7ce5d00a63fd46b7bb317f3be21fc3fac +size 368492928 diff --git a/Qwen3-0.6B-Diagnose.Q3_K_M.gguf b/Qwen3-0.6B-Diagnose.Q3_K_M.gguf new file mode 100644 index 0000000..3a5dca3 --- /dev/null +++ b/Qwen3-0.6B-Diagnose.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a8446b40fc270b2e6e2a5fda0539ceb8f2627a6fd0ef74004c95eb09577ff89 +size 347128192 diff --git a/Qwen3-0.6B-Diagnose.Q3_K_S.gguf b/Qwen3-0.6B-Diagnose.Q3_K_S.gguf new file mode 100644 index 0000000..56cef86 --- /dev/null +++ b/Qwen3-0.6B-Diagnose.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11bac1b2c42c79fba31666ac12eee37e71a02068de6544bb267ab4c41cfecd8e +size 323076480 diff --git a/Qwen3-0.6B-Diagnose.Q4_K_M.gguf b/Qwen3-0.6B-Diagnose.Q4_K_M.gguf new file mode 100644 index 0000000..6a109ad --- /dev/null +++ b/Qwen3-0.6B-Diagnose.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:249b403083cbba8f927bbb8ebce3d62d84a852a509fb59f369fc68c13c1ca0fb +size 396706176 diff --git a/Qwen3-0.6B-Diagnose.Q4_K_S.gguf b/Qwen3-0.6B-Diagnose.Q4_K_S.gguf new file mode 100644 index 0000000..5b486e9 --- /dev/null +++ b/Qwen3-0.6B-Diagnose.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c0f63fb82b5b5aa7232f10086a3144a67b20cafc2cb9273a0a2e80ba9ccefc3 +size 383271296 diff --git a/Qwen3-0.6B-Diagnose.Q5_K_M.gguf b/Qwen3-0.6B-Diagnose.Q5_K_M.gguf new file mode 100644 index 0000000..1e8bbbe --- /dev/null +++ b/Qwen3-0.6B-Diagnose.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f370f5e3298610346128d6bd6fb14f48a8466e67d98523f7360028f65c02c04 +size 444416384 diff --git a/Qwen3-0.6B-Diagnose.Q5_K_S.gguf b/Qwen3-0.6B-Diagnose.Q5_K_S.gguf new file mode 100644 index 0000000..5efda0f --- /dev/null +++ b/Qwen3-0.6B-Diagnose.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4db388cb59e449b6a51d7f491433c9d0721dd54edbc308182cc3de49714cd90 +size 436617600 diff --git a/Qwen3-0.6B-Diagnose.Q6_K.gguf b/Qwen3-0.6B-Diagnose.Q6_K.gguf new file mode 100644 index 0000000..62267dc --- /dev/null +++ b/Qwen3-0.6B-Diagnose.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b285d87b8d88700c4354a1f3730941a2621fd142a09303db06cb463048c36b +size 495108480 diff --git a/Qwen3-0.6B-Diagnose.Q8_0.gguf b/Qwen3-0.6B-Diagnose.Q8_0.gguf new file mode 100644 index 0000000..984e9e7 --- /dev/null +++ b/Qwen3-0.6B-Diagnose.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e080dc75a1fcbf9f7b00dd3cba18389d55160f7fed886b0142dcb696e006e22b +size 639448448 diff --git a/Qwen3-0.6B-Diagnose.f16.gguf b/Qwen3-0.6B-Diagnose.f16.gguf new file mode 100644 index 0000000..46706d8 --- /dev/null +++ b/Qwen3-0.6B-Diagnose.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f79fbea5ca5dccd25b61f8424d97642a3f8a9dde38db91396a5bcd6e5195823 +size 1198183808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f78f982 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: suayptalha/Qwen3-0.6B-Diagnose +datasets: +- suayptalha/Diagnose-Instructions +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/suayptalha/Qwen3-0.6B-Diagnose + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-Diagnose-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-GGUF/resolve/main/Qwen3-0.6B-Diagnose.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-GGUF/resolve/main/Qwen3-0.6B-Diagnose.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-GGUF/resolve/main/Qwen3-0.6B-Diagnose.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-GGUF/resolve/main/Qwen3-0.6B-Diagnose.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-GGUF/resolve/main/Qwen3-0.6B-Diagnose.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-GGUF/resolve/main/Qwen3-0.6B-Diagnose.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-GGUF/resolve/main/Qwen3-0.6B-Diagnose.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-GGUF/resolve/main/Qwen3-0.6B-Diagnose.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-GGUF/resolve/main/Qwen3-0.6B-Diagnose.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-GGUF/resolve/main/Qwen3-0.6B-Diagnose.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-GGUF/resolve/main/Qwen3-0.6B-Diagnose.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Diagnose-GGUF/resolve/main/Qwen3-0.6B-Diagnose.f16.gguf) | f16 | 1.3 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +