commit 8ca739a3bcab28e598ebfd8dee164288261dc9ce Author: ModelHub XC Date: Wed Jul 22 20:35:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cd5071e --- /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 +Qwen3-4B-Instruct-2507-NanoWriter-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-NanoWriter-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-NanoWriter-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-NanoWriter-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-NanoWriter-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-NanoWriter-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-NanoWriter-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-NanoWriter-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-NanoWriter-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Instruct-2507-NanoWriter-v2.IQ4_XS.gguf b/Qwen3-4B-Instruct-2507-NanoWriter-v2.IQ4_XS.gguf new file mode 100644 index 0000000..246b791 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-NanoWriter-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6572627dd59bd85df6a23dcdf700788bbb23a72f5000dfa14aa804d2549dbae1 +size 2286317728 diff --git a/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q2_K.gguf b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q2_K.gguf new file mode 100644 index 0000000..7c939a9 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b337d5ecc4d458c9fb055efe9875cfd279b14a1f9ed9942e3c408d8f588bbbd1 +size 1669501088 diff --git a/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_L.gguf b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_L.gguf new file mode 100644 index 0000000..1257085 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9775f51753ac593c1f92e49a3169bc19e750efa0abc30e724dc11dbb174723b8 +size 2239787168 diff --git a/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_M.gguf b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_M.gguf new file mode 100644 index 0000000..f0bfad4 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:267c81ad169c3a0c6f2dd61fd4418b8cc9d3b42f89cbe17a59377787f35db0ea +size 2075619488 diff --git a/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_S.gguf b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_S.gguf new file mode 100644 index 0000000..1988cc6 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9cee28bd1e411ad1303fa82353df4028aae58ade7d3c4ab0c7e374ef792983 +size 1886998688 diff --git a/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q4_K_M.gguf b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q4_K_M.gguf new file mode 100644 index 0000000..54bfe15 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a54755bc91715ac88b1cbb900ff246c6ce32a56eeace3bdb56884a23b30094bc +size 2497282208 diff --git a/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q4_K_S.gguf b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q4_K_S.gguf new file mode 100644 index 0000000..7197163 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44986cefa764736a2d8258caf008cdb495de63cf7361d427f9afd30e2adc551c +size 2383311008 diff --git a/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q5_K_M.gguf b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q5_K_M.gguf new file mode 100644 index 0000000..e33500c --- /dev/null +++ b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f1da41a86cbef135fe66d6df55696988bb383ec5a3f115afc41193ff354c0fe +size 2889515168 diff --git a/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q5_K_S.gguf b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q5_K_S.gguf new file mode 100644 index 0000000..8e2e884 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf3a448c73c73e33df96955bc74b32558d0816857fd7a2aedb17286f8c6b0754 +size 2823712928 diff --git a/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q6_K.gguf b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q6_K.gguf new file mode 100644 index 0000000..2242772 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:732a8abb69b493fbd0471eec6bdcf9dfccb049ebbeea78d77e69cebf4619eb5a +size 3306262688 diff --git a/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q8_0.gguf b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q8_0.gguf new file mode 100644 index 0000000..90c9cd1 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14f6e803c8b39c1f3f6ba11989cbea464dfd8bfa6fd449d4a35c638753471576 +size 4280406688 diff --git a/Qwen3-4B-Instruct-2507-NanoWriter-v2.f16.gguf b/Qwen3-4B-Instruct-2507-NanoWriter-v2.f16.gguf new file mode 100644 index 0000000..ee68f06 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-NanoWriter-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06db899606421d1b75e0987eaeb6b5cf4aa4911632749b30e8afd8586d5490ca +size 8051286688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dfe3eb7 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: 0xA50C1A1/Qwen3-4B-Instruct-2507-NanoWriter-v2 +datasets: +- Gryphe/Opus-WritingPrompts +- Gryphe/ChatGPT-4o-Writing-Prompts +- 0xA50C1A1/Storytelling-DPO +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +- heretic +- uncensored +- decensored +- abliterated +- creative-writing +- storytelling +- writing +--- +## About + + + + + + + + + +static quants of https://huggingface.co/0xA50C1A1/Qwen3-4B-Instruct-2507-NanoWriter-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-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/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF/resolve/main/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF/resolve/main/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF/resolve/main/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF/resolve/main/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF/resolve/main/Qwen3-4B-Instruct-2507-NanoWriter-v2.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF/resolve/main/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF/resolve/main/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF/resolve/main/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF/resolve/main/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF/resolve/main/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF/resolve/main/Qwen3-4B-Instruct-2507-NanoWriter-v2.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-NanoWriter-v2-GGUF/resolve/main/Qwen3-4B-Instruct-2507-NanoWriter-v2.f16.gguf) | f16 | 8.2 | 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. + +