commit 906d3abc3596f7bf55f0b7e0ffbd1a0e6a011f2a Author: ModelHub XC Date: Mon Jun 15 08:14:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..08680d6 --- /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 +LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.IQ4_XS.gguf b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.IQ4_XS.gguf new file mode 100644 index 0000000..c058c54 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37474fe19303e2c48f256f8adfb4d9924db48d9eaf446bdaba4b7a69e2a06c05 +size 668620896 diff --git a/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q2_K.gguf b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q2_K.gguf new file mode 100644 index 0000000..956ef35 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec50ca5f81d667688da74ce3e7e334c4c3b6d34195488adaa6673483bd3388f6 +size 483399776 diff --git a/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_L.gguf b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_L.gguf new file mode 100644 index 0000000..afa85b4 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2ae13c0613909716e63a351ab821f35ef75bd2084c2f1ed602a9c7cdcf6ec7 +size 635476064 diff --git a/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_M.gguf b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_M.gguf new file mode 100644 index 0000000..562c9bb --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ea5b141e54b4db1768ef57550e45d548c92e49cb9f876227453ce92911193ed +size 600348768 diff --git a/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_S.gguf b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_S.gguf new file mode 100644 index 0000000..f9741ff --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0da8274af9569313587e6d8abc0596b01e2ca9d219b12b0c3042ee7f0b837528 +size 558159968 diff --git a/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q4_K_M.gguf b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q4_K_M.gguf new file mode 100644 index 0000000..2c3b8c0 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a678c4d6c8f2e9373fde183e26bf5f071d92b89fcd6035e3ce428d74c4356c8f +size 730896480 diff --git a/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q4_K_S.gguf b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q4_K_S.gguf new file mode 100644 index 0000000..205ee8e --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c29a8ba01dfb552f37f7af576778be7fba93eb8d3f994e514d0a64bc2ba9290 +size 700471392 diff --git a/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q5_K_M.gguf b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q5_K_M.gguf new file mode 100644 index 0000000..a476604 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf961cfb56a6371bb35b8e052702554c7b3ade4316a94b931c068c4cf0f6e05c +size 843356256 diff --git a/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q5_K_S.gguf b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q5_K_S.gguf new file mode 100644 index 0000000..43a64a9 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2d4fd8f7f9500e89f5c1fb91a4616c0ceea51028919198e8c67b9db770ccbbe +size 825251936 diff --git a/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q6_K.gguf b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q6_K.gguf new file mode 100644 index 0000000..07a9c2a --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bfff67cf0a5a1a6b793c66e0053df15642ccf1cae8a251b2a06429f647a788a +size 962844768 diff --git a/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q8_0.gguf b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q8_0.gguf new file mode 100644 index 0000000..df3e1be --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3ebc4f770aeca988e2b06b2b4b4ed4faf58ca04fc0541bb6c4f590396a1daf2 +size 1246255200 diff --git a/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.f16.gguf b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.f16.gguf new file mode 100644 index 0000000..ae550aa --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b013c2f36e52574a20dbd1452106e991abcc76cbf5a1d3bc89b254b9f7748ee +size 2343327840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..69fd263 --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: DavidAU/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL +datasets: +- TeichAI/kimi-k2-thinking-1000x +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- finetune +- All use cases +- bfloat16 +- creative +- creative writing +- fiction writing +- plot generation +- sub-plot generation +- fiction writing +- story generation +- scene continue +- storytelling +- fiction story +- science fiction +- romance +- all genres +- story +- writing +- vivid prosing +- vivid writing +- fiction +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DavidAU/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-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/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q2_K.gguf) | Q2_K | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Kimi-V2-DISTILL.f16.gguf) | f16 | 2.4 | 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. + +