commit 4591866eab9238fb3e83609e88f603f7676da812 Author: ModelHub XC Date: Sat Apr 11 06:37:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Reasoning-SmolLM2-135M-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..28ee94c --- /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 +Reasoning-SmolLM2-135M.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-SmolLM2-135M.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-SmolLM2-135M.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-SmolLM2-135M.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-SmolLM2-135M.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-SmolLM2-135M.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-SmolLM2-135M.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-SmolLM2-135M.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-SmolLM2-135M.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-SmolLM2-135M.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-SmolLM2-135M.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-SmolLM2-135M.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d8125df --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: prithivMLmods/Reasoning-SmolLM2-135M +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- trl +- smolLM +- llama +- CoT +- Thinker +- LlamaForCausalLM +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Reasoning-SmolLM2-135M + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Reasoning-SmolLM2-135M-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/Reasoning-SmolLM2-135M-GGUF/resolve/main/Reasoning-SmolLM2-135M.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-SmolLM2-135M-GGUF/resolve/main/Reasoning-SmolLM2-135M.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-SmolLM2-135M-GGUF/resolve/main/Reasoning-SmolLM2-135M.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-SmolLM2-135M-GGUF/resolve/main/Reasoning-SmolLM2-135M.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-SmolLM2-135M-GGUF/resolve/main/Reasoning-SmolLM2-135M.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-SmolLM2-135M-GGUF/resolve/main/Reasoning-SmolLM2-135M.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-SmolLM2-135M-GGUF/resolve/main/Reasoning-SmolLM2-135M.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-SmolLM2-135M-GGUF/resolve/main/Reasoning-SmolLM2-135M.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-SmolLM2-135M-GGUF/resolve/main/Reasoning-SmolLM2-135M.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-SmolLM2-135M-GGUF/resolve/main/Reasoning-SmolLM2-135M.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-SmolLM2-135M-GGUF/resolve/main/Reasoning-SmolLM2-135M.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-SmolLM2-135M-GGUF/resolve/main/Reasoning-SmolLM2-135M.f16.gguf) | f16 | 0.4 | 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. + + diff --git a/Reasoning-SmolLM2-135M.IQ4_XS.gguf b/Reasoning-SmolLM2-135M.IQ4_XS.gguf new file mode 100644 index 0000000..10409b0 --- /dev/null +++ b/Reasoning-SmolLM2-135M.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b55b4d0fa17a9ac4d117bff163f90fcea922aab9de7a5f52140639d516ab1c +size 91312992 diff --git a/Reasoning-SmolLM2-135M.Q2_K.gguf b/Reasoning-SmolLM2-135M.Q2_K.gguf new file mode 100644 index 0000000..d44f1b2 --- /dev/null +++ b/Reasoning-SmolLM2-135M.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cad438c189a95b3bff8102d1276cb32af99898fff8d446a425ad97f8a0d6969c +size 88202592 diff --git a/Reasoning-SmolLM2-135M.Q3_K_L.gguf b/Reasoning-SmolLM2-135M.Q3_K_L.gguf new file mode 100644 index 0000000..8332a44 --- /dev/null +++ b/Reasoning-SmolLM2-135M.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40fb7e52065c5405fe37f80f293f422f93cc026d882e03eb51fb4d8070588a77 +size 97533792 diff --git a/Reasoning-SmolLM2-135M.Q3_K_M.gguf b/Reasoning-SmolLM2-135M.Q3_K_M.gguf new file mode 100644 index 0000000..5da039a --- /dev/null +++ b/Reasoning-SmolLM2-135M.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f778ba145bb3c400f490360a03098fa6f8010a9a95643a83aa721393db884d5 +size 93511008 diff --git a/Reasoning-SmolLM2-135M.Q3_K_S.gguf b/Reasoning-SmolLM2-135M.Q3_K_S.gguf new file mode 100644 index 0000000..956c4df --- /dev/null +++ b/Reasoning-SmolLM2-135M.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4431ad0e26648c1f7b39064f4eb1d173833e33b33f6c1c364bddae5bd53f20ba +size 88202592 diff --git a/Reasoning-SmolLM2-135M.Q4_K_M.gguf b/Reasoning-SmolLM2-135M.Q4_K_M.gguf new file mode 100644 index 0000000..617c13c --- /dev/null +++ b/Reasoning-SmolLM2-135M.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:add79a43c03abd084c89c9b125965814ef9c561afa2ba7339e0a9f1fbb44502d +size 105454944 diff --git a/Reasoning-SmolLM2-135M.Q4_K_S.gguf b/Reasoning-SmolLM2-135M.Q4_K_S.gguf new file mode 100644 index 0000000..603b18f --- /dev/null +++ b/Reasoning-SmolLM2-135M.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99e63ef9f44d5f95ffadb445ba08b1f671978a8fdac298406236d45205f4bf42 +size 102040416 diff --git a/Reasoning-SmolLM2-135M.Q5_K_M.gguf b/Reasoning-SmolLM2-135M.Q5_K_M.gguf new file mode 100644 index 0000000..c2c61e0 --- /dev/null +++ b/Reasoning-SmolLM2-135M.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d05f5ed103bff89bac5ce5001c3054c9b6064461bc1f68659288c4b3d4cf2ac +size 112104288 diff --git a/Reasoning-SmolLM2-135M.Q5_K_S.gguf b/Reasoning-SmolLM2-135M.Q5_K_S.gguf new file mode 100644 index 0000000..63a81e1 --- /dev/null +++ b/Reasoning-SmolLM2-135M.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2285e73e389a402a08a53beb873e73a78d13f17a8fdec47fb1bd236befccf8 +size 109975392 diff --git a/Reasoning-SmolLM2-135M.Q6_K.gguf b/Reasoning-SmolLM2-135M.Q6_K.gguf new file mode 100644 index 0000000..ea27c2c --- /dev/null +++ b/Reasoning-SmolLM2-135M.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ee6c4a40993a8eb56f8ba06b8e1e1b87b5d4e679ce0d267f1db614bdc4d725 +size 138383712 diff --git a/Reasoning-SmolLM2-135M.Q8_0.gguf b/Reasoning-SmolLM2-135M.Q8_0.gguf new file mode 100644 index 0000000..2aa11ee --- /dev/null +++ b/Reasoning-SmolLM2-135M.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:756f21967e924798a0331d719e4d3404f62145e5050c6d5d0f7149b259adadcf +size 144811872 diff --git a/Reasoning-SmolLM2-135M.f16.gguf b/Reasoning-SmolLM2-135M.f16.gguf new file mode 100644 index 0000000..a1c9a99 --- /dev/null +++ b/Reasoning-SmolLM2-135M.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83c3d1fb66020f84d68448b5bcb0f6d11dc83213abf0a7bf807dd143c67f5458 +size 270886752