commit 2561157d6d43e95328817a4d1188e58a7db4dd82 Author: ModelHub XC Date: Tue Sep 1 15:30:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Avtrkrb/SmolLM2-135M-Instruct-bnb-4bit-reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3340fe1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,41 @@ +*.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 +SmolLM2-135M-Instruct-bnb-4bit-reasoning-F16.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6861718 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +license: apache-2.0 +language: + - en +pipeline_tag: text-generation + +base_model: Avtrkrb/SmolLM2-135M-Instruct-bnb-4bit-reasoning + +tags: + +- gguf +- llama.cpp +- ollama +- reasoning +- smollm2 +--- + +# SmolLM2-135M-Instruct-Reasoning-GGUF + +GGUF conversions of: + +Avtrkrb/SmolLM2-135M-Instruct-bnb-4bit-reasoning + +## Available Quantizations + +| Quantization | Recommended Use | +| ------------ | --------------------------------- | +| Q4_0 | Same as Q4_K_M | +| Q4_K_M | Best balance of quality and size | +| Q5_K_M | Better quality | +| Q6_K | Better quaity smaller than Q8_0 | +| Q8_0 | Highest quality quantized version | + +## Chat Template + +This model uses the standard SmolLM2 chat template. + +<|im_start|>system +You are a helpful AI assistant named SmolLM, trained by Hugging Face +<|im_end|> + +<|im_start|>user +Hello +<|im_end|> + +<|im_start|>assistant + +## Ollama Example + +FROM ./SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q4_K_M.gguf + +TEMPLATE """ +{{ .Prompt }} +""" + +## llama.cpp Example + +./llama-cli +-m SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q4_K_M.gguf + +## Notes + +When using GGUF versions, ensure the same chat template used during training is applied during inference. Incorrect templates can significantly reduce model quality. + +## Source Model + +Avtrkrb/SmolLM2-135M-Instruct-bnb-4bit-reasoning diff --git a/SmolLM2-135M-Instruct-bnb-4bit-reasoning-F16.gguf b/SmolLM2-135M-Instruct-bnb-4bit-reasoning-F16.gguf new file mode 100644 index 0000000..e79a70b --- /dev/null +++ b/SmolLM2-135M-Instruct-bnb-4bit-reasoning-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3783f6e2d45a8f45506217072083dee9ec08cb921e851d3308544bf54f11ec5a +size 270886560 diff --git a/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q4_0.gguf b/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q4_0.gguf new file mode 100644 index 0000000..f28e8a1 --- /dev/null +++ b/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed5997f104b77e00956bc74f07b1b4a8871dfd4647c864faa86ca274334c4ec8 +size 91727520 diff --git a/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q4_K_M.gguf b/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q4_K_M.gguf new file mode 100644 index 0000000..301c9c2 --- /dev/null +++ b/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc27bea3b2caf096f68ac9b448c0180e74be33eabb97c9eddb31369aa92dff4 +size 105454752 diff --git a/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q5_K_M.gguf b/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q5_K_M.gguf new file mode 100644 index 0000000..55620a2 --- /dev/null +++ b/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaa0c9a09e5e30b96995a6d711b2becae824c1e1c54b481204cb3ba04b1ddd50 +size 112104096 diff --git a/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q6_K.gguf b/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q6_K.gguf new file mode 100644 index 0000000..31e29f3 --- /dev/null +++ b/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2e94a8c706e964b6d856f2118340272fa25f23e68568d4674521fbd36faf9f +size 138383520 diff --git a/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q8_0.gguf b/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q8_0.gguf new file mode 100644 index 0000000..02cdc10 --- /dev/null +++ b/SmolLM2-135M-Instruct-bnb-4bit-reasoning-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5877814662990412a42e5f5bea337bf397b36290d88c302ef7e0bca2020532c +size 144811680