commit 0778b3a0551c3d54c88981727d6c4d45ac2e228b Author: ModelHub XC Date: Fri Jun 19 12:27:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/SmolLM2-1.7B-F32-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /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 +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..982923e --- /dev/null +++ b/README.md @@ -0,0 +1,42 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- HuggingFaceTB/SmolLM2-1.7B-Instruct +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +--- + +# **SmolLM2-1.7B-Instruct-GGUF** + +> [SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct) : The 1.7B variant demonstrates significant advances over its predecessor SmolLM1-1.7B, particularly in instruction following, knowledge, reasoning, and mathematics. It was trained on 11 trillion tokens using a diverse dataset combination: FineWeb-Edu, DCLM, The Stack, along with new mathematics and coding datasets that we curated and will release soon. We developed the instruct version through supervised fine-tuning (SFT) using a combination of public datasets and our own curated datasets. We then applied Direct Preference Optimization (DPO) using UltraFeedback. + +## Model Files + +| File Name | Size | Format Description | +|-----------|------|-------------------| +| SmolLM2-1.7B-Instruct.F32.gguf | 6.85 GB | Full precision (32-bit floating point) | +| SmolLM2-1.7B-Instruct.BF16.gguf | 3.42 GB | Brain floating point 16-bit | +| SmolLM2-1.7B-Instruct.F16.gguf | 3.42 GB | Half precision (16-bit floating point) | +| SmolLM2-1.7B-Instruct.Q8_0.gguf | 1.82 GB | 8-bit quantization | +| SmolLM2-1.7B-Instruct.Q6_K.gguf | 1.41 GB | 6-bit quantization (K-quant) | +| SmolLM2-1.7B-Instruct.Q5_K_M.gguf | 1.23 GB | 5-bit quantization (K-quant, medium) | +| SmolLM2-1.7B-Instruct.Q5_K_S.gguf | 1.19 GB | 5-bit quantization (K-quant, small) | +| SmolLM2-1.7B-Instruct.Q4_K_M.gguf | 1.06 GB | 4-bit quantization (K-quant, medium) | +| SmolLM2-1.7B-Instruct.Q4_K_S.gguf | 999 MB | 4-bit quantization (K-quant, small) | +| SmolLM2-1.7B-Instruct.Q3_K_L.gguf | 933 MB | 3-bit quantization (K-quant, large) | +| SmolLM2-1.7B-Instruct.Q3_K_M.gguf | 860 MB | 3-bit quantization (K-quant, medium) | +| SmolLM2-1.7B-Instruct.Q3_K_S.gguf | 777 MB | 3-bit quantization (K-quant, small) | +| SmolLM2-1.7B-Instruct.Q2_K.gguf | 675 MB | 2-bit quantization (K-quant) | + +## Quants Usage + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +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) \ No newline at end of file diff --git a/SmolLM2-1.7B-Instruct.BF16.gguf b/SmolLM2-1.7B-Instruct.BF16.gguf new file mode 100644 index 0000000..fff4bcd --- /dev/null +++ b/SmolLM2-1.7B-Instruct.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ee350980bbbdc8b43dfe33348063f55423caee69c11daddc6e43fcd24aafbb0 +size 3424735744 diff --git a/SmolLM2-1.7B-Instruct.F16.gguf b/SmolLM2-1.7B-Instruct.F16.gguf new file mode 100644 index 0000000..36be06a --- /dev/null +++ b/SmolLM2-1.7B-Instruct.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a60a7dd9cd76a3764d693aae2b2843dd69dbffe70590ceb359b264931ba498 +size 3424735744 diff --git a/SmolLM2-1.7B-Instruct.F32.gguf b/SmolLM2-1.7B-Instruct.F32.gguf new file mode 100644 index 0000000..4b485ab --- /dev/null +++ b/SmolLM2-1.7B-Instruct.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fd0697f219fefbceda6976e177bd719bdde76e0cba8f2abf7c7655b95e3b75a +size 6847287808 diff --git a/SmolLM2-1.7B-Instruct.Q2_K.gguf b/SmolLM2-1.7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..4e1cacb --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef150aa647504ed15fc774eaecb86880bc510a1336ffd0d28e7f8f3f1d3893e3 +size 674583040 diff --git a/SmolLM2-1.7B-Instruct.Q3_K_L.gguf b/SmolLM2-1.7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..162164b --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7182f87d86251e0d56925aebc47c7b802f8c278aad16060d92bb34e118bf3338 +size 932532736 diff --git a/SmolLM2-1.7B-Instruct.Q3_K_M.gguf b/SmolLM2-1.7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..ab3256e --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb9a8ca41e516d1d8fb663d7d40058c3b7d61513cae6d2dedb28be7ff2b69d54 +size 860180992 diff --git a/SmolLM2-1.7B-Instruct.Q3_K_S.gguf b/SmolLM2-1.7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..78ac7ac --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a84e3caa6a500f7f6adc11624e59316e179571201d9cbb1b1eb2a5533f3d4980 +size 776819200 diff --git a/SmolLM2-1.7B-Instruct.Q4_K_M.gguf b/SmolLM2-1.7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..0aa06d2 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e594099b6ca3fbb43f677f4529d2448ddc8071dace4d498a906b707450b91435 +size 1055609344 diff --git a/SmolLM2-1.7B-Instruct.Q4_K_S.gguf b/SmolLM2-1.7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..2293243 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f7fda06f38db4895c88549bc310c45f0253084fc4f220c747e1cceff9b4eaf7 +size 999117312 diff --git a/SmolLM2-1.7B-Instruct.Q5_K_M.gguf b/SmolLM2-1.7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..4f641bf --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5126e95eb5bb26b254d95765ff325e3f86886399c1323a6cb648e6c945086c7a +size 1225478656 diff --git a/SmolLM2-1.7B-Instruct.Q5_K_S.gguf b/SmolLM2-1.7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..7c96a63 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4759bce08dbfb1b251d6f90986fb919fd2ca21c1169f4aa60f88bed3e472b4fc +size 1192055296 diff --git a/SmolLM2-1.7B-Instruct.Q6_K.gguf b/SmolLM2-1.7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..5b62ea0 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade414ccfb3e26b41d49b0af44d356ba0eaebcf6c560d01af193cdcd91160dac +size 1405964800 diff --git a/SmolLM2-1.7B-Instruct.Q8_0.gguf b/SmolLM2-1.7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..356235f --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71b79765ae6f1c7a535d1fe9b186d15dcfe6fdca7d02f4c6955ad91af87b71c8 +size 1820414464 diff --git a/config.json b/config.json new file mode 100644 index 0000000..beb74f6 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "llama" +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file