commit 3b46b9913c07ff1655fde5891d9d03f0fc7d11f8 Author: ModelHub XC Date: Sat Jul 4 16:57:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: di-zhang-fdu/Supra-50M-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..df536fc --- /dev/null +++ b/.gitattributes @@ -0,0 +1,43 @@ +*.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 +Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +model.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Q2_K.gguf b/Q2_K.gguf new file mode 100644 index 0000000..7328522 --- /dev/null +++ b/Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:559f965b5e702998784bc10af8f6b5733c9b10aba0dcf14f54cacbc81f6cd5c1 +size 28752640 diff --git a/Q3_K_S.gguf b/Q3_K_S.gguf new file mode 100644 index 0000000..6bf9ef1 --- /dev/null +++ b/Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dc4075e8ef958d36302b3993601042e865493c42a9fdeb2ae4b8df5f10e02c0 +size 30989056 diff --git a/Q4_0.gguf b/Q4_0.gguf new file mode 100644 index 0000000..7beded7 --- /dev/null +++ b/Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c024958107c8933919b58ffed81125944b37136784d89298356ae2f7bb9d68b3 +size 34540288 diff --git a/Q4_K_M.gguf b/Q4_K_M.gguf new file mode 100644 index 0000000..c0d6a37 --- /dev/null +++ b/Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:792a090bad0e4ed00e567a1576d984f5743e88c61a55436a236b85200c3e963c +size 37446400 diff --git a/Q4_K_S.gguf b/Q4_K_S.gguf new file mode 100644 index 0000000..9f03ae0 --- /dev/null +++ b/Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad18b8355fa2c131e5ed273578469ff6b4026f3f4f0cab4c4fb042b740526b19 +size 35732224 diff --git a/Q6_K.gguf b/Q6_K.gguf new file mode 100644 index 0000000..7a68bbd --- /dev/null +++ b/Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f28c2e9fcbfca49f48c9743240a5eb3143343f47b7c788bbfde2857dc99e17a0 +size 45759232 diff --git a/Q8_0.gguf b/Q8_0.gguf new file mode 100644 index 0000000..be9c285 --- /dev/null +++ b/Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a23696bf0a6ad75d30da6a2e24895660f20f8ed6fe7fd9442a8deda1ee31a8 +size 56203008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fda12aa --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +license: apache-2.0 +base_model: SupraLabs/Supra-50M-Instruct +library_name: llama.cpp +tags: +- gguf +- llama.cpp +- quantized +- supra +- text-generation +--- + +# Supra-50M-Instruct-GGUF + +GGUF quantizations of [SupraLabs/Supra-50M-Instruct](https://huggingface.co/SupraLabs/Supra-50M-Instruct). + +## Files + +| File | Quantization | Size | +| --- | --- | ---: | +| `model.gguf` | F16 base GGUF | 100M | +| `Q8_0.gguf` | Q8_0 | 54M | +| `Q6_K.gguf` | Q6_K | 44M | +| `Q4_K_M.gguf` | Q4_K_M | 36M | +| `Q4_K_S.gguf` | Q4_K_S | 35M | +| `Q4_0.gguf` | Q4_0 | 33M | +| `Q3_K_S.gguf` | Q3_K_S | 30M | +| `Q2_K.gguf` | Q2_K | 28M | + +Checksums are in `SHA256SUMS`. + +## Conversion + +`model.gguf` is the F16 GGUF from the source repository. The quantized files were generated with `llama.cpp` build `b9550` using `llama-quantize`. + +Some K-quant outputs may contain fallback tensor types where tensor dimensions are not divisible by the required K-quant block size. This is normal `llama.cpp` behavior for this model shape. + +## Usage + +This model was instruction-tuned with the Alpaca prompt format. It is not a ChatML-style multi-turn chat model, so use completion mode and include the prompt template. The GGUF files intentionally do not include `tokenizer.chat_template`, because llama.cpp chat mode would otherwise try to apply the wrong template. + +```text +Below is an instruction that describes a task. Write a response that appropriately completes the request. + +### Instruction: +What is the capital of Japan? + +### Response: +``` + +Example with `llama.cpp`: + +```bash +cat > prompt.txt <<'EOF' +Below is an instruction that describes a task. Write a response that appropriately completes the request. + +### Instruction: +What is the capital of Japan? + +### Response: +EOF + +llama-completion \ + -hf di-zhang-fdu/Supra-50M-Instruct-GGUF:Q4_K_M \ + -f prompt.txt \ + -n 128 \ + --temp 0.7 \ + --top-k 50 \ + --top-p 0.9 \ + --repeat-penalty 1.15 \ + -no-cnv +``` + +For deterministic checks, use `--temp 0 --top-k 1`. diff --git a/SHA256SUMS b/SHA256SUMS new file mode 100644 index 0000000..3f615e1 --- /dev/null +++ b/SHA256SUMS @@ -0,0 +1,8 @@ +559f965b5e702998784bc10af8f6b5733c9b10aba0dcf14f54cacbc81f6cd5c1 Q2_K.gguf +5dc4075e8ef958d36302b3993601042e865493c42a9fdeb2ae4b8df5f10e02c0 Q3_K_S.gguf +c024958107c8933919b58ffed81125944b37136784d89298356ae2f7bb9d68b3 Q4_0.gguf +792a090bad0e4ed00e567a1576d984f5743e88c61a55436a236b85200c3e963c Q4_K_M.gguf +ad18b8355fa2c131e5ed273578469ff6b4026f3f4f0cab4c4fb042b740526b19 Q4_K_S.gguf +f28c2e9fcbfca49f48c9743240a5eb3143343f47b7c788bbfde2857dc99e17a0 Q6_K.gguf +37a23696bf0a6ad75d30da6a2e24895660f20f8ed6fe7fd9442a8deda1ee31a8 Q8_0.gguf +dfddc7c000ca6c948c285fd52c525516eab4d9ab404478af92781af39c24851e model.gguf diff --git a/model.gguf b/model.gguf new file mode 100644 index 0000000..1bf5655 --- /dev/null +++ b/model.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfddc7c000ca6c948c285fd52c525516eab4d9ab404478af92781af39c24851e +size 104740608