commit 49d07bdc3d5cc5164173c35cc7df996dc65eeba6 Author: ModelHub XC Date: Fri Jul 24 00:07:09 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6c22d2f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +granite-4.0-h-1b-DISTILL-glm-4.7-think-f16.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q2_k.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_1.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_1.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-DISTILL-glm-4.7-think-q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7433964 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think +library_name: gguf +license: apache-2.0 +language: +- en +- fr +tags: +- granite +- gguf +- quantized +- llama.cpp +- ollama +quantized_by: llama.cpp +pipeline_tag: text-generation +--- + +# granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF + +GGUF quantized versions of [granite-4.0-h-1b-DISTILL-glm-4.7-think](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think) + +## Available Formats + +| Filename | Size | Quant Type | Description | +|----------|------|------------|-------------| +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-f16.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-f16.gguf) | 2.73 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-F16 | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q2_k.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q2_k.gguf) | 0.55 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q2_K | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_l.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_l.gguf) | 0.71 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q3_K_L | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_m.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_m.gguf) | 0.68 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q3_K_M | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_s.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_s.gguf) | 0.65 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q3_K_S | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_0.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_0.gguf) | 0.81 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q4_0 | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_1.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_1.gguf) | 0.88 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q4_1 | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_m.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_m.gguf) | 0.84 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q4_K_M | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_s.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_s.gguf) | 0.81 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q4_K_S | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_0.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_0.gguf) | 0.96 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q5_0 | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_1.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_1.gguf) | 1.04 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q5_1 | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_m.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_m.gguf) | 0.98 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q5_K_M | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_s.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_s.gguf) | 0.96 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q5_K_S | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q6_k.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q6_k.gguf) | 1.12 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q6_K | | +| [granite-4.0-h-1b-DISTILL-glm-4.7-think-q8_0.gguf](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF/blob/main/granite-4.0-h-1b-DISTILL-glm-4.7-think-q8_0.gguf) | 1.45 GB | GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q8_0 | | + + +## Quick Start + +### Ollama + +```bash +# Use Q4_K_M (recommended) +ollama run hf.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M + +# Or other quantizations +ollama run hf.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q8_0 +ollama run hf.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q2_K +``` + +### llama.cpp + +```bash +# Download and run +llama-cli --hf-repo glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF --hf-file granite-4.0-h-1b-distill-glm-4.7-think-q4_k_m.gguf -p "Hello, how are you?" + +# With server +llama-server --hf-repo glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF --hf-file granite-4.0-h-1b-distill-glm-4.7-think-q4_k_m.gguf -c 2048 +``` + +### LM Studio / GPT4All + +Download the `.gguf` file of your choice and load it in your application. + +## Quantization Details + +| Type | Bits | Use Case | +|------|------|----------| +| Q2_K | 2 | Extreme compression, low quality | +| Q3_K_M | 3 | Very compressed | +| Q4_K_M | 4 | **Recommended** - Best size/quality | +| Q5_K_M | 5 | High quality | +| Q6_K | 6 | Very high quality | +| Q8_0 | 8 | Near lossless | +| F16 | 16 | Original precision | + +## Original Model + +This is the quantized version of [granite-4.0-h-1b-DISTILL-glm-4.7-think](https://huggingface.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think) + +- **Base Model:** ibm-granite/granite-4.0-h-1b +- **Fine-tuning Dataset:** TeichAI/glm-4.7-2000x +- **Training Loss:** 0.6364 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-f16.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-f16.gguf new file mode 100644 index 0000000..3cde4f4 --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6647d4671ff0fd2cfa96a9923c3b3f867445bbc781446a87763a51addd5e97 +size 2928331808 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q2_k.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q2_k.gguf new file mode 100644 index 0000000..f91af92 --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49fc2d8975dd7886e247985704ae7a03727dfa5fdabca1dfc9cce7ecbd3b7d70 +size 588928256 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_l.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_l.gguf new file mode 100644 index 0000000..c535548 --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_l.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d4c437b21a5ea49937b299ffdcc4f8516e6cf8a1a44869316be8205114fbfa +size 762913280 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_m.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_m.gguf new file mode 100644 index 0000000..baa9f2b --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c058d76f5059e3378444548084fbecbde79adc32ff7628bfc772103bf42b372b +size 731652608 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_s.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_s.gguf new file mode 100644 index 0000000..6d521d9 --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4855fc286f30952da2290178d5666d18cdb8cff5fb1057c7e5c6aee6fdaa54c +size 694788608 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_0.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_0.gguf new file mode 100644 index 0000000..d1d09a5 --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7725bf2c653c1b732b16f4cd69c1a169370503c5746623f49fac99dbf8b39680 +size 868315904 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_1.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_1.gguf new file mode 100644 index 0000000..9aa7383 --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9daeb19b295118b02f11a95b4992bfe9d0f0837e10d2cc492b06dd8188f0eca +size 949975808 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_m.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_m.gguf new file mode 100644 index 0000000..9bfbc4c --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eda2573424434fbc540ae99f449913e21dd47c39fb72f0d48aabf0d3eef5959 +size 901161728 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_s.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_s.gguf new file mode 100644 index 0000000..5fde736 --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8857f485d8ac6b02a2d91d688534173828459a09c5d810f125aa8277a737ae6b +size 872641280 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_0.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_0.gguf new file mode 100644 index 0000000..5072765 --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e8b9a21e71af170a6fafe52b3e1152e4ec09c238f7e3e187b7bdf7f95d3402 +size 1031635712 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_1.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_1.gguf new file mode 100644 index 0000000..86f4900 --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b5012fbf40ce3d9a842ae96711e5a1b12ef0cddd47b4fd1d5979555e1c2cc1 +size 1113295616 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_m.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_m.gguf new file mode 100644 index 0000000..834d3a2 --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d94200f1c81aea7ea94554a7566c8ac360cdcabcfe5259aa310117b3321bf9c9 +size 1048556288 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_s.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_s.gguf new file mode 100644 index 0000000..b9b4e5f --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11f559595b5ce33618bb2fb3f8599f442aa806f72eea1c87018e28269356174a +size 1031635712 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q6_k.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q6_k.gguf new file mode 100644 index 0000000..0fbaf37 --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:732474ae98c6b3846edbda9f933630ce725d448a429669247beed69d7c089143 +size 1205163008 diff --git a/granite-4.0-h-1b-DISTILL-glm-4.7-think-q8_0.gguf b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q8_0.gguf new file mode 100644 index 0000000..30ae8c1 --- /dev/null +++ b/granite-4.0-h-1b-DISTILL-glm-4.7-think-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ce53612c56685c00cd5726772990ab9007bd3e43b70fc7feee64401fe112fca +size 1558926080