commit 541268204c1609f1f48de4c702003e732bcbfaf2 Author: ModelHub XC Date: Wed Jun 17 05:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/hc-llama-8b-0308-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..46b0ba4 --- /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 +hc-llama-8b-0308.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +hc-llama-8b-0308.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +hc-llama-8b-0308.f16.gguf filter=lfs diff=lfs merge=lfs -text +hc-llama-8b-0308.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +hc-llama-8b-0308.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +hc-llama-8b-0308.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +hc-llama-8b-0308.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +hc-llama-8b-0308.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +hc-llama-8b-0308.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +hc-llama-8b-0308.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +hc-llama-8b-0308.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +hc-llama-8b-0308.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e9f321b --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: q5390498/hc-llama-8b-0308 +datasets: AI-MO/NuminaMath-TIR +language: +- en +library_name: transformers +model_name: hc-llama-8b-0308 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/q5390498/hc-llama-8b-0308 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/hc-llama-8b-0308-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/hc-llama-8b-0308-GGUF/resolve/main/hc-llama-8b-0308.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/hc-llama-8b-0308-GGUF/resolve/main/hc-llama-8b-0308.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/hc-llama-8b-0308-GGUF/resolve/main/hc-llama-8b-0308.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/hc-llama-8b-0308-GGUF/resolve/main/hc-llama-8b-0308.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/hc-llama-8b-0308-GGUF/resolve/main/hc-llama-8b-0308.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/hc-llama-8b-0308-GGUF/resolve/main/hc-llama-8b-0308.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/hc-llama-8b-0308-GGUF/resolve/main/hc-llama-8b-0308.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/hc-llama-8b-0308-GGUF/resolve/main/hc-llama-8b-0308.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/hc-llama-8b-0308-GGUF/resolve/main/hc-llama-8b-0308.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/hc-llama-8b-0308-GGUF/resolve/main/hc-llama-8b-0308.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/hc-llama-8b-0308-GGUF/resolve/main/hc-llama-8b-0308.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/hc-llama-8b-0308-GGUF/resolve/main/hc-llama-8b-0308.f16.gguf) | f16 | 16.2 | 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/hc-llama-8b-0308.IQ4_XS.gguf b/hc-llama-8b-0308.IQ4_XS.gguf new file mode 100644 index 0000000..8379679 --- /dev/null +++ b/hc-llama-8b-0308.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def721e9d9046491df2806b6eb1a4cef67790290e6021c70da92c4c3f4334478 +size 4484363584 diff --git a/hc-llama-8b-0308.Q2_K.gguf b/hc-llama-8b-0308.Q2_K.gguf new file mode 100644 index 0000000..eaaa7e0 --- /dev/null +++ b/hc-llama-8b-0308.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db9767acf8d6911547983b0fbf0b114af31dcb709a3de8a694370f757983b390 +size 3179132224 diff --git a/hc-llama-8b-0308.Q3_K_L.gguf b/hc-llama-8b-0308.Q3_K_L.gguf new file mode 100644 index 0000000..b853176 --- /dev/null +++ b/hc-llama-8b-0308.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b3c5564f6d388f54d0d96b9cc8baa858471cf1fc38a52b85ceb36807acc236 +size 4321957184 diff --git a/hc-llama-8b-0308.Q3_K_M.gguf b/hc-llama-8b-0308.Q3_K_M.gguf new file mode 100644 index 0000000..4e139e2 --- /dev/null +++ b/hc-llama-8b-0308.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b808c3e889f7ea9328dc64a4b19bad0748303ac59a555b5884ee6815223ea19d +size 4018918720 diff --git a/hc-llama-8b-0308.Q3_K_S.gguf b/hc-llama-8b-0308.Q3_K_S.gguf new file mode 100644 index 0000000..c27ea13 --- /dev/null +++ b/hc-llama-8b-0308.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b64cd5bb0d583e180e6f32e896548d3f30e37235e2c68ede85e9bd17fab84b71 +size 3664500032 diff --git a/hc-llama-8b-0308.Q4_K_M.gguf b/hc-llama-8b-0308.Q4_K_M.gguf new file mode 100644 index 0000000..7058cb4 --- /dev/null +++ b/hc-llama-8b-0308.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:440214d25ae9ec2b6fe1a7c3d232119dfc6fd9ce91b49e215971bc8197492303 +size 4920735040 diff --git a/hc-llama-8b-0308.Q4_K_S.gguf b/hc-llama-8b-0308.Q4_K_S.gguf new file mode 100644 index 0000000..5dd242b --- /dev/null +++ b/hc-llama-8b-0308.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da0cb4434edc6bf391f4e2bc77017e107764e610e111f63722149703e63e1bc1 +size 4692669760 diff --git a/hc-llama-8b-0308.Q5_K_M.gguf b/hc-llama-8b-0308.Q5_K_M.gguf new file mode 100644 index 0000000..f25e397 --- /dev/null +++ b/hc-llama-8b-0308.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:343d042356082f643a43fe70269f10af0090f4b4a67f4e710123fd9df6d90744 +size 5732988224 diff --git a/hc-llama-8b-0308.Q5_K_S.gguf b/hc-llama-8b-0308.Q5_K_S.gguf new file mode 100644 index 0000000..ccf3530 --- /dev/null +++ b/hc-llama-8b-0308.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac01ee748719564878007c4683d373d1f52c47b50682af21f6f1b5ac3062ea3e +size 5599294784 diff --git a/hc-llama-8b-0308.Q6_K.gguf b/hc-llama-8b-0308.Q6_K.gguf new file mode 100644 index 0000000..bfe672b --- /dev/null +++ b/hc-llama-8b-0308.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee06fdccd3e374aca4d29a7b39d1bd6c4f8d729459b07b795c1ae7e11c142e67 +size 6596007232 diff --git a/hc-llama-8b-0308.Q8_0.gguf b/hc-llama-8b-0308.Q8_0.gguf new file mode 100644 index 0000000..ffd22b8 --- /dev/null +++ b/hc-llama-8b-0308.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f0bc25e9c3f77f9f62cf5b6fd631ad52ee3f7f20b00fd814e4b5dc3406ea3b3 +size 8540771648 diff --git a/hc-llama-8b-0308.f16.gguf b/hc-llama-8b-0308.f16.gguf new file mode 100644 index 0000000..577b2ad --- /dev/null +++ b/hc-llama-8b-0308.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c38fd9cec15e4cfe5fea8ad7c28d8489adf2d5869e328596170f1fe297dd1e0 +size 16068891968