commit f8c47032cf94918dbdff9cc31184fc34156a37b1 Author: ModelHub XC Date: Fri May 8 13:42:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TwinLlama-3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..82cacda --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +TwinLlama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ca12b73 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: mlabonne/TwinLlama-3.1-8B +datasets: +- mlabonne/llmtwin +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/mlabonne/TwinLlama-3.1-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/TwinLlama-3.1-8B-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/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-GGUF/resolve/main/TwinLlama-3.1-8B.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/TwinLlama-3.1-8B.IQ4_XS.gguf b/TwinLlama-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..93cac6e --- /dev/null +++ b/TwinLlama-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67d1b7363618282807d4ebda3eff7891374b7daeba814e7fd452460418ab9692 +size 4484363680 diff --git a/TwinLlama-3.1-8B.Q2_K.gguf b/TwinLlama-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..f48d51d --- /dev/null +++ b/TwinLlama-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b62f1e3841cb47fdff3dd8b26cecb1e8f4aec0e14bdfe58fa0387964faa01316 +size 3179132320 diff --git a/TwinLlama-3.1-8B.Q3_K_L.gguf b/TwinLlama-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..ecc24c1 --- /dev/null +++ b/TwinLlama-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bde41b81f9ac3f300d1dfc01e18224900c98aaeddaeae07f56b168304ca4aa02 +size 4321957280 diff --git a/TwinLlama-3.1-8B.Q3_K_M.gguf b/TwinLlama-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..3291593 --- /dev/null +++ b/TwinLlama-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b90bff25119e89dcaf2256a5a473cb708af2025d7b7aab35c1a13c7fd438e1d8 +size 4018918816 diff --git a/TwinLlama-3.1-8B.Q3_K_S.gguf b/TwinLlama-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..3c0a90c --- /dev/null +++ b/TwinLlama-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eff84c93c68366e97674ce3a8baa7d9b1400121ef67291d53310155558c8d870 +size 3664500128 diff --git a/TwinLlama-3.1-8B.Q4_0_4_4.gguf b/TwinLlama-3.1-8B.Q4_0_4_4.gguf new file mode 100644 index 0000000..3a056f0 --- /dev/null +++ b/TwinLlama-3.1-8B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c21fd2fbb91962f4d191c568f79909ce9bdbbfbccb4711e2004b8e1507540e6 +size 4661212576 diff --git a/TwinLlama-3.1-8B.Q4_K_M.gguf b/TwinLlama-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..020743f --- /dev/null +++ b/TwinLlama-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06d29d8bc7d3d8c3cf3c8e9f6f0b499a3414df49274bbd86077f0102cb1bc39d +size 4920735136 diff --git a/TwinLlama-3.1-8B.Q4_K_S.gguf b/TwinLlama-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..3c4f9dc --- /dev/null +++ b/TwinLlama-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23ad3edf7d0549d16f35bcfaa13e294144f18bbb184f6cb1d2c19d2d20fca899 +size 4692669856 diff --git a/TwinLlama-3.1-8B.Q5_K_M.gguf b/TwinLlama-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..6c295f7 --- /dev/null +++ b/TwinLlama-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8fdbcaf80b46e5f3203703e764cf81cf3ec4d831ee5860d847dc60914675437 +size 5732988320 diff --git a/TwinLlama-3.1-8B.Q5_K_S.gguf b/TwinLlama-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..566ca09 --- /dev/null +++ b/TwinLlama-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ac9ff23a19ac15a5a664efc0d2dff43d7a5af10326c486a39e9a6dc90a81efe +size 5599294880 diff --git a/TwinLlama-3.1-8B.Q6_K.gguf b/TwinLlama-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..929c7b8 --- /dev/null +++ b/TwinLlama-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff369a145755df0feed3baee426ee04c51e29936ea8fd6b1a43eb575813ea776 +size 6596007328 diff --git a/TwinLlama-3.1-8B.Q8_0.gguf b/TwinLlama-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..e2d6d08 --- /dev/null +++ b/TwinLlama-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc24eb94a1050379379d15e94037452925893d448ab543508bffc2632f9d5883 +size 8540771744 diff --git a/TwinLlama-3.1-8B.f16.gguf b/TwinLlama-3.1-8B.f16.gguf new file mode 100644 index 0000000..b52d607 --- /dev/null +++ b/TwinLlama-3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a0aae5a522f85b8fbce75bc8b9b09bfc8def6a0e10efccb7913b8151bae1900 +size 16068892064