commit bb0b0f24bcc71b7cdf8b19c3aa8420fab77f5c03 Author: ModelHub XC Date: Sat May 9 12:21:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f1bce23 --- /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 +Cerebras-GPT-1.3B-Alpaca-SP.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-GPT-1.3B-Alpaca-SP.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-GPT-1.3B-Alpaca-SP.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-GPT-1.3B-Alpaca-SP.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-GPT-1.3B-Alpaca-SP.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-GPT-1.3B-Alpaca-SP.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-GPT-1.3B-Alpaca-SP.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-GPT-1.3B-Alpaca-SP.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Cerebras-GPT-1.3B-Alpaca-SP.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Cerebras-GPT-1.3B-Alpaca-SP.IQ4_XS.gguf b/Cerebras-GPT-1.3B-Alpaca-SP.IQ4_XS.gguf new file mode 100644 index 0000000..656b5b1 --- /dev/null +++ b/Cerebras-GPT-1.3B-Alpaca-SP.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5365d0b7dcace44ff736cb1dcf64bda1c46f37985c60e835aea48eac71fee1 +size 755157952 diff --git a/Cerebras-GPT-1.3B-Alpaca-SP.Q2_K.gguf b/Cerebras-GPT-1.3B-Alpaca-SP.Q2_K.gguf new file mode 100644 index 0000000..18a1245 --- /dev/null +++ b/Cerebras-GPT-1.3B-Alpaca-SP.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee4da3c816be970d50d198626c26bd2a4b13a3dafd2a5e0b9c4d1c0e49980bb0 +size 553044928 diff --git a/Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_L.gguf b/Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_L.gguf new file mode 100644 index 0000000..d06664c --- /dev/null +++ b/Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1b921df9f11e2d831ae88a84dd9c2c4c27b177de5a55446da9ac1627beb00a +size 794479552 diff --git a/Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_M.gguf b/Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_M.gguf new file mode 100644 index 0000000..64f535f --- /dev/null +++ b/Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a149fb4089ff76aa57dcc2c1519fe27bd689eab049e641d9b5d1b91125db343d +size 733662144 diff --git a/Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_S.gguf b/Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_S.gguf new file mode 100644 index 0000000..0088a63 --- /dev/null +++ b/Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2dc4810b5d8dbff9a580d42ea02c6c9a3a0317e8925b854c08f5e72cfb05df9 +size 624610240 diff --git a/Cerebras-GPT-1.3B-Alpaca-SP.Q4_K_M.gguf b/Cerebras-GPT-1.3B-Alpaca-SP.Q4_K_M.gguf new file mode 100644 index 0000000..16baea8 --- /dev/null +++ b/Cerebras-GPT-1.3B-Alpaca-SP.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af5f27ce5a1d0a2568983657a36deb8e4e244b6e650433bc7aec98bb99297b5 +size 874695616 diff --git a/Cerebras-GPT-1.3B-Alpaca-SP.Q4_K_S.gguf b/Cerebras-GPT-1.3B-Alpaca-SP.Q4_K_S.gguf new file mode 100644 index 0000000..cb3d8b5 --- /dev/null +++ b/Cerebras-GPT-1.3B-Alpaca-SP.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3704454d100eae41741647b1908b886e5d32e343fb510e37d4cabd2133c5778 +size 791333824 diff --git a/Cerebras-GPT-1.3B-Alpaca-SP.Q5_K_M.gguf b/Cerebras-GPT-1.3B-Alpaca-SP.Q5_K_M.gguf new file mode 100644 index 0000000..9024c66 --- /dev/null +++ b/Cerebras-GPT-1.3B-Alpaca-SP.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65e9f5a25f4d1c9221d6db260e6a5456f44406df409b638f9814cb2ad74444c2 +size 1002884032 diff --git a/Cerebras-GPT-1.3B-Alpaca-SP.Q5_K_S.gguf b/Cerebras-GPT-1.3B-Alpaca-SP.Q5_K_S.gguf new file mode 100644 index 0000000..10d810e --- /dev/null +++ b/Cerebras-GPT-1.3B-Alpaca-SP.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f95ab75242dc5b6d26bddaea2e4470d63b63142a823bd8c87a9d15d5fcdac3 +size 936037312 diff --git a/Cerebras-GPT-1.3B-Alpaca-SP.Q6_K.gguf b/Cerebras-GPT-1.3B-Alpaca-SP.Q6_K.gguf new file mode 100644 index 0000000..f8cb9cf --- /dev/null +++ b/Cerebras-GPT-1.3B-Alpaca-SP.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea8052cfa03d9f1bdb2a0a70870cd673c8c1cf06e241cd8bff1018ea506b6f0d +size 1096469440 diff --git a/Cerebras-GPT-1.3B-Alpaca-SP.Q8_0.gguf b/Cerebras-GPT-1.3B-Alpaca-SP.Q8_0.gguf new file mode 100644 index 0000000..c14065b --- /dev/null +++ b/Cerebras-GPT-1.3B-Alpaca-SP.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c185c564cf790fce94f1fa2c0b5af5028fec1be9b3b303d265ef29b3e7eade5e +size 1413949600 diff --git a/Cerebras-GPT-1.3B-Alpaca-SP.f16.gguf b/Cerebras-GPT-1.3B-Alpaca-SP.f16.gguf new file mode 100644 index 0000000..ceb2fb2 --- /dev/null +++ b/Cerebras-GPT-1.3B-Alpaca-SP.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e87718d72d4b0d1cc7494862df630e9730aee357500f65d100c23ffd2cdbac4 +size 2642905120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dcd09eb --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: lxe/Cerebras-GPT-1.3B-Alpaca-SP +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/lxe/Cerebras-GPT-1.3B-Alpaca-SP + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-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/Cerebras-GPT-1.3B-Alpaca-SP-GGUF/resolve/main/Cerebras-GPT-1.3B-Alpaca-SP.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-GGUF/resolve/main/Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-GGUF/resolve/main/Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-GGUF/resolve/main/Cerebras-GPT-1.3B-Alpaca-SP.IQ4_XS.gguf) | IQ4_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-GGUF/resolve/main/Cerebras-GPT-1.3B-Alpaca-SP.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-GGUF/resolve/main/Cerebras-GPT-1.3B-Alpaca-SP.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-GGUF/resolve/main/Cerebras-GPT-1.3B-Alpaca-SP.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-GGUF/resolve/main/Cerebras-GPT-1.3B-Alpaca-SP.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-GGUF/resolve/main/Cerebras-GPT-1.3B-Alpaca-SP.Q5_K_M.gguf) | Q5_K_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-GGUF/resolve/main/Cerebras-GPT-1.3B-Alpaca-SP.Q6_K.gguf) | Q6_K | 1.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-GGUF/resolve/main/Cerebras-GPT-1.3B-Alpaca-SP.Q8_0.gguf) | Q8_0 | 1.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Cerebras-GPT-1.3B-Alpaca-SP-GGUF/resolve/main/Cerebras-GPT-1.3B-Alpaca-SP.f16.gguf) | f16 | 2.7 | 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. + +