commit c27834dff604ae1df4f3a34a91cf2b870c4505c3 Author: ModelHub XC Date: Wed Jul 8 18:06:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53f3418 --- /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 +open-llama-0.7T-7B-open-instruct-v1.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f21d90d --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: VMware/open-llama-0.7T-7B-open-instruct-v1.1 +datasets: +- VMware/open-instruct-v1.1-oasst-dolly-hhrlhf +language: +- en +library_name: transformers +license: cc +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/VMware/open-llama-0.7T-7B-open-instruct-v1.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-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/open-llama-0.7T-7B-open-instruct-v1.1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.f16.gguf) | f16 | 13.6 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.IQ4_XS.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.IQ4_XS.gguf new file mode 100644 index 0000000..7b7fe99 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b5d388406203900b7363055e07dfb76002e8f4ca63d50a8aaf7344ab11e84e1 +size 3647552224 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.Q2_K.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.Q2_K.gguf new file mode 100644 index 0000000..7a34f20 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e94158d90ca65d9eaaa92f21e85fa3af9d9d27927514faf501708019cebb33d +size 2532899552 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_L.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_L.gguf new file mode 100644 index 0000000..d3e152e --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3a3f27feac48fc98e4e306abe17e795f80c31767ec91e66d1fae733295f1719 +size 3597146848 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_M.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_M.gguf new file mode 100644 index 0000000..0afae76 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ba83982186b9be490a97739f423ff7c95acb2a8e7576471b08db75d882a0ec6 +size 3298040544 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_S.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_S.gguf new file mode 100644 index 0000000..65774e1 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dd5d7fd1b14feec39de9515f6cee802a65359f89c6a76aa62e55e36d042b4c1 +size 2948340448 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.Q4_K_M.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.Q4_K_M.gguf new file mode 100644 index 0000000..3853771 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef112f5ad831280c4ab37da6b657ffbaf2d27bc746e2d155feedba280bfeb57 +size 4081040096 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.Q4_K_S.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.Q4_K_S.gguf new file mode 100644 index 0000000..16d8262 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a45ed4ff602200318749973399965c5a14bc7f8fa9d273de3101497ae3d80df3 +size 3856775904 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.Q5_K_M.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.Q5_K_M.gguf new file mode 100644 index 0000000..06c9028 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1c3b7a00b1c47a4c6d1abfa0dddd7725adddf2d31ed9525dae6a0eb28f8ca76 +size 4783192800 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.Q5_K_S.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.Q5_K_S.gguf new file mode 100644 index 0000000..3c82389 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1141f88f29b41d1febf17a2af42ba0bf208418577ef5e1d5bfab4739b537915d +size 4651727584 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.Q6_K.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.Q6_K.gguf new file mode 100644 index 0000000..3e7525b --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94adfe83085546eb89a70fabb9c43a523caddd282c1bb3bbb008409612dfafdb +size 5529230048 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.Q8_0.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.Q8_0.gguf new file mode 100644 index 0000000..7efbc40 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:375ac627f50ef1e8b849fea5c4eac92c46ce490bab686be3462a7bb27af99c33 +size 7161125600 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.f16.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.f16.gguf new file mode 100644 index 0000000..a0beef0 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d123d5475395b4ccbca83fea07dc07d581aece98e268b24e46c965521bd51a1 +size 13478140640