commit bad5568823abac3969d94d9ea289f7321e507132 Author: ModelHub XC Date: Wed Sep 30 16:38:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5d5515a --- /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 +mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.f16.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mintrec-1-meta-llama-Llama-2-7b-hf.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..87d8869 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: saransh03sharma/mintrec-1-meta-llama-Llama-2-7b-hf +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/saransh03sharma/mintrec-1-meta-llama-Llama-2-7b-hf + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-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/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/mintrec-1-meta-llama-Llama-2-7b-hf-GGUF/resolve/main/mintrec-1-meta-llama-Llama-2-7b-hf.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. + + diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_M.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_M.gguf new file mode 100644 index 0000000..c234a20 --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90a93dabeb53a5a5b9d05f3e03f6def40422e1e51139e4f63f042334bdd11404 +size 3114865216 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_S.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_S.gguf new file mode 100644 index 0000000..58f25aa --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02c231a62d2da87fe379a7ed34785a269acfe45376e1449a6ee4e226238e9c75 +size 2948305472 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_XS.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_XS.gguf new file mode 100644 index 0000000..d098b53 --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:896e7bbc7d68a0c07f511372c948b91074644eb2736060e9ac06308380516d6c +size 2796524096 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.IQ4_XS.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.IQ4_XS.gguf new file mode 100644 index 0000000..5a31c9f --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:084b793615f579bc6fc094983c307458873408497c346e3c209bde8309bb91bb +size 3647517248 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.Q2_K.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.Q2_K.gguf new file mode 100644 index 0000000..1d84cfe --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebcb08be55156ab971c2657ebc247b5da7f5415bfcb841fe939466b26933c147 +size 2532864576 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_L.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_L.gguf new file mode 100644 index 0000000..6acdad7 --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a2aa6a5b06372642867e555192f117d64462b009e769705c1c3cbd3a6fdc6a7 +size 3597111872 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_M.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_M.gguf new file mode 100644 index 0000000..20abb0e --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90455342a4d572f6e0f5ae956f14c35a122cfd4f0d497b389ea5e2915c721819 +size 3298005568 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_S.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_S.gguf new file mode 100644 index 0000000..6a949f6 --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3867b8e1134cf3da48a8b5b54ae3e4500ab9055107318fa0935fe17712da5a7f +size 2948305472 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.Q4_K_M.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.Q4_K_M.gguf new file mode 100644 index 0000000..4868561 --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd37a0aa95b850066a4ef14ebef85d9e5e1bde7bf4c0191bed0483b8d53540f +size 4081005120 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.Q4_K_S.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.Q4_K_S.gguf new file mode 100644 index 0000000..7c80e29 --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2a3cb49d263fb9a5c881e137c1df6edbf336795ddd148bb9507d4c61b34d415 +size 3856740928 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.Q5_K_M.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.Q5_K_M.gguf new file mode 100644 index 0000000..ad3c51c --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc2b717d7f955fcb50e6eedb2eff34946e892f1f85302913444503ade5251e19 +size 4783157824 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.Q5_K_S.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.Q5_K_S.gguf new file mode 100644 index 0000000..b9f53c7 --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d14d1cf983048a845941082a65741803f865e2a8f7e20b166bd2bc8bab8f488e +size 4651692608 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.Q6_K.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.Q6_K.gguf new file mode 100644 index 0000000..c9fe6e2 --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39f998b5c412acbdbe21a8db5a7692804565ae4baa8594188c8efa33f0a92f4e +size 5529195072 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.Q8_0.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.Q8_0.gguf new file mode 100644 index 0000000..e8f60d4 --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944dd976325e4d94a135e90f23e8c99c6ca0b4e22131430faafad67d08e02178 +size 7161090624 diff --git a/mintrec-1-meta-llama-Llama-2-7b-hf.f16.gguf b/mintrec-1-meta-llama-Llama-2-7b-hf.f16.gguf new file mode 100644 index 0000000..cae5966 --- /dev/null +++ b/mintrec-1-meta-llama-Llama-2-7b-hf.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8114a853407d2f9c1ddbc4033aab251b43434422f2b619db1c49be60243f92fb +size 13478105664