commit 5181db12bfddb470c8517c99abf673c7e26a5c3c Author: ModelHub XC Date: Thu Jul 9 05:11:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantFactory/llama-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..17f450b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +llama-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..beadcae --- /dev/null +++ b/README.md @@ -0,0 +1,20 @@ + +--- + +license: other + +--- + +[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory) + + +# QuantFactory/llama-7b-GGUF +This is quantized version of [huggyllama/llama-7b](https://huggingface.co/huggyllama/llama-7b) created using llama.cpp + +# Original Model Card + + +This contains the weights for the LLaMA-7b model. This model is under a non-commercial license (see the LICENSE file). +You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form) but either lost your copy of the weights or got some trouble converting them to the Transformers format. + + diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "allow_remote": true} \ No newline at end of file diff --git a/llama-7b.Q2_K.gguf b/llama-7b.Q2_K.gguf new file mode 100644 index 0000000..15e687e --- /dev/null +++ b/llama-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3283d2db140f069e8814bc869a91e647fcaf3a2a074243f3cfb4d82dc103aef0 +size 2532865536 diff --git a/llama-7b.Q3_K_L.gguf b/llama-7b.Q3_K_L.gguf new file mode 100644 index 0000000..4df62f6 --- /dev/null +++ b/llama-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ae73eabb1b0e72904ffb540c2f5340cfe982f61b58665411e2d5b4f50085df +size 3597112832 diff --git a/llama-7b.Q3_K_M.gguf b/llama-7b.Q3_K_M.gguf new file mode 100644 index 0000000..0cea213 --- /dev/null +++ b/llama-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3565da54b8be96d086f6e7eb25e8c1dff1e443d25bf447e165ddc2d4ce42ca0 +size 3298006528 diff --git a/llama-7b.Q3_K_S.gguf b/llama-7b.Q3_K_S.gguf new file mode 100644 index 0000000..b4c4f26 --- /dev/null +++ b/llama-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18f7dad34b75e93c0c16c3eb3f9def981a3cb1edfe47663d2948ef2cd875674d +size 2948306432 diff --git a/llama-7b.Q4_0.gguf b/llama-7b.Q4_0.gguf new file mode 100644 index 0000000..9dff734 --- /dev/null +++ b/llama-7b.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaaae3ab6f952b8b10379d4afc2ab6b8ee21c1968035de82607df896f01c5022 +size 3825808896 diff --git a/llama-7b.Q4_1.gguf b/llama-7b.Q4_1.gguf new file mode 100644 index 0000000..f68206f --- /dev/null +++ b/llama-7b.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecafc1ec5dc4e49a99c41cf80be667f50fd59e845cce6fa12f24744de7f8431c +size 4238751232 diff --git a/llama-7b.Q4_K_M.gguf b/llama-7b.Q4_K_M.gguf new file mode 100644 index 0000000..7925680 --- /dev/null +++ b/llama-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a6a03a80540e8f6a50b9fe4ecd3ad134c6208fb5d39c3556db06046612f3369 +size 4081006080 diff --git a/llama-7b.Q4_K_S.gguf b/llama-7b.Q4_K_S.gguf new file mode 100644 index 0000000..9a2102f --- /dev/null +++ b/llama-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984dcf76d4128529ffa1370a0333f4ebbd5f16107b6c8a6d1344524b03e66ec6 +size 3856741888 diff --git a/llama-7b.Q5_0.gguf b/llama-7b.Q5_0.gguf new file mode 100644 index 0000000..06f856d --- /dev/null +++ b/llama-7b.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b81542bbe14d79201e195e95c4f09c4fda505e6f1f866dd94ab1420ff3aabbf1 +size 4651693568 diff --git a/llama-7b.Q5_1.gguf b/llama-7b.Q5_1.gguf new file mode 100644 index 0000000..59ef4b5 --- /dev/null +++ b/llama-7b.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1f6b3518dfcdbc08a62afc9965b2eaef24f678b16ae4ce7974baa8c5ff92bb2 +size 5064635904 diff --git a/llama-7b.Q5_K_M.gguf b/llama-7b.Q5_K_M.gguf new file mode 100644 index 0000000..2f0222c --- /dev/null +++ b/llama-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f66c696c0b2c3c97dff1d8c281f76f0645d02f56653b821918185a1b4233a2b6 +size 4783158784 diff --git a/llama-7b.Q5_K_S.gguf b/llama-7b.Q5_K_S.gguf new file mode 100644 index 0000000..fd31f5b --- /dev/null +++ b/llama-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e123c79fd61d7a4cac2797f6137a021b619e28545b6dd45f0db7fadbb1fd39b +size 4651693568 diff --git a/llama-7b.Q6_K.gguf b/llama-7b.Q6_K.gguf new file mode 100644 index 0000000..d24d494 --- /dev/null +++ b/llama-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:344dcb8186dfa79f2f3868207db6dacc09d8abbad5085cb758d4a3d1470ca4ed +size 5529196032 diff --git a/llama-7b.Q8_0.gguf b/llama-7b.Q8_0.gguf new file mode 100644 index 0000000..350a3bb --- /dev/null +++ b/llama-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99b51364feb0bbb7cd964a3331705f052333dac79d452665ed9db14b23532259 +size 7161091584