commit 2db25d72dd74d8b41df744a4eebf3b300283dcf7 Author: ModelHub XC Date: Tue May 26 12:58:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7B-fp16-safe-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a2fc96e --- /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 +Llama-2-7B-fp16-safe.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-fp16-safe.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-fp16-safe.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-fp16-safe.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-fp16-safe.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-fp16-safe.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-fp16-safe.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-fp16-safe.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-fp16-safe.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-fp16-safe.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-fp16-safe.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-fp16-safe.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7B-fp16-safe.IQ4_XS.gguf b/Llama-2-7B-fp16-safe.IQ4_XS.gguf new file mode 100644 index 0000000..33608f0 --- /dev/null +++ b/Llama-2-7B-fp16-safe.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d3ca27894c9a0afd4af4e149732308b22f1406a30476a156e1d8c8d0cd03d4 +size 3647517792 diff --git a/Llama-2-7B-fp16-safe.Q2_K.gguf b/Llama-2-7B-fp16-safe.Q2_K.gguf new file mode 100644 index 0000000..f1b5e5a --- /dev/null +++ b/Llama-2-7B-fp16-safe.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:035cc6f634557602b28a34871c4c0b81de7e8b219e73b30e0765af02fd987b2e +size 2532865120 diff --git a/Llama-2-7B-fp16-safe.Q3_K_L.gguf b/Llama-2-7B-fp16-safe.Q3_K_L.gguf new file mode 100644 index 0000000..36370c5 --- /dev/null +++ b/Llama-2-7B-fp16-safe.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f96e595ab791c0beed26a0398d9ec06d50a2d8c25b71cf89be232dca4d434ddb +size 3597112416 diff --git a/Llama-2-7B-fp16-safe.Q3_K_M.gguf b/Llama-2-7B-fp16-safe.Q3_K_M.gguf new file mode 100644 index 0000000..2c8aaff --- /dev/null +++ b/Llama-2-7B-fp16-safe.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5920a43fefda9b4d3b2295ec16337cc6b5d7785e7c9f42c501796c46d4df4550 +size 3298006112 diff --git a/Llama-2-7B-fp16-safe.Q3_K_S.gguf b/Llama-2-7B-fp16-safe.Q3_K_S.gguf new file mode 100644 index 0000000..c88d749 --- /dev/null +++ b/Llama-2-7B-fp16-safe.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:798029d062bd4b7818156a3c4ab8d9491e1cf2e4bce2617905b90d9d929bf2a2 +size 2948306016 diff --git a/Llama-2-7B-fp16-safe.Q4_K_M.gguf b/Llama-2-7B-fp16-safe.Q4_K_M.gguf new file mode 100644 index 0000000..d9532e7 --- /dev/null +++ b/Llama-2-7B-fp16-safe.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47713d022ee48d714b331fe0a3661bfb54044a9571b84f8a855dc279414cb8c0 +size 4081005664 diff --git a/Llama-2-7B-fp16-safe.Q4_K_S.gguf b/Llama-2-7B-fp16-safe.Q4_K_S.gguf new file mode 100644 index 0000000..5ec8b13 --- /dev/null +++ b/Llama-2-7B-fp16-safe.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d810caad5052600ff784030f30f21aada3ee0d52083fdfbcc60a82b0b17f8ae1 +size 3856741472 diff --git a/Llama-2-7B-fp16-safe.Q5_K_M.gguf b/Llama-2-7B-fp16-safe.Q5_K_M.gguf new file mode 100644 index 0000000..ac4a528 --- /dev/null +++ b/Llama-2-7B-fp16-safe.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f02b786becd863d32672c5bdd1560d7ed208bb6ea880c7f9f3bce20ebb81fba +size 4783158368 diff --git a/Llama-2-7B-fp16-safe.Q5_K_S.gguf b/Llama-2-7B-fp16-safe.Q5_K_S.gguf new file mode 100644 index 0000000..da92c63 --- /dev/null +++ b/Llama-2-7B-fp16-safe.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cf347fab926949d71821b047f523fdd8e577d3a27777ce7b239857053dcb049 +size 4651693152 diff --git a/Llama-2-7B-fp16-safe.Q6_K.gguf b/Llama-2-7B-fp16-safe.Q6_K.gguf new file mode 100644 index 0000000..17a98c4 --- /dev/null +++ b/Llama-2-7B-fp16-safe.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:681436b38fbfdec08e882ac094c419f1729b33dd425f07ac1b53eab7099e61e5 +size 5529195616 diff --git a/Llama-2-7B-fp16-safe.Q8_0.gguf b/Llama-2-7B-fp16-safe.Q8_0.gguf new file mode 100644 index 0000000..49dd274 --- /dev/null +++ b/Llama-2-7B-fp16-safe.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1504de72df091e8b96a341effdedc0adf68be715c5965477e05e937e33601c8 +size 7161091168 diff --git a/Llama-2-7B-fp16-safe.f16.gguf b/Llama-2-7B-fp16-safe.f16.gguf new file mode 100644 index 0000000..3b9d769 --- /dev/null +++ b/Llama-2-7B-fp16-safe.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e808b07bfe01ca8d012c51368c3373cfea13b1cf4c4aa96f5c9eda3ecc56fd69 +size 13478106208 diff --git a/README.md b/README.md new file mode 100644 index 0000000..14f4362 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: jyu911/Llama-2-7B-fp16-safe +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- base_model:adapter:TheBloke/Llama-2-7B-fp16 +- lora +- transformers +--- +## About + + + + + + + + + +static quants of https://huggingface.co/jyu911/Llama-2-7B-fp16-safe + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-2-7B-fp16-safe-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/Llama-2-7B-fp16-safe-GGUF/resolve/main/Llama-2-7B-fp16-safe.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-fp16-safe-GGUF/resolve/main/Llama-2-7B-fp16-safe.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-fp16-safe-GGUF/resolve/main/Llama-2-7B-fp16-safe.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-fp16-safe-GGUF/resolve/main/Llama-2-7B-fp16-safe.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-fp16-safe-GGUF/resolve/main/Llama-2-7B-fp16-safe.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-fp16-safe-GGUF/resolve/main/Llama-2-7B-fp16-safe.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-fp16-safe-GGUF/resolve/main/Llama-2-7B-fp16-safe.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-fp16-safe-GGUF/resolve/main/Llama-2-7B-fp16-safe.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-fp16-safe-GGUF/resolve/main/Llama-2-7B-fp16-safe.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-fp16-safe-GGUF/resolve/main/Llama-2-7B-fp16-safe.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-fp16-safe-GGUF/resolve/main/Llama-2-7B-fp16-safe.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-fp16-safe-GGUF/resolve/main/Llama-2-7B-fp16-safe.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. + +