commit b31e2e1e9c20b7c2b876fbf8591bff93435ed241 Author: ModelHub XC Date: Sat Oct 24 10:18:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PA-RAG_Llama-2-7b-chat-hf-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2332b79 --- /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 +PA-RAG_Llama-2-7b-chat-hf.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PA-RAG_Llama-2-7b-chat-hf.f16.gguf filter=lfs diff=lfs merge=lfs -text +PA-RAG_Llama-2-7b-chat-hf.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PA-RAG_Llama-2-7b-chat-hf.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PA-RAG_Llama-2-7b-chat-hf.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PA-RAG_Llama-2-7b-chat-hf.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PA-RAG_Llama-2-7b-chat-hf.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PA-RAG_Llama-2-7b-chat-hf.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PA-RAG_Llama-2-7b-chat-hf.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PA-RAG_Llama-2-7b-chat-hf.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PA-RAG_Llama-2-7b-chat-hf.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PA-RAG_Llama-2-7b-chat-hf.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PA-RAG_Llama-2-7b-chat-hf.IQ4_XS.gguf b/PA-RAG_Llama-2-7b-chat-hf.IQ4_XS.gguf new file mode 100644 index 0000000..350227d --- /dev/null +++ b/PA-RAG_Llama-2-7b-chat-hf.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc739e0afec259e0ccec63351b7588c8168abb616e40f6f006c515ae7f416c4e +size 3647518208 diff --git a/PA-RAG_Llama-2-7b-chat-hf.Q2_K.gguf b/PA-RAG_Llama-2-7b-chat-hf.Q2_K.gguf new file mode 100644 index 0000000..0a1d922 --- /dev/null +++ b/PA-RAG_Llama-2-7b-chat-hf.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98528fe4c004cbadd4a1c4455202dcd2a6773d4414c0fa7c421f8d4d7efb095 +size 2532865536 diff --git a/PA-RAG_Llama-2-7b-chat-hf.Q3_K_L.gguf b/PA-RAG_Llama-2-7b-chat-hf.Q3_K_L.gguf new file mode 100644 index 0000000..2d35254 --- /dev/null +++ b/PA-RAG_Llama-2-7b-chat-hf.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:903c78cd5142d3859256067da45e312b346c291f1eb9c7e102f24dbc7848ad8b +size 3597112832 diff --git a/PA-RAG_Llama-2-7b-chat-hf.Q3_K_M.gguf b/PA-RAG_Llama-2-7b-chat-hf.Q3_K_M.gguf new file mode 100644 index 0000000..713a3d1 --- /dev/null +++ b/PA-RAG_Llama-2-7b-chat-hf.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b523a7af595affa0b4267c15815e8322a1e9e71e1840b6da61a93a5a8b90c93 +size 3298006528 diff --git a/PA-RAG_Llama-2-7b-chat-hf.Q3_K_S.gguf b/PA-RAG_Llama-2-7b-chat-hf.Q3_K_S.gguf new file mode 100644 index 0000000..5923667 --- /dev/null +++ b/PA-RAG_Llama-2-7b-chat-hf.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f93ec542e1c30a9f013efc7a758361f4f9714a94894e9e9c489eaa568da4f8b6 +size 2948306432 diff --git a/PA-RAG_Llama-2-7b-chat-hf.Q4_K_M.gguf b/PA-RAG_Llama-2-7b-chat-hf.Q4_K_M.gguf new file mode 100644 index 0000000..1edb2ea --- /dev/null +++ b/PA-RAG_Llama-2-7b-chat-hf.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88f0a904a3b5f8c3c27d4ece7d956778ad8c409cb68e4900a99cd80b80c8a4c2 +size 4081006080 diff --git a/PA-RAG_Llama-2-7b-chat-hf.Q4_K_S.gguf b/PA-RAG_Llama-2-7b-chat-hf.Q4_K_S.gguf new file mode 100644 index 0000000..b4384b5 --- /dev/null +++ b/PA-RAG_Llama-2-7b-chat-hf.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf6339c8c295dd32eea47f8d1443e18104645c5e2530b7d41c8c18198ff777f7 +size 3856741888 diff --git a/PA-RAG_Llama-2-7b-chat-hf.Q5_K_M.gguf b/PA-RAG_Llama-2-7b-chat-hf.Q5_K_M.gguf new file mode 100644 index 0000000..b59203a --- /dev/null +++ b/PA-RAG_Llama-2-7b-chat-hf.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f745378316b8254e915ba06a4ec6799ae709cce26357aa1471f58fdd09d9fa +size 4783158784 diff --git a/PA-RAG_Llama-2-7b-chat-hf.Q5_K_S.gguf b/PA-RAG_Llama-2-7b-chat-hf.Q5_K_S.gguf new file mode 100644 index 0000000..ed5802f --- /dev/null +++ b/PA-RAG_Llama-2-7b-chat-hf.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c424c3c4785f2f025919ebf331b5baaf5c40db346392e38d8500aeda1997b567 +size 4651693568 diff --git a/PA-RAG_Llama-2-7b-chat-hf.Q6_K.gguf b/PA-RAG_Llama-2-7b-chat-hf.Q6_K.gguf new file mode 100644 index 0000000..53cc80e --- /dev/null +++ b/PA-RAG_Llama-2-7b-chat-hf.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b675d456aa460bdeadeb39be70f9721a65df242cfdcbcd5e7231916a0d8ca3c1 +size 5529196032 diff --git a/PA-RAG_Llama-2-7b-chat-hf.Q8_0.gguf b/PA-RAG_Llama-2-7b-chat-hf.Q8_0.gguf new file mode 100644 index 0000000..503783d --- /dev/null +++ b/PA-RAG_Llama-2-7b-chat-hf.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78942e8b35fc55ee6e2257bb24e6a5c0200167f6b34afc839fd1c7cb08b7ebaa +size 7161091584 diff --git a/PA-RAG_Llama-2-7b-chat-hf.f16.gguf b/PA-RAG_Llama-2-7b-chat-hf.f16.gguf new file mode 100644 index 0000000..f878ee4 --- /dev/null +++ b/PA-RAG_Llama-2-7b-chat-hf.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4cc017156730252fe690a454c830848c302993110a9580c2522db1db3005210 +size 13478106624 diff --git a/README.md b/README.md new file mode 100644 index 0000000..44baac7 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: wuqiong1/PA-RAG_Llama-2-7b-chat-hf +datasets: +- wuqiong1/PA-RAG_training_data +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/wuqiong1/PA-RAG_Llama-2-7b-chat-hf + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/PA-RAG_Llama-2-7b-chat-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/PA-RAG_Llama-2-7b-chat-hf-GGUF/resolve/main/PA-RAG_Llama-2-7b-chat-hf.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/PA-RAG_Llama-2-7b-chat-hf-GGUF/resolve/main/PA-RAG_Llama-2-7b-chat-hf.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/PA-RAG_Llama-2-7b-chat-hf-GGUF/resolve/main/PA-RAG_Llama-2-7b-chat-hf.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PA-RAG_Llama-2-7b-chat-hf-GGUF/resolve/main/PA-RAG_Llama-2-7b-chat-hf.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/PA-RAG_Llama-2-7b-chat-hf-GGUF/resolve/main/PA-RAG_Llama-2-7b-chat-hf.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/PA-RAG_Llama-2-7b-chat-hf-GGUF/resolve/main/PA-RAG_Llama-2-7b-chat-hf.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PA-RAG_Llama-2-7b-chat-hf-GGUF/resolve/main/PA-RAG_Llama-2-7b-chat-hf.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PA-RAG_Llama-2-7b-chat-hf-GGUF/resolve/main/PA-RAG_Llama-2-7b-chat-hf.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/PA-RAG_Llama-2-7b-chat-hf-GGUF/resolve/main/PA-RAG_Llama-2-7b-chat-hf.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/PA-RAG_Llama-2-7b-chat-hf-GGUF/resolve/main/PA-RAG_Llama-2-7b-chat-hf.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PA-RAG_Llama-2-7b-chat-hf-GGUF/resolve/main/PA-RAG_Llama-2-7b-chat-hf.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PA-RAG_Llama-2-7b-chat-hf-GGUF/resolve/main/PA-RAG_Llama-2-7b-chat-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. + +