commit e9f500d2374be14188e032fe67f69d1a8fd88e18 Author: ModelHub XC Date: Mon Sep 7 03:22:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/persona-generator-llama-2-7b-qlora-merged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..37dbc04 --- /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 +persona-generator-llama-2-7b-qlora-merged.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +persona-generator-llama-2-7b-qlora-merged.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +persona-generator-llama-2-7b-qlora-merged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +persona-generator-llama-2-7b-qlora-merged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +persona-generator-llama-2-7b-qlora-merged.f16.gguf filter=lfs diff=lfs merge=lfs -text +persona-generator-llama-2-7b-qlora-merged.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +persona-generator-llama-2-7b-qlora-merged.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +persona-generator-llama-2-7b-qlora-merged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +persona-generator-llama-2-7b-qlora-merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +persona-generator-llama-2-7b-qlora-merged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +persona-generator-llama-2-7b-qlora-merged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +persona-generator-llama-2-7b-qlora-merged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e0a5dab --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: danlou/persona-generator-llama-2-7b-qlora-merged +language: +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/danlou/persona-generator-llama-2-7b-qlora-merged + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/persona-generator-llama-2-7b-qlora-merged-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/persona-generator-llama-2-7b-qlora-merged-GGUF/resolve/main/persona-generator-llama-2-7b-qlora-merged.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/persona-generator-llama-2-7b-qlora-merged-GGUF/resolve/main/persona-generator-llama-2-7b-qlora-merged.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/persona-generator-llama-2-7b-qlora-merged-GGUF/resolve/main/persona-generator-llama-2-7b-qlora-merged.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/persona-generator-llama-2-7b-qlora-merged-GGUF/resolve/main/persona-generator-llama-2-7b-qlora-merged.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/persona-generator-llama-2-7b-qlora-merged-GGUF/resolve/main/persona-generator-llama-2-7b-qlora-merged.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/persona-generator-llama-2-7b-qlora-merged-GGUF/resolve/main/persona-generator-llama-2-7b-qlora-merged.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/persona-generator-llama-2-7b-qlora-merged-GGUF/resolve/main/persona-generator-llama-2-7b-qlora-merged.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/persona-generator-llama-2-7b-qlora-merged-GGUF/resolve/main/persona-generator-llama-2-7b-qlora-merged.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/persona-generator-llama-2-7b-qlora-merged-GGUF/resolve/main/persona-generator-llama-2-7b-qlora-merged.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/persona-generator-llama-2-7b-qlora-merged-GGUF/resolve/main/persona-generator-llama-2-7b-qlora-merged.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/persona-generator-llama-2-7b-qlora-merged-GGUF/resolve/main/persona-generator-llama-2-7b-qlora-merged.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/persona-generator-llama-2-7b-qlora-merged-GGUF/resolve/main/persona-generator-llama-2-7b-qlora-merged.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/persona-generator-llama-2-7b-qlora-merged.IQ4_XS.gguf b/persona-generator-llama-2-7b-qlora-merged.IQ4_XS.gguf new file mode 100644 index 0000000..e2eafea --- /dev/null +++ b/persona-generator-llama-2-7b-qlora-merged.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f32ef5c911741f4ff5ce5db43b66506b11b8ef1c034a26e3cb8abb91db83e9 +size 3647517600 diff --git a/persona-generator-llama-2-7b-qlora-merged.Q2_K.gguf b/persona-generator-llama-2-7b-qlora-merged.Q2_K.gguf new file mode 100644 index 0000000..9bb7f2f --- /dev/null +++ b/persona-generator-llama-2-7b-qlora-merged.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88eb566b97a0f5618beba69d44bfc54a2d435c67d233c26a24a6e2bc121d33ab +size 2532864928 diff --git a/persona-generator-llama-2-7b-qlora-merged.Q3_K_L.gguf b/persona-generator-llama-2-7b-qlora-merged.Q3_K_L.gguf new file mode 100644 index 0000000..733b98e --- /dev/null +++ b/persona-generator-llama-2-7b-qlora-merged.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53be9587c17a020486627dd7d353d0f4b2c1492098ca8bb4b9df9650948e2018 +size 3597112224 diff --git a/persona-generator-llama-2-7b-qlora-merged.Q3_K_M.gguf b/persona-generator-llama-2-7b-qlora-merged.Q3_K_M.gguf new file mode 100644 index 0000000..3e2597d --- /dev/null +++ b/persona-generator-llama-2-7b-qlora-merged.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db975e3187ec753ae99d6cd7074f0b22285726214ede355bd96cf64db19b3511 +size 3298005920 diff --git a/persona-generator-llama-2-7b-qlora-merged.Q3_K_S.gguf b/persona-generator-llama-2-7b-qlora-merged.Q3_K_S.gguf new file mode 100644 index 0000000..8d9fb35 --- /dev/null +++ b/persona-generator-llama-2-7b-qlora-merged.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7d671bb0c965d4f4a2acb510f83fe88239cfed55c77cdb23b7758fdab3b4ed9 +size 2948305824 diff --git a/persona-generator-llama-2-7b-qlora-merged.Q4_K_M.gguf b/persona-generator-llama-2-7b-qlora-merged.Q4_K_M.gguf new file mode 100644 index 0000000..ece0ed3 --- /dev/null +++ b/persona-generator-llama-2-7b-qlora-merged.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc6f34ff55c25a3fd30c7baf78882eeefed23503a616f5f018fa953136706b6 +size 4081005472 diff --git a/persona-generator-llama-2-7b-qlora-merged.Q4_K_S.gguf b/persona-generator-llama-2-7b-qlora-merged.Q4_K_S.gguf new file mode 100644 index 0000000..74c5b25 --- /dev/null +++ b/persona-generator-llama-2-7b-qlora-merged.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0772b89d16b81dab3e6f1a5ab31ef76bc48ee705b246161cfecc353ed1dd2df2 +size 3856741280 diff --git a/persona-generator-llama-2-7b-qlora-merged.Q5_K_M.gguf b/persona-generator-llama-2-7b-qlora-merged.Q5_K_M.gguf new file mode 100644 index 0000000..985f2ee --- /dev/null +++ b/persona-generator-llama-2-7b-qlora-merged.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a925584db7d4784f2ae8b93ad19e4275266de67ec0a5b66af292e56efc762d86 +size 4783158176 diff --git a/persona-generator-llama-2-7b-qlora-merged.Q5_K_S.gguf b/persona-generator-llama-2-7b-qlora-merged.Q5_K_S.gguf new file mode 100644 index 0000000..78cd18b --- /dev/null +++ b/persona-generator-llama-2-7b-qlora-merged.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0e06cad393e3bc99c6c7b4517db3cbca74cd635a7c84893338502234bebe3ae +size 4651692960 diff --git a/persona-generator-llama-2-7b-qlora-merged.Q6_K.gguf b/persona-generator-llama-2-7b-qlora-merged.Q6_K.gguf new file mode 100644 index 0000000..dc20303 --- /dev/null +++ b/persona-generator-llama-2-7b-qlora-merged.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa0692ba54aa7778772af9faad0c37e5f45adbe39fac7296e9320344abb64b53 +size 5529195424 diff --git a/persona-generator-llama-2-7b-qlora-merged.Q8_0.gguf b/persona-generator-llama-2-7b-qlora-merged.Q8_0.gguf new file mode 100644 index 0000000..50b3009 --- /dev/null +++ b/persona-generator-llama-2-7b-qlora-merged.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:212eec48021e4ee7ac967a371e3014cf9f30ce1b148a34fe6eb3bb65e0ee4528 +size 7161090976 diff --git a/persona-generator-llama-2-7b-qlora-merged.f16.gguf b/persona-generator-llama-2-7b-qlora-merged.f16.gguf new file mode 100644 index 0000000..3850d40 --- /dev/null +++ b/persona-generator-llama-2-7b-qlora-merged.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33760e8a93ca3f1610432458f3ef294365f6dbe4e6efcf916974330feaf26263 +size 13478106016