commit 0588ab0eca30f248da49952d6ecc3b8e2b58c8cc Author: ModelHub XC Date: Sat Sep 26 19:59:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-chat-hf_fictional_Korean_v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bca42be --- /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-chat-hf_fictional_Korean_v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_Korean_v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_Korean_v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_Korean_v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_Korean_v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_Korean_v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_Korean_v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_Korean_v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_Korean_v1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-chat-hf_fictional_Korean_v1.IQ4_XS.gguf b/Llama-2-7b-chat-hf_fictional_Korean_v1.IQ4_XS.gguf new file mode 100644 index 0000000..d6ee4b3 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_Korean_v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07ed552fbdef79a8819bf2e69da8063f1f06b71cf254990be1d7fa9ee5346d7e +size 3647518656 diff --git a/Llama-2-7b-chat-hf_fictional_Korean_v1.Q2_K.gguf b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q2_K.gguf new file mode 100644 index 0000000..71bec1e --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db7c8a1948fad30984bd868cc637d2ce482aaadd91e9783ea042a290519c37c5 +size 2532865984 diff --git a/Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_L.gguf b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_L.gguf new file mode 100644 index 0000000..a19ed92 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfec5a9d0b6534a20b89c7408c1d932ff720f6ba1a4f4ef7dfbe9852a37adb84 +size 3597113280 diff --git a/Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_M.gguf b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_M.gguf new file mode 100644 index 0000000..a9def20 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0977f0535c0736e48f3a69cb3c33dffb146573338126e7c2878825c12a0a7f28 +size 3298006976 diff --git a/Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_S.gguf b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_S.gguf new file mode 100644 index 0000000..6d3c8d6 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:036b75ea0ceb285f34fadc639ad870b66e1071fdabb8a0a0f4941a901eb301cb +size 2948306880 diff --git a/Llama-2-7b-chat-hf_fictional_Korean_v1.Q4_K_M.gguf b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q4_K_M.gguf new file mode 100644 index 0000000..690470c --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6103fd7835293dda2010a56b1fdbac993be2f7d92c3347859aac100d297c2c89 +size 4081006528 diff --git a/Llama-2-7b-chat-hf_fictional_Korean_v1.Q4_K_S.gguf b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q4_K_S.gguf new file mode 100644 index 0000000..dfa056b --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf1a086af9bd76372b21581b101dde744b7a73e0558e58f092c66b6e95130b41 +size 3856742336 diff --git a/Llama-2-7b-chat-hf_fictional_Korean_v1.Q5_K_M.gguf b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q5_K_M.gguf new file mode 100644 index 0000000..4ed072a --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6655a61588e9a37c6e4133ccd9115a17309b15a75c8f0575bbd88c5627a0fe4b +size 4783159232 diff --git a/Llama-2-7b-chat-hf_fictional_Korean_v1.Q5_K_S.gguf b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q5_K_S.gguf new file mode 100644 index 0000000..6ea5368 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd2ee52167de8db2457a75c417c8b09233f5ad32a5704420ba954ba00778dc64 +size 4651694016 diff --git a/Llama-2-7b-chat-hf_fictional_Korean_v1.Q6_K.gguf b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q6_K.gguf new file mode 100644 index 0000000..d67dbb9 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53a0e1ef958fda71c6df7d80037c5c0b0a4ffcb6f01135a8dd480f56c3e79f3a +size 5529196480 diff --git a/Llama-2-7b-chat-hf_fictional_Korean_v1.Q8_0.gguf b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q8_0.gguf new file mode 100644 index 0000000..7370296 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_Korean_v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd1f11c017e48f798486ee7cc1d19f3c11043c170ddf55cd2a7b89ad55246846 +size 7161092032 diff --git a/Llama-2-7b-chat-hf_fictional_Korean_v1.f16.gguf b/Llama-2-7b-chat-hf_fictional_Korean_v1.f16.gguf new file mode 100644 index 0000000..6a59b97 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_Korean_v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b806d071c6e595d5bcb2baf6220fb5633f157f44bbcd1265766b13013575d90c +size 13478107072 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a06ef57 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: yzhuang/Llama-2-7b-chat-hf_fictional_Korean_v1 +datasets: +- generator +language: +- en +library_name: transformers +license: llama2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- trl +- sft +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/yzhuang/Llama-2-7b-chat-hf_fictional_Korean_v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-2-7b-chat-hf_fictional_Korean_v1-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-chat-hf_fictional_Korean_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_Korean_v1.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_Korean_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_Korean_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_Korean_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_Korean_v1.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_Korean_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_Korean_v1.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_Korean_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_Korean_v1.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_Korean_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_Korean_v1.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_Korean_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_Korean_v1.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_Korean_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_Korean_v1.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_Korean_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_Korean_v1.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_Korean_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_Korean_v1.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_Korean_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_Korean_v1.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. + +