commit 475d1ffb351be6e02bc6a736f3081b3fae7f4bbc Author: ModelHub XC Date: Sat Oct 3 15:51:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-chat-hf_fictional_v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fa68684 --- /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_v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-chat-hf_fictional_v1.IQ4_XS.gguf b/Llama-2-7b-chat-hf_fictional_v1.IQ4_XS.gguf new file mode 100644 index 0000000..853c61c --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8636289b21ea5079bc1a77e474b4ee90768b5cc935573a3aa001bbb4bbf6dd66 +size 3647518592 diff --git a/Llama-2-7b-chat-hf_fictional_v1.Q2_K.gguf b/Llama-2-7b-chat-hf_fictional_v1.Q2_K.gguf new file mode 100644 index 0000000..428c5f6 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a53f7d60b5af0e6dc873d19650c669086b24b3a4bfa9fcde471d495e9545ac1 +size 2532865920 diff --git a/Llama-2-7b-chat-hf_fictional_v1.Q3_K_L.gguf b/Llama-2-7b-chat-hf_fictional_v1.Q3_K_L.gguf new file mode 100644 index 0000000..4baa8b8 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d71868f4d403cdbf83950faf58f6a1699ced345de4f14bec351c5cea2632859e +size 3597113216 diff --git a/Llama-2-7b-chat-hf_fictional_v1.Q3_K_M.gguf b/Llama-2-7b-chat-hf_fictional_v1.Q3_K_M.gguf new file mode 100644 index 0000000..8eb15b6 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aff01ca15a22eed718ba7e93230a318670c94ad46e46f98db1d48919d687334 +size 3298006912 diff --git a/Llama-2-7b-chat-hf_fictional_v1.Q3_K_S.gguf b/Llama-2-7b-chat-hf_fictional_v1.Q3_K_S.gguf new file mode 100644 index 0000000..5589ff5 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:420b458b2229754d69a673ce4d8c6ba7d857b9f3ce0075578d5e41c282fbf732 +size 2948306816 diff --git a/Llama-2-7b-chat-hf_fictional_v1.Q4_K_M.gguf b/Llama-2-7b-chat-hf_fictional_v1.Q4_K_M.gguf new file mode 100644 index 0000000..fe647e5 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68d93bf081b18cd4afed467988e264971cb7ad994995ea7b51ad2ff955e9e9bc +size 4081006464 diff --git a/Llama-2-7b-chat-hf_fictional_v1.Q4_K_S.gguf b/Llama-2-7b-chat-hf_fictional_v1.Q4_K_S.gguf new file mode 100644 index 0000000..df78eda --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47c4d0ebf3902d71595f8d7ec5db7db6fe30ee473141a6308e7aec1ed7bdfd55 +size 3856742272 diff --git a/Llama-2-7b-chat-hf_fictional_v1.Q5_K_M.gguf b/Llama-2-7b-chat-hf_fictional_v1.Q5_K_M.gguf new file mode 100644 index 0000000..7d89f45 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed4b0d28e83262a06891b3f64fe325c981fc7f4f9c161a530b5ea18d2b1d9b23 +size 4783159168 diff --git a/Llama-2-7b-chat-hf_fictional_v1.Q5_K_S.gguf b/Llama-2-7b-chat-hf_fictional_v1.Q5_K_S.gguf new file mode 100644 index 0000000..5b4efc6 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dfff0bfcc7cb20c49231c103dffbf0f1546c92bc376b9685da3fa542529698e +size 4651693952 diff --git a/Llama-2-7b-chat-hf_fictional_v1.Q6_K.gguf b/Llama-2-7b-chat-hf_fictional_v1.Q6_K.gguf new file mode 100644 index 0000000..2127304 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e41c11f587bbadd96556a0b76d1bbcd82439b632470dc5ae02a00ce517de7d8c +size 5529196416 diff --git a/Llama-2-7b-chat-hf_fictional_v1.Q8_0.gguf b/Llama-2-7b-chat-hf_fictional_v1.Q8_0.gguf new file mode 100644 index 0000000..35a8fe0 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f7b8d30037d257a6e54096e78f2407a7b88edf947025b07271c71e552101c73 +size 7161091968 diff --git a/Llama-2-7b-chat-hf_fictional_v1.f16.gguf b/Llama-2-7b-chat-hf_fictional_v1.f16.gguf new file mode 100644 index 0000000..d29087e --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93968734422c35c939a84a76e68803b5e1ac9a4a2eefa7d6d5ccb4a1280c4303 +size 13478107008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ce845a7 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: yzhuang/Llama-2-7b-chat-hf_fictional_v1 +datasets: +- generator +language: +- en +library_name: transformers +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_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_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_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_v1.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_v1.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_v1.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_v1.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_v1.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_v1.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_v1.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_v1.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_v1.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_v1.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_v1.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_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. + +