commit 664ee4e60e19216b315d536af9bd39ee2173fc03 Author: ModelHub XC Date: Mon Sep 28 13:01:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-chat-CNN-chatbot-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9074edf --- /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-CNN-chatbot.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-CNN-chatbot.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-CNN-chatbot.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-CNN-chatbot.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-CNN-chatbot.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-CNN-chatbot.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-CNN-chatbot.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-CNN-chatbot.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-CNN-chatbot.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-CNN-chatbot.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-CNN-chatbot.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-CNN-chatbot.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-chat-CNN-chatbot.IQ4_XS.gguf b/Llama-2-7b-chat-CNN-chatbot.IQ4_XS.gguf new file mode 100644 index 0000000..4f39a72 --- /dev/null +++ b/Llama-2-7b-chat-CNN-chatbot.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e82824ee45efd62af6fad88fc6370a851a3d3159a2e0effc67819f405cca3bc8 +size 3647518176 diff --git a/Llama-2-7b-chat-CNN-chatbot.Q2_K.gguf b/Llama-2-7b-chat-CNN-chatbot.Q2_K.gguf new file mode 100644 index 0000000..a88f428 --- /dev/null +++ b/Llama-2-7b-chat-CNN-chatbot.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecc9a11b74d71526d51f1d996f224ff7f0bf1b421f4751edb34eaa4dd9a169c5 +size 2532865504 diff --git a/Llama-2-7b-chat-CNN-chatbot.Q3_K_L.gguf b/Llama-2-7b-chat-CNN-chatbot.Q3_K_L.gguf new file mode 100644 index 0000000..858e44c --- /dev/null +++ b/Llama-2-7b-chat-CNN-chatbot.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e015b7f980cffa8f5837abab67e6e00c9184cedc4d0ecb01233ccc811196838d +size 3597112800 diff --git a/Llama-2-7b-chat-CNN-chatbot.Q3_K_M.gguf b/Llama-2-7b-chat-CNN-chatbot.Q3_K_M.gguf new file mode 100644 index 0000000..7c125c1 --- /dev/null +++ b/Llama-2-7b-chat-CNN-chatbot.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:425d172ef6c71e004f340ce38f6c3596ecc2c273a26d7fb3123ad4312fa1b200 +size 3298006496 diff --git a/Llama-2-7b-chat-CNN-chatbot.Q3_K_S.gguf b/Llama-2-7b-chat-CNN-chatbot.Q3_K_S.gguf new file mode 100644 index 0000000..d3eeeda --- /dev/null +++ b/Llama-2-7b-chat-CNN-chatbot.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf84adb5ea6129d32060a037896e7410358cf1bc21ad7be488db5d37de77045a +size 2948306400 diff --git a/Llama-2-7b-chat-CNN-chatbot.Q4_K_M.gguf b/Llama-2-7b-chat-CNN-chatbot.Q4_K_M.gguf new file mode 100644 index 0000000..c2ecde2 --- /dev/null +++ b/Llama-2-7b-chat-CNN-chatbot.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0420281cfba9985a5bbe34923ce5a95489e2f13935d605940971493bb18ce0e1 +size 4081006048 diff --git a/Llama-2-7b-chat-CNN-chatbot.Q4_K_S.gguf b/Llama-2-7b-chat-CNN-chatbot.Q4_K_S.gguf new file mode 100644 index 0000000..9b5985f --- /dev/null +++ b/Llama-2-7b-chat-CNN-chatbot.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:997cab637e895e6b505490bc1d6a6b9f1a4ae9ad357c2c039b78770ebf88c4ba +size 3856741856 diff --git a/Llama-2-7b-chat-CNN-chatbot.Q5_K_M.gguf b/Llama-2-7b-chat-CNN-chatbot.Q5_K_M.gguf new file mode 100644 index 0000000..4e5dba1 --- /dev/null +++ b/Llama-2-7b-chat-CNN-chatbot.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6b596968699df0032ae7d522b917ebde21bf8e9bfd6dcc1c83a6914f7c5057 +size 4783158752 diff --git a/Llama-2-7b-chat-CNN-chatbot.Q5_K_S.gguf b/Llama-2-7b-chat-CNN-chatbot.Q5_K_S.gguf new file mode 100644 index 0000000..ea1e2da --- /dev/null +++ b/Llama-2-7b-chat-CNN-chatbot.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2fc2554704bc66723acd7685fca834fa9a7f6a6c60c23371880b620a6ddedbd +size 4651693536 diff --git a/Llama-2-7b-chat-CNN-chatbot.Q6_K.gguf b/Llama-2-7b-chat-CNN-chatbot.Q6_K.gguf new file mode 100644 index 0000000..9fefd8e --- /dev/null +++ b/Llama-2-7b-chat-CNN-chatbot.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e811a0437ef8a4843eea3a7c9fca6da3852ead7cd8abc30786eddc06909f69e +size 5529196000 diff --git a/Llama-2-7b-chat-CNN-chatbot.Q8_0.gguf b/Llama-2-7b-chat-CNN-chatbot.Q8_0.gguf new file mode 100644 index 0000000..5686389 --- /dev/null +++ b/Llama-2-7b-chat-CNN-chatbot.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f13cae682b0dd52b5e0f2e64a4129083a9b9a5bff19f9be7629d97343b8abe +size 7161091552 diff --git a/Llama-2-7b-chat-CNN-chatbot.f16.gguf b/Llama-2-7b-chat-CNN-chatbot.f16.gguf new file mode 100644 index 0000000..98fa33e --- /dev/null +++ b/Llama-2-7b-chat-CNN-chatbot.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcd30f19cfad74574bb8b73c4fa9c290fa8ee0cbcf8de854324d9c31c23a8061 +size 13478106592 diff --git a/README.md b/README.md new file mode 100644 index 0000000..871d64f --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: usamaatta/Llama-2-7b-chat-CNN-chatbot +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/usamaatta/Llama-2-7b-chat-CNN-chatbot + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-2-7b-chat-CNN-chatbot-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-CNN-chatbot-GGUF/resolve/main/Llama-2-7b-chat-CNN-chatbot.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-CNN-chatbot-GGUF/resolve/main/Llama-2-7b-chat-CNN-chatbot.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-CNN-chatbot-GGUF/resolve/main/Llama-2-7b-chat-CNN-chatbot.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-CNN-chatbot-GGUF/resolve/main/Llama-2-7b-chat-CNN-chatbot.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-CNN-chatbot-GGUF/resolve/main/Llama-2-7b-chat-CNN-chatbot.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-CNN-chatbot-GGUF/resolve/main/Llama-2-7b-chat-CNN-chatbot.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-CNN-chatbot-GGUF/resolve/main/Llama-2-7b-chat-CNN-chatbot.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-CNN-chatbot-GGUF/resolve/main/Llama-2-7b-chat-CNN-chatbot.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-CNN-chatbot-GGUF/resolve/main/Llama-2-7b-chat-CNN-chatbot.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-CNN-chatbot-GGUF/resolve/main/Llama-2-7b-chat-CNN-chatbot.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-CNN-chatbot-GGUF/resolve/main/Llama-2-7b-chat-CNN-chatbot.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-CNN-chatbot-GGUF/resolve/main/Llama-2-7b-chat-CNN-chatbot.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. + +