commit a5f9c27d978ece16e5bbd0510fbef483402774ac Author: ModelHub XC Date: Fri Jun 19 03:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/neural-chat-7b-v3-3-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21083c5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +neural-chat-7b-v3-3.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e410d53 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: Intel/neural-chat-7b-v3-3 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- LLMs +- mistral +- math +- Intel +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Intel/neural-chat-7b-v3-3 + + +static quants are available at https://huggingface.co/mradermacher/neural-chat-7b-v3-3-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/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.2 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.2 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/neural-chat-7b-v3-3-i1-GGUF/resolve/main/neural-chat-7b-v3-3.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..da4270f --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c8de63a7159dd46a0c6ad0fb721a52d2f7210598333271d91ae5652358f6a03 +size 4988157 diff --git a/neural-chat-7b-v3-3.i1-IQ1_M.gguf b/neural-chat-7b-v3-3.i1-IQ1_M.gguf new file mode 100644 index 0000000..1e1c399 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ffb44dedae6d9cd1d18b2bc15d6c1748c019bd4b5246cedcc4bfa727b227302 +size 1754447968 diff --git a/neural-chat-7b-v3-3.i1-IQ1_S.gguf b/neural-chat-7b-v3-3.i1-IQ1_S.gguf new file mode 100644 index 0000000..d884c55 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aa9595d7ac990e29739850bb6876592cd986ccf4b4c28e7f41b58daca7f787e +size 1612103776 diff --git a/neural-chat-7b-v3-3.i1-IQ2_M.gguf b/neural-chat-7b-v3-3.i1-IQ2_M.gguf new file mode 100644 index 0000000..76e4913 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee2a14b7e40b573d047229e75a1173f486b284e4ad0a29abbec642436f96a1f +size 2500714592 diff --git a/neural-chat-7b-v3-3.i1-IQ2_S.gguf b/neural-chat-7b-v3-3.i1-IQ2_S.gguf new file mode 100644 index 0000000..b3ad0b2 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a28b1a75552960c7c69f9458d70650849027e16ca9039755143043c50720f67c +size 2310922336 diff --git a/neural-chat-7b-v3-3.i1-IQ2_XS.gguf b/neural-chat-7b-v3-3.i1-IQ2_XS.gguf new file mode 100644 index 0000000..caba68c --- /dev/null +++ b/neural-chat-7b-v3-3.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb3083bf2c2dd7d15ce66cd4b1a1a387058925beae16f78d0456ba35cbc5e190 +size 2198257760 diff --git a/neural-chat-7b-v3-3.i1-IQ2_XXS.gguf b/neural-chat-7b-v3-3.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..2cb79e2 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48d02ae5aa0a3ccb97dac9ffa8b4da278e10c1ef9e825d889ba5743896276743 +size 1991688288 diff --git a/neural-chat-7b-v3-3.i1-IQ3_M.gguf b/neural-chat-7b-v3-3.i1-IQ3_M.gguf new file mode 100644 index 0000000..3a43419 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d06dcae9fa331d1dd8cb9823e690a5c9a993c21c2246d8b7e895e963e340dbf1 +size 3284893792 diff --git a/neural-chat-7b-v3-3.i1-IQ3_S.gguf b/neural-chat-7b-v3-3.i1-IQ3_S.gguf new file mode 100644 index 0000000..29a57b5 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad8ed6b493129543efc9653f1494d4f7f261ef6c99f4293caf8c656fdd87929c +size 3182395488 diff --git a/neural-chat-7b-v3-3.i1-IQ3_XS.gguf b/neural-chat-7b-v3-3.i1-IQ3_XS.gguf new file mode 100644 index 0000000..369b79a --- /dev/null +++ b/neural-chat-7b-v3-3.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c389d130c5066e9daa6e57d9bf6bb9a086067e69462968af068b7050ee10037 +size 3018817632 diff --git a/neural-chat-7b-v3-3.i1-IQ3_XXS.gguf b/neural-chat-7b-v3-3.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8a32736 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ced3a723bfd4f6e5bd8c8b4bb93c69018a8251558684598b283013a4b12b03c +size 2827346016 diff --git a/neural-chat-7b-v3-3.i1-IQ4_XS.gguf b/neural-chat-7b-v3-3.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9183e7e --- /dev/null +++ b/neural-chat-7b-v3-3.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ef4fdda7f972d390d30771860df39f82ff746f98f94b36ece3fe88da9a1f43f +size 3907690592 diff --git a/neural-chat-7b-v3-3.i1-Q2_K.gguf b/neural-chat-7b-v3-3.i1-Q2_K.gguf new file mode 100644 index 0000000..66fd878 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51240ac7d8928742cf6fc61cd25e4ab7067c1ab425e050c6b7bf5c7a09ad122a +size 2719244384 diff --git a/neural-chat-7b-v3-3.i1-Q3_K_L.gguf b/neural-chat-7b-v3-3.i1-Q3_K_L.gguf new file mode 100644 index 0000000..0f2b3d7 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9a4fa2591a1abacd9d7723aa64df83da26f3f82ed053bcac3ae8dd5ea6b1e97 +size 3822026848 diff --git a/neural-chat-7b-v3-3.i1-Q3_K_M.gguf b/neural-chat-7b-v3-3.i1-Q3_K_M.gguf new file mode 100644 index 0000000..7d25aca --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d575b8aebee863e4fd3cdacc5da375096a4d84790280bc4c274465a2e39518b +size 3518988384 diff --git a/neural-chat-7b-v3-3.i1-Q3_K_S.gguf b/neural-chat-7b-v3-3.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a324e3f --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7020112663495cb88ac2295cd1a49c2bbe5fdb9e6a97075314277aa9114c2582 +size 3164569696 diff --git a/neural-chat-7b-v3-3.i1-Q4_0.gguf b/neural-chat-7b-v3-3.i1-Q4_0.gguf new file mode 100644 index 0000000..ff4689b --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264ceffc60876403ed743a8854831d862df154e0f002a51eec887757cba62a60 +size 4123598944 diff --git a/neural-chat-7b-v3-3.i1-Q4_0_4_4.gguf b/neural-chat-7b-v3-3.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..159eaf6 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cdae164b0de9cfca660fe089ee8b9aadfb2f31446aba0cde39b18abd827b3b0 +size 4108918880 diff --git a/neural-chat-7b-v3-3.i1-Q4_0_4_8.gguf b/neural-chat-7b-v3-3.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..5187d9d --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:326709cc30fd9f4481f99169dfb72d997887ca5e7d2581cd825d287641fece56 +size 4108918880 diff --git a/neural-chat-7b-v3-3.i1-Q4_0_8_8.gguf b/neural-chat-7b-v3-3.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..e84b247 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da8e3705c3dd8d01c68e1ab5df7d0e8ce207c37f46baba913a2159a18ff872c6 +size 4108918880 diff --git a/neural-chat-7b-v3-3.i1-Q4_K_M.gguf b/neural-chat-7b-v3-3.i1-Q4_K_M.gguf new file mode 100644 index 0000000..982010b --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a686916cbd93f925a9376cbe174c785f3afe01aacb42fe499bc1d4980644c270 +size 4368441440 diff --git a/neural-chat-7b-v3-3.i1-Q4_K_S.gguf b/neural-chat-7b-v3-3.i1-Q4_K_S.gguf new file mode 100644 index 0000000..caf798c --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17b3dbc63d651efc313f4e70a9ef835dc61cabc2bb1dada104e26023cbfe85e5 +size 4140376160 diff --git a/neural-chat-7b-v3-3.i1-Q5_K_M.gguf b/neural-chat-7b-v3-3.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ce8e748 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f8fa0065b304a517dc3779e9d6647f35c329c2fc09e1c239fc060857de0baad +size 5131411552 diff --git a/neural-chat-7b-v3-3.i1-Q5_K_S.gguf b/neural-chat-7b-v3-3.i1-Q5_K_S.gguf new file mode 100644 index 0000000..7772ba5 --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb8b4a71030b08c301e60ed7f69128f221e941dd73b3bd9e560ed48b9b1f0086 +size 4997718112 diff --git a/neural-chat-7b-v3-3.i1-Q6_K.gguf b/neural-chat-7b-v3-3.i1-Q6_K.gguf new file mode 100644 index 0000000..f53d16f --- /dev/null +++ b/neural-chat-7b-v3-3.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bef8989d8fc63be382489b1579b965213db1e6da54d4fe50c8bd1c2cbb12813 +size 5942067296