commit 4622d6f9c52b510ec80067fe938124514382275f Author: ModelHub XC Date: Mon Aug 10 19:19:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..46c0936 --- /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 +llama-3-nvidia-ChatQA-1.5-8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-nvidia-ChatQA-1.5-8B.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..87fcbf9 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: grimjim/llama-3-nvidia-ChatQA-1.5-8B +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- nvidia +- chatqa-1.5 +- chatqa +- llama-3 +- pytorch +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/grimjim/llama-3-nvidia-ChatQA-1.5-8B + + +static quants are available at https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-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/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF/resolve/main/llama-3-nvidia-ChatQA-1.5-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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..c849db4 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baff1ce4bbff78d6ae7381034a52b7e4f0eb0264b0b8238f50de3785391f94fb +size 4988157 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ1_M.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..d65557f --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf499b6495d06b9dfec7aed737afa2bc189621d63c398a9449083d34b86e59dd +size 2161972832 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ1_S.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..a8799a3 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:427770dd621faf7b33885c6868295f3f2f07bc982cafc2e3bb4419c1294c42c1 +size 2019628640 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_M.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..9237bad --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0a4c8a35a557c66519ec129f390a6966c7747693cfaa3a17b896f8465dc785d +size 2948281952 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_S.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..6142117 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2852fab73e0a1eb3ccfa0d62cb73f2386368002d205ba4ee35ae9d5e0d206f46 +size 2758489696 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_XS.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3941ed8 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef49d01c6740f8cd2452ca1e138cdd520ea652b329b4a7e4fb5e04474c95dfa5 +size 2605782624 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_XXS.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8c10c76 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7098c961c242aafd6b64a77e0c7df2fc6d0eac1f93e998e844a82eb3cbb679f5 +size 2399213152 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_M.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..8e65008 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af31f344a7d72e56f37b6956fe48a32ec2377023cbce2c03f0299c290e666ada +size 3784824416 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_S.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..0145c52 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19b32d42d3c52e6d1bf22cc4f12599bfa88f89c0f64071d12a6e7a469b39ff3 +size 3682326112 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_XS.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..799314e --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67af92145e72511268b90e2b1737db5fb0a3fc710fc9875d6a394427ebae1797 +size 3518748256 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_XXS.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..eb7ff03 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e843e7c964d7ac83f2c900015fd4281600a3d08a3cfceb0dccf12cbb9488102 +size 3274913376 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ4_NL.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..8cad586 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8db0ad10297448e486a8a532276f38e9c6d80810ccf2298174de0007989d7e4c +size 4677989984 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ4_XS.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..32505f0 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caaed896de16c531b7ab2f66c4a3ed725b80b7cec743335ef5a61300ee815090 +size 4447663712 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-Q2_K.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q2_K.gguf new file mode 100644 index 0000000..41c6488 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6bbd818a4526f6eeb3a2b5fec913880b45ce442ac7768718ddc8acd779965e +size 3179132512 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-Q2_K_S.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..9c8fa1d --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ddda38a9bf26bb2abaed6667dcf3c499f31d793a58cb0f21aeecaf0fe2f548e +size 2988815968 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_L.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e2fdbbe --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9f3f5f007e87c8d6f34e3e075c58c7f1084ef83d6f413ae808c3aa4a9cbad6 +size 4321957472 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_M.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a752a17 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356f1901f5a7968352d1a55b9fd0f609f526844be8158984b32606139f86c3ab +size 4018919008 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_S.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e55d9d6 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca080ffcb5a0f6e049be007fe18614f0452bd301610ccce0a64a00a81cb0a0a +size 3664500320 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_0.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_0.gguf new file mode 100644 index 0000000..527571a --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2ae5c7e898687f745451962c561c65006bab06e45f0944c0477f89d5af355d5 +size 4675892832 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_1.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_1.gguf new file mode 100644 index 0000000..1bea4e8 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbf08d2eb0a02257715db0b203501d0c3a644424839f2691e2582a8e97aacfa8 +size 5130253920 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_K_M.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..bf3a218 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a31b161eaad50228b9e1214db80ce4aeeab31a37d4f0ddd5c5d43aa8686c354 +size 4920735328 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_K_S.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b342ecd --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:129ca8279b0cb947822c69671f8b91ea91d05e047c6d0893619dfe1606e26644 +size 4692670048 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-Q5_K_M.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..d992d42 --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d7ee28784a42b8e70191bfb2eaa78a36abd53e1fde7c64322c36d36ac1760d8 +size 5732988512 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-Q5_K_S.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b9cb86a --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90ae116a9feb6725f30167c6c1e02dc14e7560d6fa0bddfb0ff5213f9d012f1c +size 5599295072 diff --git a/llama-3-nvidia-ChatQA-1.5-8B.i1-Q6_K.gguf b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q6_K.gguf new file mode 100644 index 0000000..35a08af --- /dev/null +++ b/llama-3-nvidia-ChatQA-1.5-8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b555497c2e67c6adb5d542eaa4bd5e65b4ca1e346a7090b336c4476def7dd225 +size 6596007520