diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..70731a2aa0dc4b787628c49e1bc60954dd5b45bd 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,5 @@ saved_model/**/* 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 +onnx/language_model.onnx_data filter=lfs diff=lfs merge=lfs -text +onnx/language_model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text diff --git a/onnx/embed_tokens.onnx b/onnx/embed_tokens.onnx new file mode 100644 index 0000000000000000000000000000000000000000..7434175fded71f0c962fff286b1a86915431f69c --- /dev/null +++ b/onnx/embed_tokens.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b65c83b08bd82cfb4ef6009755244316374f593970625761957278f12920c6 +size 838861039 diff --git a/onnx/embed_tokens_bnb4.onnx b/onnx/embed_tokens_bnb4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8fc92817ef806dda08bd9341cdd246655d168451 --- /dev/null +++ b/onnx/embed_tokens_bnb4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9695e9ebef47e981674f9d318192fae971f66c5605f533457f2926cd1a150833 +size 838861058 diff --git a/onnx/embed_tokens_fp16.onnx b/onnx/embed_tokens_fp16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..05c07dc653da8543dd3b0b4851e22a95735815ef --- /dev/null +++ b/onnx/embed_tokens_fp16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e13f081811bb240f55c4a25884b8b86f72aa379848c95f8feafb0d712f2283e +size 419430789 diff --git a/onnx/embed_tokens_int8.onnx b/onnx/embed_tokens_int8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..dad1b6f2c5089c449eb8e1fe50be29b1a5b93991 --- /dev/null +++ b/onnx/embed_tokens_int8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ad3a9956a9acb69cbccc724608644a13bfe1a075dc094af71f0f4e0432e6ff +size 209715680 diff --git a/onnx/embed_tokens_q4.onnx b/onnx/embed_tokens_q4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8fc92817ef806dda08bd9341cdd246655d168451 --- /dev/null +++ b/onnx/embed_tokens_q4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9695e9ebef47e981674f9d318192fae971f66c5605f533457f2926cd1a150833 +size 838861058 diff --git a/onnx/embed_tokens_q4f16.onnx b/onnx/embed_tokens_q4f16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..60732d85969a3c60ec8e19e6cd218947b1278228 --- /dev/null +++ b/onnx/embed_tokens_q4f16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fb1bca15de5024f723485b8e09fcea6d5d3eea1a6ffa9ccf11883259237748d +size 419430808 diff --git a/onnx/embed_tokens_quantized.onnx b/onnx/embed_tokens_quantized.onnx new file mode 100644 index 0000000000000000000000000000000000000000..dad1b6f2c5089c449eb8e1fe50be29b1a5b93991 --- /dev/null +++ b/onnx/embed_tokens_quantized.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ad3a9956a9acb69cbccc724608644a13bfe1a075dc094af71f0f4e0432e6ff +size 209715680 diff --git a/onnx/embed_tokens_uint8.onnx b/onnx/embed_tokens_uint8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..dad1b6f2c5089c449eb8e1fe50be29b1a5b93991 --- /dev/null +++ b/onnx/embed_tokens_uint8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ad3a9956a9acb69cbccc724608644a13bfe1a075dc094af71f0f4e0432e6ff +size 209715680 diff --git a/onnx/gen_head.onnx b/onnx/gen_head.onnx new file mode 100644 index 0000000000000000000000000000000000000000..0ace5e4fa3bfebab9f66d9eb9a9e01aa1c7d73f9 --- /dev/null +++ b/onnx/gen_head.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c49d215163009f0a15f0861f8c31732650123f3d669cfa93d760f0dcd83b46c0 +size 151070926 diff --git a/onnx/gen_head_bnb4.onnx b/onnx/gen_head_bnb4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..0ebf7df61422c2902397c0aef5a3f21b587a0509 --- /dev/null +++ b/onnx/gen_head_bnb4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84ffe51f9602350f35f5fa1f9099fe459714de6823f7f12a6dfe88760d37d8e1 +size 21309979 diff --git a/onnx/gen_head_fp16.onnx b/onnx/gen_head_fp16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8192239b8c00ee5e9725d49be88ea7793c87e781 --- /dev/null +++ b/onnx/gen_head_fp16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59563c2c872555def6959653ad078bfe93d3484f6f9e692e25160ac2dadf4eae +size 75536078 diff --git a/onnx/gen_head_int8.onnx b/onnx/gen_head_int8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..190a2fe13578886cc1930e7587070ce8b251400f --- /dev/null +++ b/onnx/gen_head_int8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:151beac801a597cf738867c003d9bc145dd166c5640a3517882bb7650498f6ba +size 37826612 diff --git a/onnx/gen_head_q4.onnx b/onnx/gen_head_q4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..0db8a1083cf169e68763d27522ef0dea20d93e4a --- /dev/null +++ b/onnx/gen_head_q4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f447b2f77cdfa88c0675553423fce2401a3612ee87707cd258827fa315f4c657 +size 23669258 diff --git a/onnx/gen_head_q4f16.onnx b/onnx/gen_head_q4f16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..ca6605a028f4748454d4f1cd60b9e83deb923d55 --- /dev/null +++ b/onnx/gen_head_q4f16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43172cb13fd4061f792be204bab7c39a542622ae2e449067a6fe662e5f66a902 +size 21273332 diff --git a/onnx/gen_head_quantized.onnx b/onnx/gen_head_quantized.onnx new file mode 100644 index 0000000000000000000000000000000000000000..190a2fe13578886cc1930e7587070ce8b251400f --- /dev/null +++ b/onnx/gen_head_quantized.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:151beac801a597cf738867c003d9bc145dd166c5640a3517882bb7650498f6ba +size 37826612 diff --git a/onnx/gen_head_uint8.onnx b/onnx/gen_head_uint8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d2df0ad7e6580c032c2d8c1ea339219a91d41d71 --- /dev/null +++ b/onnx/gen_head_uint8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cbb8efeab921092c8fc68668658290c1f935428d28d668b025876bdf4c4d11e +size 37826612 diff --git a/onnx/gen_img_embeds.onnx b/onnx/gen_img_embeds.onnx new file mode 100644 index 0000000000000000000000000000000000000000..e34e7ab4ec19694a61879417d05d15e0ecc27e35 --- /dev/null +++ b/onnx/gen_img_embeds.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9217a706c0676b16d0aa5caeb6e103eec78cc9f221d245105579d2c65bc5cb74 +size 17385630 diff --git a/onnx/gen_img_embeds_bnb4.onnx b/onnx/gen_img_embeds_bnb4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..f76690705d1c02f6588d3b47f52a8411f7294453 --- /dev/null +++ b/onnx/gen_img_embeds_bnb4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84dd408c2c3819b35c95f608fa2521b474d1db8bedfedaef26b5819b7b5eaeef +size 2911712 diff --git a/onnx/gen_img_embeds_fp16.onnx b/onnx/gen_img_embeds_fp16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..0e79ab22414c0534834a18fad1c7cb87163f3e8f --- /dev/null +++ b/onnx/gen_img_embeds_fp16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1501cac82ce8d4b26b27af5f9f993b1575e27a42a09d07ac508feaebb79aedde +size 8695058 diff --git a/onnx/gen_img_embeds_int8.onnx b/onnx/gen_img_embeds_int8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..c6b8ce4a29da51f0564a9561d282e3eafe9a4aef --- /dev/null +++ b/onnx/gen_img_embeds_int8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4151d9a8f8ef977c4c16221b9a5d61783485d6f8b00b403b542ebd3dc73e4613 +size 4363472 diff --git a/onnx/gen_img_embeds_q4.onnx b/onnx/gen_img_embeds_q4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..661a0bbb6ee8194378de632303f539984535bc82 --- /dev/null +++ b/onnx/gen_img_embeds_q4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:159725b8d897c65d83448fa098259096893410189866e78fd61750048ce0d29f +size 3205586 diff --git a/onnx/gen_img_embeds_q4f16.onnx b/onnx/gen_img_embeds_q4f16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..96bf73a992f2a3b792ce59615928d2222f88e517 --- /dev/null +++ b/onnx/gen_img_embeds_q4f16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9598e2a95a9463e0d72342b05996afef29de50f48fdf6fcd9a760d506840897f +size 2669722 diff --git a/onnx/gen_img_embeds_quantized.onnx b/onnx/gen_img_embeds_quantized.onnx new file mode 100644 index 0000000000000000000000000000000000000000..c6b8ce4a29da51f0564a9561d282e3eafe9a4aef --- /dev/null +++ b/onnx/gen_img_embeds_quantized.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4151d9a8f8ef977c4c16221b9a5d61783485d6f8b00b403b542ebd3dc73e4613 +size 4363472 diff --git a/onnx/gen_img_embeds_uint8.onnx b/onnx/gen_img_embeds_uint8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..47e5ecd40d4f1dde296e818301bf53531827cc79 --- /dev/null +++ b/onnx/gen_img_embeds_uint8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:becea3b8f33052093d5b36878e35cf4cbcb93037cc394faa41abfb4b10b5e6e8 +size 4363474 diff --git a/onnx/image_decode.onnx b/onnx/image_decode.onnx new file mode 100644 index 0000000000000000000000000000000000000000..426c091cc73af43502d5e542655b7bcf83166eb1 --- /dev/null +++ b/onnx/image_decode.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5395223c9212df6dca1f29a540f7c5c78971c0d2ee7a3ac88a4e8f5f2b227fb8 +size 170460651 diff --git a/onnx/image_decode_bnb4.onnx b/onnx/image_decode_bnb4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..feb825eaba5223518a838d828553075e7bf40170 --- /dev/null +++ b/onnx/image_decode_bnb4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:850954e84b253682a8ad8c582ffe07f0b295fbed5ff3e69e02e33f64aafd358d +size 170460670 diff --git a/onnx/image_decode_fp16.onnx b/onnx/image_decode_fp16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d7379dabf1be19e382518cefbad54df6a17ecb96 --- /dev/null +++ b/onnx/image_decode_fp16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c29001e88eb560f2fa17736784fb33e15ba6933612321463d7818234eb84a09 +size 85297169 diff --git a/onnx/image_decode_int8.onnx b/onnx/image_decode_int8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..1b36f1ade0364d82066d7cb232a218fa4be307ca --- /dev/null +++ b/onnx/image_decode_int8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f0628808dadc9ff3f3fbbbc1896d5b950673da570e66a7a8c48c6748a4e5b95 +size 42936957 diff --git a/onnx/image_decode_q4.onnx b/onnx/image_decode_q4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..feb825eaba5223518a838d828553075e7bf40170 --- /dev/null +++ b/onnx/image_decode_q4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:850954e84b253682a8ad8c582ffe07f0b295fbed5ff3e69e02e33f64aafd358d +size 170460670 diff --git a/onnx/image_decode_q4f16.onnx b/onnx/image_decode_q4f16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..04cca7922ded3cf38e5abd2223a4ec7e29112141 --- /dev/null +++ b/onnx/image_decode_q4f16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321080bbfc750e49ada58e5b6e3bdb7b8e11c511d38b799f788c121eae9ce6f2 +size 85297188 diff --git a/onnx/image_decode_quantized.onnx b/onnx/image_decode_quantized.onnx new file mode 100644 index 0000000000000000000000000000000000000000..329d84741277034eb64920d9e15d90cc9ea1630a --- /dev/null +++ b/onnx/image_decode_quantized.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:103729cd44ffdd00e1e35ab7938ce938e55363ffa8af993dc64044976303cc06 +size 42936990 diff --git a/onnx/image_decode_uint8.onnx b/onnx/image_decode_uint8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..329d84741277034eb64920d9e15d90cc9ea1630a --- /dev/null +++ b/onnx/image_decode_uint8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:103729cd44ffdd00e1e35ab7938ce938e55363ffa8af993dc64044976303cc06 +size 42936990 diff --git a/onnx/language_model.onnx b/onnx/language_model.onnx new file mode 100644 index 0000000000000000000000000000000000000000..13717eee08ad7c856e6612d4a9c7b108697028ac --- /dev/null +++ b/onnx/language_model.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6170cb9b0baedba74a30585ef1cb0ed6bedd90c1ad3b83b74b23e7f5959f41a3 +size 181661 diff --git a/onnx/language_model.onnx_data b/onnx/language_model.onnx_data new file mode 100644 index 0000000000000000000000000000000000000000..9cf91251f57c3e74654cde0bb4273ccdcfe4eeaf --- /dev/null +++ b/onnx/language_model.onnx_data @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e831d6c63daf4bdfc8526a370a8bc088a0ae3d18a6148e6aad0ad15d6621e00 +size 4941291520 diff --git a/onnx/language_model_bnb4.onnx b/onnx/language_model_bnb4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..f05a77da50781d0fc51881b45f0b31fb0ef2b99a --- /dev/null +++ b/onnx/language_model_bnb4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b98021fe28068323f52f373cdfad5cb1948f7e675a3406ab1e80c382e8557174 +size 702623304 diff --git a/onnx/language_model_fp16.onnx b/onnx/language_model_fp16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..c739c513bfba11abc737a9fda991465825f06078 --- /dev/null +++ b/onnx/language_model_fp16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7014bcaa5c53fdb25609af3d1ff2a0bd3116ca203d4124b37d1e2094ba3b4cf3 +size 377865125 diff --git a/onnx/language_model_fp16.onnx_data b/onnx/language_model_fp16.onnx_data new file mode 100644 index 0000000000000000000000000000000000000000..6d51fb04ff39612278d11d2a82af292e5a929eb1 --- /dev/null +++ b/onnx/language_model_fp16.onnx_data @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd8cedadedf3b7138eb6d7e7ca9958d85e6c5de510f73cc111c9d46a160eaafc +size 2092957696 diff --git a/onnx/language_model_int8.onnx b/onnx/language_model_int8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..e6d8edfdb274df670fc4b49de355921ae6f7adf6 --- /dev/null +++ b/onnx/language_model_int8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d8c4a9346edd362e836407d8453a0dc1b6157bc6eed5e66f497786e3c0f875 +size 1242273839 diff --git a/onnx/language_model_q4.onnx b/onnx/language_model_q4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..5a28ccd4a1c626e5e17b5f8ecdf54ad3fe7a7351 --- /dev/null +++ b/onnx/language_model_q4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acdf40d04c8b0a42afbc1289332ac706b9ff2a9d7dd4bbd4806a5e5c9e388ca0 +size 779633963 diff --git a/onnx/language_model_q4f16.onnx b/onnx/language_model_q4f16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..780393b8295e4611b8a7796a17133ee8b6ddbffc --- /dev/null +++ b/onnx/language_model_q4f16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda78684bd85d4beda5558179e2a5da960f13969f111a8024f75be11cdef9a61 +size 698231365 diff --git a/onnx/language_model_quantized.onnx b/onnx/language_model_quantized.onnx new file mode 100644 index 0000000000000000000000000000000000000000..cd6ad2259b497d93d8f4074915f7ebf9b6e1feb4 --- /dev/null +++ b/onnx/language_model_quantized.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29ac163aadb26bcd7667e036054bffac057ee2802711e7efaf4a025b09f35aad +size 1242273924 diff --git a/onnx/language_model_uint8.onnx b/onnx/language_model_uint8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..cd6ad2259b497d93d8f4074915f7ebf9b6e1feb4 --- /dev/null +++ b/onnx/language_model_uint8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29ac163aadb26bcd7667e036054bffac057ee2802711e7efaf4a025b09f35aad +size 1242273924 diff --git a/onnx/lm_head.onnx b/onnx/lm_head.onnx new file mode 100644 index 0000000000000000000000000000000000000000..2550e242577a80947bb6f8a97ab1b5ca11b6bc46 --- /dev/null +++ b/onnx/lm_head.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35120d0b88a8fb243b7edb7d1aeda1b0e288ef5137f996836046794e195fc0fc +size 838861112 diff --git a/onnx/lm_head_bnb4.onnx b/onnx/lm_head_bnb4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8edb16bcfd7178357663db6cf336bc9996542f36 --- /dev/null +++ b/onnx/lm_head_bnb4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b79815938f13327eed649aaf70220902b7e44e68dd1ad71ed7e5e5b7aa106a4 +size 117965285 diff --git a/onnx/lm_head_fp16.onnx b/onnx/lm_head_fp16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..ae95bbd9da5950bff5c2e141b2315ebd7c853ce0 --- /dev/null +++ b/onnx/lm_head_fp16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:215ccbdb0efd6067e68b3057ba798802727d36795b064fd95dea5a4c79f8a733 +size 419430700 diff --git a/onnx/lm_head_int8.onnx b/onnx/lm_head_int8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..5ab413179066d13bcffe959396a81dc368d2ccb9 --- /dev/null +++ b/onnx/lm_head_int8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:784f909b304956a9a6c5ef624f2474f2a1fb30e01b1f5b50a05e319bb3989e9a +size 209716198 diff --git a/onnx/lm_head_q4.onnx b/onnx/lm_head_q4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..2b7b93f61b1bf90fbf85bcccb1f2a3360d340065 --- /dev/null +++ b/onnx/lm_head_q4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1436d760db25589d6f27528e3841500b3294b47e69c15318182baa1aa6470e4 +size 131072477 diff --git a/onnx/lm_head_q4f16.onnx b/onnx/lm_head_q4f16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..aa56bb3406b4cfe16ccf969a4131f78f1368cbe4 --- /dev/null +++ b/onnx/lm_head_q4f16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eacee1c23476f0315d44742e41b135d660f5d94747abb35c8e73dbbfcab44d3a +size 117965517 diff --git a/onnx/lm_head_quantized.onnx b/onnx/lm_head_quantized.onnx new file mode 100644 index 0000000000000000000000000000000000000000..5ab413179066d13bcffe959396a81dc368d2ccb9 --- /dev/null +++ b/onnx/lm_head_quantized.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:784f909b304956a9a6c5ef624f2474f2a1fb30e01b1f5b50a05e319bb3989e9a +size 209716198 diff --git a/onnx/lm_head_uint8.onnx b/onnx/lm_head_uint8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..59d06d9187a2da8f24ae9f49f06ace1e4dcb5366 --- /dev/null +++ b/onnx/lm_head_uint8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca7750094682c6ef81e4db6e3f0f5abed04d60eae99843ab1039aafed17eddc +size 209716198 diff --git a/onnx/prepare_inputs_embeds.onnx b/onnx/prepare_inputs_embeds.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8739c78ecbaa7d533142ebd62daf8bb40fb6f0e0 --- /dev/null +++ b/onnx/prepare_inputs_embeds.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:537e9e91316ea303ab1809af8f02034d7c6a22a983340210e8ad3979ed67a0fe +size 2079328482 diff --git a/onnx/prepare_inputs_embeds_bnb4.onnx b/onnx/prepare_inputs_embeds_bnb4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d54b39e4bc834c670aec3d8ad902178f91b00c6e --- /dev/null +++ b/onnx/prepare_inputs_embeds_bnb4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f479e38eebfaa27cbc99a0d5c7c7a83667de30dc21d4b599abab7ea0db15a3d7 +size 1019626816 diff --git a/onnx/prepare_inputs_embeds_fp16.onnx b/onnx/prepare_inputs_embeds_fp16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..75f4324e1612dc757560c4df78547a4abe3c48b1 --- /dev/null +++ b/onnx/prepare_inputs_embeds_fp16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:108e1b55fec0c955e36d63aee7e4ae6eb6f1a4bceb865efcc36db64ebe337ea5 +size 1039930756 diff --git a/onnx/prepare_inputs_embeds_int8.onnx b/onnx/prepare_inputs_embeds_int8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..69ba8c850637ebc78449635cbbd49cfc041b55ba --- /dev/null +++ b/onnx/prepare_inputs_embeds_int8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e0936c207c594c8bc7e8aca989323152bcd8be343f7939e2eebee28fd585657 +size 523348475 diff --git a/onnx/prepare_inputs_embeds_q4.onnx b/onnx/prepare_inputs_embeds_q4.onnx new file mode 100644 index 0000000000000000000000000000000000000000..33bd2463ff947c34b84222e505a7a1fb6409c5f0 --- /dev/null +++ b/onnx/prepare_inputs_embeds_q4.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd44c883d250215241fa3970be1ef9e02876b79d2fe20e18a24eeadc465255ce +size 1038893591 diff --git a/onnx/prepare_inputs_embeds_q4f16.onnx b/onnx/prepare_inputs_embeds_q4f16.onnx new file mode 100644 index 0000000000000000000000000000000000000000..7df8c9d91524150c42e75e21d2cd37d8ba4992e8 --- /dev/null +++ b/onnx/prepare_inputs_embeds_q4f16.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca0aa806b897d7a2778dcda13c7f4a049adeded60d00518abf19f0ecf2f6f5d +size 596981360 diff --git a/onnx/prepare_inputs_embeds_quantized.onnx b/onnx/prepare_inputs_embeds_quantized.onnx new file mode 100644 index 0000000000000000000000000000000000000000..f21a66392cd470b8112c0d0991037177148dc169 --- /dev/null +++ b/onnx/prepare_inputs_embeds_quantized.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84a6be05146df9fac6a4058bad17de391abc9e2663f2ab1b092ff0e484697811 +size 523348514 diff --git a/onnx/prepare_inputs_embeds_uint8.onnx b/onnx/prepare_inputs_embeds_uint8.onnx new file mode 100644 index 0000000000000000000000000000000000000000..f21a66392cd470b8112c0d0991037177148dc169 --- /dev/null +++ b/onnx/prepare_inputs_embeds_uint8.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84a6be05146df9fac6a4058bad17de391abc9e2663f2ab1b092ff0e484697811 +size 523348514