Reduce repo size (#5)

* Remove binary files from git

* Add Makefile

* update

Makefile

@@ -0,0 +1,26 @@
+POETRY_EXISTS := $(shell which poetry &> /dev/null)
+LOCAL_MODEL := testdata/tiny-70M/models/fastertransformer/1
+
+all:
+
+pre-commit:
+	poetry run pre-commit
+
+install-poetry:
+ifndef POETRY_EXISTS
+	curl -sSL https://install.python-poetry.org | POETRY_VERSION=1.4.0 python3 -
+endif
+
+$(LOCAL_MODEL):
+	poetry run python converter/huggingface_gptneox_convert.py \
+		-in_file EleutherAI/pythia-70m-deduped \
+		-o $@ \
+		-i_g 1 -m_n tiny-70M -p 1 -w fp16
+
+setup-development-environment: install-poetry $(LOCAL_MODEL)
+
+up: $(LOCAL_MODEL)
+	docker-compose -f deployment/docker-compose.yml up
+
+dev: $(setup-development-environment) $(LOCAL_MODEL)
+	docker-compose -f deployment/docker-compose.yml -f deployment/docker-compose.dev.yml up --build

README.md

@@ -15,3 +15,12 @@ An opensource / on-prem alternative to GitHub Copilot
 * [`converter`](./converter): Converts a [transformers](https://huggingface.co/docs/transformers) causal LM model into TensorRT / FasterTransformer serving formats.
 * [`preprocess`](./preprocess): Preprocess files into [datasets](https://huggingface.co/docs/datasets)
 * [`tabformer`](./tabformer): *NOT RELEASED* Trainer(PEFT w/RLHF) for tabby models.
+
+## Development
+
+Assuming Linux workstation with:
+1. docker
+2. docker w/ gpu driver
+3. python 3.10
+
+Use `make dev` to start local dev server.

deployment/docker-compose.yml

@@ -14,7 +14,7 @@ services:
       - "5000:5000"
     volumes:
       - ./logs:/logs
-      - ../testdata/gptneox/tokenizer:/tokenizer
+      - ../testdata/tiny-70M/tokenizer:/tokenizer
     links:
       - triton
       - vector
@@ -25,7 +25,7 @@ services:
     command: mpirun -n 1 --allow-run-as-root /opt/tritonserver/bin/tritonserver --model-repository=/model
     shm_size: 1gb
     volumes:
-      - ../testdata/gptneox/models:/model
+      - ../testdata/tiny-70M/models:/model
     deploy:
       resources:
         reservations:

testdata/gptneox/models/fastertransformer/1/1-gpu/config.ini

@@ -1,12 +0,0 @@
-[gptneox]
-model_name = gptneox
-head_num = 12
-size_per_head = 64
-inter_size = 3072
-num_layer = 12
-rotary_embedding = 64
-vocab_size = 50304
-start_id = 0
-end_id = 0
-use_gptj_residual = 0
-weight_data_type = fp32

testdata/gptneox/models/fastertransformer/1/1-gpu/model.final_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c8e8e6b531dabfeff987975cc6c937428139beb7f5699b8b938545716d8eeca7
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.final_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a20104b8a794c5dfa02c2847d25a2697ae60971ea296192dc88a9eaaa479f606
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.0.attention.dense.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3df9dbc92f1617b447db1aa855da24d07660a12c41b22dee002696813b3ebbba
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.0.attention.dense.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5eba16ee6fe2391cf2efcb7162e4662dd905a58cb8610ff32d07813e7575d6fc
-size 2359296

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.0.attention.query_key_value.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:93fb9545a9c7ba88f8927bb1929a3d1d74962d18909ee21225e6b9756c77c332
-size 9216

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.0.attention.query_key_value.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:35a3c434d0af69813352edd06e29e671e8e160de1221a90abe6f308cd6b624ab
-size 7077888

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.0.input_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f324b52b78c5e245f0b68559ac1b40c7c54aa1d48005ca2d12887cb53dbbc9b2
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.0.input_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1c632d0534e7e7e4eab3d843a0a1f0d0f3843aa9b1aefd6b706ad71cf3de08ed
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.0.mlp.dense_4h_to_h.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7e2b220335cce206b3928380f069259c01e382937189f1d86d40641bea319a27
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.0.mlp.dense_4h_to_h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2d59fe9d26e5a6b5bf67a2d631bf012cb67e30a8aee34d5a8b5589a1a3b767d0
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.0.mlp.dense_h_to_4h.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1fb0620b893fc6c19a0d99f7b0b19fcbc81262b7de48532a0cfd74a6c2ceb11e
-size 12288

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.0.mlp.dense_h_to_4h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ea4b2ed74e487155f748f4ad057070db5a1ef9bbe18f155caf05f1889a7db0e4
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.0.post_attention_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0e949431800d44dc72725fb2a14c1b6257df33a087c89a5363504b2796f033ef
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.0.post_attention_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e63fbed352f174592299da93e92c5652b45d4d439aea92867c30bc292d2d8891
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.1.attention.dense.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ca3de5c5d037abd4ba67b56fca3fd35e11f2d3355313684066188424579295f0
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.1.attention.dense.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3bfab993d3877ea0dcdbb35f1bfbe371cf03dee47e23a124e1a3004c9abde182
-size 2359296

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.1.attention.query_key_value.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ef2961811f9b09add00d1acf68bbb0d983b2a266415bcf4167c108cf0af2b162
-size 9216

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.1.attention.query_key_value.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:678d7bdfff7a580935c141a3c8d56121925ad5688ca4839150f7c38aa07b3816
-size 7077888

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.1.input_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:22ee83ada70710e37e74558e042db460e1264b2373ad2272891f8681dd32992f
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.1.input_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ea7f1c9586a26d8b4c7db214c5e036691d24a6aaa0700434e34fb89789e8413d
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.1.mlp.dense_4h_to_h.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ea6d9660941b2258411fa5a95bc2efae46f9b37b2c2677dbfd15fc4bfa97b7d8
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.1.mlp.dense_4h_to_h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:df394855b5b83e6cef0b009b66d75bc6ad9536f63ea81c118821269ddb389811
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.1.mlp.dense_h_to_4h.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:970ccc870e06e091619acffcd71eec44e61ea4e38490094850dea049a55ee4d4
-size 12288

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.1.mlp.dense_h_to_4h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:669ab6458f06db05c0310bf04a4c6681b00faa5ad498d144552ddc8b0ebcad1c
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.1.post_attention_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d77f19d5997955ea3d639595ca6d0a1d94f16eb0a54e6ed9256d151e84a32160
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.1.post_attention_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a208323db32e45ec21cb6fa92754862a2d8db9dc32a148ede730567e1b53ea6d
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.10.attention.dense.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9a991d95e2e3a0c716990227c3fca9617a3762963404bd1bbb1649d6031476d7
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.10.attention.dense.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0948b6eb35b6e388e7ad4cdf315abdf943960d7952dfebbebb4897023cc9a278
-size 2359296

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.10.attention.query_key_value.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4755cff515205a9072c5f00b4e592939e5359f7b535d447bc1f7da44830ce011
-size 9216

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.10.attention.query_key_value.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4b52cdfe8cd07b6f604cd3d848c7ab44efaa5a260441b7da057c42488992b3d6
-size 7077888

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.10.input_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:21b95c5b59d5a99b5f833825f620ddde882036901fda433046d6047a2ad90b51
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.10.input_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2e927894a15e7a284be51655cb46338d98d4ca77378d9f865dc00707ae62758b
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.10.mlp.dense_4h_to_h.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dbf8db67c06bf5b4bb5060f3ace4e5a84ddcc07dea1efc631b93a1244916da4f
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.10.mlp.dense_4h_to_h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7f1d8f3a25a663c5a16d2f390c6db233c808ba22a5617a057f6a0d3350d70260
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.10.mlp.dense_h_to_4h.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:85917a5c6f37da43778c01ddd45b5a444e55265cb17c9156044545c8b378fbbb
-size 12288

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.10.mlp.dense_h_to_4h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:291116b1849ae751a730ebd574548936105cff112b22e1b21a3830640f2b3b6e
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.10.post_attention_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aedc1896553c1017fcbfa8672ba0ce8a26968f288009904e1e91966e6bb90518
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.10.post_attention_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0d0447f6a6765688512b646eccc2fbb742b273d7f6ba14568a813b1e6d13d4d2
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.11.attention.dense.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e9abd3af37bf3a976fa9a6c2fd499e1e852fa8e6f80af55e868dbcc31b92c6cc
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.11.attention.dense.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b249f47f438a6a13ac0b10f42308dc9c84cf53bab9300129140c56d44d8d4296
-size 2359296

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.11.attention.query_key_value.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e13dee33e6ca1356ef5415df8a755832ca0a4d546256ac9beafc954011402756
-size 9216

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.11.attention.query_key_value.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0a14a2b3a7f763772f4401da40419fa7cc1caae2cd7bf416ce9b1ff78501954a
-size 7077888

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.11.input_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bf6231f0316632a83598eee3c9b2dedd42f6086f9aa9948ffb2c2575d42f855b
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.11.input_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:358702cdee17d0d06a44e5d4915f0cc4acd75bbe88e678d1d87e1034a823e24d
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.11.mlp.dense_4h_to_h.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f10daf518dd3b8456cbbfcf0e97df875ac9d818559e29ffbc04b6aae9b00933f
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.11.mlp.dense_4h_to_h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ed18d4ed924f201ef49ba8c84699c81f9bfb6b470f3f58c3eda58e97a6acfb12
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.11.mlp.dense_h_to_4h.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f7240fb1faaa2309b82123f827715f6294b408e97d688d7fc514d7ce14910b8a
-size 12288

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.11.mlp.dense_h_to_4h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:511d7ea871bb241619c99331ac746dceb467be2eb690031bbaec19b9b747c337
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.11.post_attention_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d35391ad45043b104204e9f80c538bf30e17e538fc38b171b37d87f2e368b517
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.11.post_attention_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b0b7d344fd44e6b84f9e01c13493425a1d4d64f1b05360b2af3d62a624e0f56d
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.2.attention.dense.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2b56ec36e26bee33f87dcb99d1a34ad4a4ef314ae186ab0f8905f1cdb17a48fb
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.2.attention.dense.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aaa0e24588292124f8bb75bfc2dba133a93a858389e8ec1c46eddf2831e62619
-size 2359296

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.2.attention.query_key_value.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:96908969d3cb3f937afbd46580634f1fabf6008d9a67db26b9fc6d612a6646eb
-size 9216

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.2.attention.query_key_value.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cf3533607c5762d74c194c9e9de52217b075cabd1429078f98ad125f8e355f60
-size 7077888

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.2.input_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d0700cab36c40ebca68bb21877b9d6d53d2a28e66d81715a45477da730bd52e4
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.2.input_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1c35503aa0ba445d5a3a462f1805351e5e8359d44eb0ab185df4c4a0637540fa
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.2.mlp.dense_4h_to_h.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f9f26d615c213bca2610bf7d4787678422e290a81ace7c6ec02fe1a7a4956e91
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.2.mlp.dense_4h_to_h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:11ae0330f6f55f61fd3ad9f69557b948cc93c4839e2f95779289f525cadb49c9
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.2.mlp.dense_h_to_4h.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6dc26ca0d9dcb757fdedf903d125fa81f08e70ff1b2b337bd17501b034e3af2d
-size 12288

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.2.mlp.dense_h_to_4h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8a2b4ad1773e3415b98242830c3ca6179ed557a716343af3a0ab04cce2fb4fe5
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.2.post_attention_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ed71f49f5cc2bde762ff61cdbecea358229b71aa0de618b3c47fee4e9c15b573
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.2.post_attention_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9ccc5ca8b79956a815cf55d3abacdd19343ebdde6063c57c024e4370693fef82
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.3.attention.dense.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:69192041d0fbdcefd4842aee8f096c9c8be4a7101eb17c832e161f920522dc67
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.3.attention.dense.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eb5b3d7db619c79fd4295d764a428e21be531ab150fb7c609fcac5ffdb44371a
-size 2359296

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.3.attention.query_key_value.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9d340631496cfb8e39db607703096b0de94985b19fc0fdc481a59797c8cf490a
-size 9216

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.3.attention.query_key_value.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e665f2a175bb8d31c013752b165eba2b55d56b1c7f3e9acb67b3a7bdea0fac2d
-size 7077888

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.3.input_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0257d8bd6309e82e3f7187dafbd6addc9906e4cec2d29efc0f124b5502f87963
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.3.input_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bef2513c61a003dadce2563c7a736f9f4b3ec8d80b6e38191da19cf68203a068
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.3.mlp.dense_4h_to_h.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:02b05a1e5131cb6551f826503d57c4c8b5440caefc6e4d8779181930027cea6c
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.3.mlp.dense_4h_to_h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:abf79be083d770af551b7058283cc9980b0d96e14dd02d4454986bdde8a2b94f
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.3.mlp.dense_h_to_4h.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ed59e44938c8f312abc8a4170cd6549951a2c03a72b9cf66d91065636e086c35
-size 12288

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.3.mlp.dense_h_to_4h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3c6249375d6a73f511df02e42db4e575515a36998030c41007b852ea36460675
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.3.post_attention_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:60bf353c91d711ee3e66d54ae42948c63c014b3f55b655ce791b559a2deebc1c
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.3.post_attention_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b46c9094b353c558b3f33921b93d490059d831f6f53936064e1a1810ce804868
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.4.attention.dense.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4df14280a937099176da15dd35d6c0ec033e804568dbafc0e4d478cc46bf606c
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.4.attention.dense.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:303c2535ff82c446017c17a22ce3396d31f904ad03fe8dad96a3624deb92d314
-size 2359296

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.4.attention.query_key_value.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ea6c5b0c270d0829bee70acb8754937a350af1a58391da691846df9f7257ec2b
-size 9216

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.4.attention.query_key_value.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bb35a15bf51a44fecb5e3a91fe92ce34d2d4b624cb8b8cfb66e758ec47326a45
-size 7077888

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.4.input_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ff06b36e63d7d4a99047b6e60dc1eb8ad3285b4c392f8f3b7d670a11e665c3b6
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.4.input_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:de2d76abb0655d8ac2637f5b21d67d1cb1732fc2461716a74b0104edc935d489
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.4.mlp.dense_4h_to_h.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:78da9207b62dd15e7d2a7311238cb467931f4aaaf8c302285308a92399d5eb44
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.4.mlp.dense_4h_to_h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5fad341cc8c6e3e13f9eca3589f06cd7ab65a44a910efe1788ca71a7b038339c
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.4.mlp.dense_h_to_4h.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4eafc33d1ac4361a999b10482dbd696c463d247f8b5d7072bc138af947819fcd
-size 12288

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.4.mlp.dense_h_to_4h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4cb67e4351c871670554e29d6435e6840168f92891fc57f567c5ed668b841b31
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.4.post_attention_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2198459a24e2116aa42c3697ed193e35c3c5efd8fa0f8e73e20bf4055c5f2263
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.4.post_attention_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:768a5c3681076f607b3d8cf4fe4302f139da630759df9ea4d7e2354b3d955f25
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.5.attention.dense.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6aafc8226bb1a02ec0e7b6d8758798f68d92dfccad1ae33a70ba10f61531659f
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.5.attention.dense.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e2764a3bc9493eb3015fdb1fb800341b939509291caefcbd170f549d4553cdcb
-size 2359296

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.5.attention.query_key_value.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ae56c34e09700a3bba5a9f9867dd58df341165c1b29db89702a4cc4f06ef0ce9
-size 9216

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.5.attention.query_key_value.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c51fa1f7a59ab7f1aa4030c2561a5ac29e540ffadc4664c848e2e408351543cd
-size 7077888

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.5.input_layernorm.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f54bf65ac4e921772d05fdbfc438c8d97afb02b342582cdc703b1cc890da3e54
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.5.input_layernorm.weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:217aab7e0e0a9963f2be641b59aba8ed1cfff8b3074acd59866a74b524e8c474
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.5.mlp.dense_4h_to_h.bias.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e4ea893467874708c4db13b747b0befe3a8487240112170422b92e9ac5f35286
-size 3072

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.5.mlp.dense_4h_to_h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:94305ee6204bdb33fb75857cb8709068f30b4d2ca9be1265e44fb89f723dc996
-size 9437184

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.5.mlp.dense_h_to_4h.bias.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8ac52c892d6832a7181ea2dc21dbf97140619adb9e6277b6b1a04d092ac89828
-size 12288

testdata/gptneox/models/fastertransformer/1/1-gpu/model.layers.5.mlp.dense_h_to_4h.weight.0.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:997863f2b1e615af8539a8fe3896e223502190fb6e09c0f4922f4d7b67f3cda5
-size 9437184