Upload 11 files

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bigscience/bloomz-7b1",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 30,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 4,
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc8dbd6b2bb6f55143876707232f82e02c4044fbd98e2ab04fef1af342debca
+size 4975258008

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d19bdf9a5872ab3df7ed982c1bf863d89b15b1543b0bdf74026e2dc4ca3f2cf
+size 4866712640

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c66d241a29663e5b0ed502d314222cff09f214237f7d0998a949fbc0e94a2b
+size 4296104456

model.safetensors.index.json

@@ -0,0 +1,372 @@
+{
+  "metadata": {
+    "total_size": 14138032128
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.20.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.20.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.20.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.21.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.21.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.21.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.7.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.7.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.7.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.8.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.8.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.8.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.9.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.9.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.9.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
+    "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
+    "transformer.word_embeddings.weight": "model-00001-of-00003.safetensors",
+    "transformer.word_embeddings_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.word_embeddings_layernorm.weight": "model-00001-of-00003.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1062a9564160bf8bc7f8ecd7b142c38dd5e0e7b5e63f5ad33ee4d52537a636
+size 36000

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9131b4dbdfbfcfbe2354cc8d0c174ba8d8f4f1b23daf18c3d61420d8df957e
+size 1064

trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": 8.5859375,
+  "best_model_checkpoint": "model_bloomz_7b_fa_v2/checkpoint-24000",
+  "epoch": 1.25,
+  "eval_steps": 6000,
+  "global_step": 30000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.95e-05,
+      "loss": 8.659,
+      "step": 6000
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 8.6171875,
+      "eval_runtime": 6400.1737,
+      "eval_samples_per_second": 0.937,
+      "eval_steps_per_second": 0.937,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9e-05,
+      "loss": 8.5668,
+      "step": 12000
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 8.59375,
+      "eval_runtime": 4301.219,
+      "eval_samples_per_second": 1.395,
+      "eval_steps_per_second": 1.395,
+      "step": 12000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.8500000000000002e-05,
+      "loss": 8.6004,
+      "step": 18000
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 8.59375,
+      "eval_runtime": 4302.1725,
+      "eval_samples_per_second": 1.395,
+      "eval_steps_per_second": 1.395,
+      "step": 18000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.8e-05,
+      "loss": 8.5774,
+      "step": 24000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 8.5859375,
+      "eval_runtime": 4302.2132,
+      "eval_samples_per_second": 1.395,
+      "eval_steps_per_second": 1.395,
+      "step": 24000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 8.559,
+      "step": 30000
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 8.5859375,
+      "eval_runtime": 6350.3496,
+      "eval_samples_per_second": 0.945,
+      "eval_steps_per_second": 0.945,
+      "step": 30000
+    }
+  ],
+  "logging_steps": 6000,
+  "max_steps": 240000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 6000,
+  "total_flos": 2.22710596632576e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de3f08dd7919da65bc382e201817d46a5e245ac1c2db9f11f45bf134f06f4de2
+size 4664