Upload RWForCausalLM

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "tiiuae/falcon-7b-instruct",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-7b-instruct--configuration_RW.RWConfig",
+    "AutoModelForCausalLM": "tiiuae/falcon-7b-instruct--modelling_RW.RWForCausalLM"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "RefinedWebModel",
+  "multi_query": true,
+  "n_head": 71,
+  "n_layer": 32,
+  "parallel_attn": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0.dev0"
+}

pytorch_model-00001-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d462e8627ae7beae4e6346d388443c7abdeec09b45e0cfb00aca1bc6ce3d2d
+size 1917140013

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:846d402e489756cb0bfb3dd1c711ada5a3d1463d31b8f924c0e4ad0a575a8f64
+size 1986955527

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b63bd5a20b52c406db18b6fbd53c13927c29147a2408a1dbfb491a8d162b40
+size 1905508597

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d9f71e8ae1e28cfd908698bf050b4d20b290ea230e40b4b44e7efce470d568
+size 1905527449

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631fa31e59bcd02188fb5426e5013ad9593632205478fde13817fdfd82770b56
+size 1986955591

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f28e002cb9b7ceaff02b4c8561f5a42a4dfce3100af3e9484e3eca5ca2af342
+size 1905508597

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:639b892d96d658574e87323662fb4229a81d24eecc7d72bbc7c7d12646eb6baa
+size 1407611877

pytorch_model.bin.index.json

@@ -0,0 +1,203 @@
+{
+  "metadata": {
+    "total_size": 13264090496
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.30.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.30.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.30.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.31.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.31.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.31.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.ln_f.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.ln_f.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00007.bin"
+  }
+}