Upload FalconForCausalLM

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "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,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": true,
+  "n_head": 71,
+  "n_layer": 32,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 32,
+  "num_kv_heads": 71,
+  "parallel_attn": true,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "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": "4.36.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7787a3b09dae2875eaad3a74f104cbd482e01ef0819e8462b573eeaffc7df5
+size 4981285848

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9596acff14788f65f1930d0beb861e3e89156b67a7a3c9bcc9de010c04e1be76
+size 4969690568

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36d3abb7eb7c4be3e02cdeff140889ea3d8f768033936cd2e09f46209b875b6
+size 3892488296

model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 13843441408
+  },
+  "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.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00001-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.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "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.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00002-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.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00002-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.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "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.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.self_attention.query_key_value.weight": "model-00003-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.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "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.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.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "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-00001-of-00003.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00001-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"
+  }
+}