Upload FalconForCausalLM

config.json

@@ -28,19 +28,7 @@
   "num_hidden_layers": 32,
   "num_kv_heads": 71,
   "parallel_attn": true,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "bfloat16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.37.0.dev0",
   "use_cache": true,
   "vocab_size": 65024

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974824e9a5e19cd6a5cadc1fd79e5c12245e0bc7993125f374eed9fe8550975b
+size 4992877824

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d86e052620f1151b9e2ae2038f159c80c931dc56990fc5857d7bc7f61d4cd4
+size 4969686200

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4198ca16a4022f80c56474bb0b004ff8cf76c9ff75893d6ac41fb02a9e6355f3
+size 4969686224

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c6ce1fc61d4c38489c22c26413c05c09687aff519a6cb749d6c5f1b9460e97
+size 4969686224

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac412a5547d7583e54f6bd5d69d0d3e6c8156ce711c3cf5e26f54b947893c94c
+size 4969686224

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9320b00a0e71511e334bdada726dae53f294bde6d1814cb3ca1e40ba0173913e
+size 2815283328

model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 27686882816
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.11.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.17.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.2.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.23.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.input_layernorm.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.29.input_layernorm.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.self_attention.dense.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.3.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.30.input_layernorm.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.30.self_attention.dense.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.30.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.31.input_layernorm.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.31.self_attention.dense.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.31.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.5.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.ln_f.bias": "model-00006-of-00006.safetensors",
+    "transformer.ln_f.weight": "model-00006-of-00006.safetensors",
+    "transformer.word_embeddings.weight": "model-00001-of-00006.safetensors"
+  }
+}