Add GPTQ 4-bit/None/True, sharded

config.json

@@ -1,38 +1,49 @@
 {
-    "alibi": false,
-    "architectures": [
-        "FalconForCausalLM"
-    ],
-    "attention_dropout": 0.0,
-    "bias": false,
-    "bos_token_id": 11,
-    "eos_token_id": 11,
-    "hidden_dropout": 0.0,
-    "hidden_size": 14848,
-    "initializer_range": 0.02,
-    "layer_norm_epsilon": 1e-05,
-    "model_type": "falcon",
-    "multi_query": true,
-    "new_decoder_architecture": true,
-    "num_attention_heads": 232,
-    "num_hidden_layers": 80,
-    "num_kv_heads": 8,
-    "parallel_attn": true,
-    "torch_dtype": "bfloat16",
-    "transformers_version": "4.32.0",
-    "use_cache": true,
-    "vocab_size": 65024,
-    "pretraining_tp": 1,
-    "pad_token_id": 0,
-    "quantization_config": {
-        "bits": 4,
-        "group_size": 128,
-        "damp_percent": 0.1,
-        "desc_act": true,
-        "sym": true,
-        "true_sequential": true,
-        "model_name_or_path": null,
-        "model_file_base_name": "model",
-        "quant_method": "gptq"
-    }
-}
+  "_name_or_path": "/workspace/process/tiiuae_falcon-180b/gptq/main/",
+  "alibi": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 14848,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": true,
+  "num_attention_heads": 232,
+  "num_hidden_layers": 80,
+  "num_kv_heads": 8,
+  "pad_token_id": 0,
+  "parallel_attn": true,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": null,
+    "damp_percent": 0.1,
+    "dataset": null,
+    "desc_act": true,
+    "disable_exllama": true,
+    "group_size": 128,
+    "model_seqlen": null,
+    "module_name_preceding_first_block": null,
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": false
+  },
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.0",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 11,
   "eos_token_id": 11,
-  "transformers_version": "4.32.0"
+  "transformers_version": "4.33.0"
 }

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b72c16c3020e6c6ba595af49a5d41938936ede036c1214472bb294845c77176
+size 9995023968

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de24bd50add4363f709fce98dd718c4dbf8cc48c71acf55193cf085d158bb12
+size 9941818992

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5b8be636cb0462e20cdbe2e042ee31af1c6bbdfaf95f257a39f7016fc59ba4e
+size 9927772520

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6247876eded62ec61414ef725ce95d04b432aa817fe35c4c6d41eadc079d83ab
+size 9690586856

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b886728e0c5ae616fadfae808d1e3bad06072bbd3db7d9b163c449ca89480c49
+size 9927772520

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4af2bb81bfd5500a00086df1e6649fac2bbfdafaea5b357b1c23f5f916dd05
+size 9690586856

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d85b9c0abb8eb2d9a556205ac6bab8054ee143b37087bb07bc8a5977aa71c209
+size 9927772520

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83db42dc982e7a97f86ced624d5a78a2720da7dde5442964ef1a24392e2e8a12
+size 9690586856

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f3c9563c9ca4704b9e0e9bc31991d52d11a2028d06bcdd84c80d4e93173b21
+size 9927772520

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf470517be3ecd77a586cfa365d98103baa135eefbb4cec079c40365dba7692
+size 5533009736