Upload GPTQ split into three parts to avoid HF upload limit

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+bloomz-splitaa filter=lfs diff=lfs merge=lfs -text
+bloomz-splitab filter=lfs diff=lfs merge=lfs -text
+bloomz-splitac filter=lfs diff=lfs merge=lfs -text

bloomz-splitaa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b871915e8ef9ce03dc786d56e9e5071c9408c6557f6ec03d3251d89a882fee56
+size 48318382080

bloomz-splitab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7366dc7df355fe42a3438f64211e55432a0b8225a6af89114a0a5e9bfc95560e
+size 48318382080

bloomz-splitac

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476624a94c0ec31b46b08a6364c1147b8ee9e8409dd272ea8c2464e2c3dc21d4
+size 4145564712

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/home/ubuntu/models/bloomz/",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 14336,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 112,
+  "n_layer": 70,
+  "pad_token_id": 3,
+  "pretraining_tp": 4,
+  "seq_length": 2048,
+  "slow_but_exact": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 250880
+}

quantize_config.json

@@ -0,0 +1,10 @@
+{
+  "bits": 4,
+  "group_size": -1,
+  "damp_percent": 0.1,
+  "desc_act": true,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}