GPTQ model commit, split due to HF 50GB 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
+bloomchat-splitaa filter=lfs diff=lfs merge=lfs -text
+bloomchat-splitab filter=lfs diff=lfs merge=lfs -text
+bloomchat-splitac filter=lfs diff=lfs merge=lfs -text

bloomchat-splitaa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfa05963c9410113ed88e3df0694041128857e5c1f8c482bd16bc8b6e9cdab7c
+size 48318382080

bloomchat-splitab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:709f827ffc00e9e144357cf689d34c6c465f180cba4f51347b278135eaea9b62
+size 48318382080

bloomchat-splitac

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a99b52f59c350ba4f59dfc0afdc81951300fea3de8ed5fcfa2b854a1b2d1a13e
+size 4145564712

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/home/ubuntu/models/sambanovasystems_BLOOMChat-176B-v1",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": false,
+  "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,
+  "return_dict": false,
+  "slow_but_exact": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.30.2",
+  "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
+}