Upload BloomForCausalLM

config.json

@@ -1,32 +1,32 @@
 {
-  "_name_or_path": "cerebras/cerebras-gpt-256M",
-  "activation_function": "gelu",
+  "_name_or_path": "bigscience/bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
   "architectures": [
-    "GPT2LMHeadModel"
+    "BloomForCausalLM"
   ],
-  "attn_pdrop": 0.0,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.0,
-  "eos_token_id": 50256,
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_embd": 1088,
-  "n_head": 17,
-  "n_inner": 4352,
-  "n_layer": 14,
-  "n_positions": 2048,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.0,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
   "torch_dtype": "float32",
   "transformers_version": "4.28.1",
+  "unk_token_id": 0,
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 250880
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
   "transformers_version": "4.28.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5332391ae9118080a58abada1490c56c8d3a2b2f007835d1047a589d860e94
-size 1082693357
+oid sha256:3ee6256b388728cb87c2f4568a319c9e0531ea3e476ad8d74314fed74dff691c
+size 2236953377