Upload BloomForCausalLM

config.json

@@ -1,26 +1,33 @@
 {
-  "_name_or_path": "ura-hcmut/ura-llama-7b",
+  "_name_or_path": "bigscience/bloomz-560m",
+  "apply_residual_connection_post_layernorm": false,
   "architectures": [
-    "LlamaForCausalLM"
+    "BloomForCausalLM"
   ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "pad_token_id": 0,
+  "layer_norm_epsilon": 1e-05,
+  "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,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "tie_word_embeddings": false,
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.31.0",
+  "unk_token_id": 0,
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 250880
 }

generation_config.json

@@ -2,6 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "pad_token_id": 0,
+  "pad_token_id": 3,
   "transformers_version": "4.31.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:461c054294b716079c27230f800784948c421890cad18b9a7ecfb54e507bf298
-size 7952798001
+oid sha256:000a459797c7b64a7927994d26cfc037b5fab8aa18ecaeac277073e6a3c94157
+size 1118528353