Upload MosaicGPT

config.json

@@ -1,29 +1,46 @@
 {
-  "apply_residual_connection_post_layernorm": false,
-  "attention_dropout": 0.0,
-  "attention_softmax_in_fp32": true,
-  "bias_dropout_fusion": true,
+  "_name_or_path": "mosaicml/mpt-1b-redpajama-200b-dolly",
+  "alibi": true,
+  "alibi_bias_max": 8,
   "architectures": [
-    "BloomForCausalLM"
+    "MosaicGPT"
   ],
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 3,
-  "unk_token_id": 0,
-  "hidden_dropout": 0.0,
-  "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "masked_softmax_fusion": true,
-  "model_type": "bloom",
-  "n_embed": 2560,
-  "n_inner": null,
-  "n_layer": 30,
-  "num_attention_heads": 32,
-  "offset_alibi": 100,
-  "pretraining_tp": 4,
-  "skip_bias_add": true,
-  "skip_bias_add_qkv": false,
-  "transformers_version": "4.20.0",
-  "use_cache": true,
-  "vocab_size": 250880
-}
+  "attn_clip_qkv": null,
+  "attn_impl": "torch",
+  "attn_pdrop": 0,
+  "attn_qk_ln": true,
+  "attn_uses_sequence_id": false,
+  "auto_map": {
+    "AutoConfig": "mosaicml/mpt-1b-redpajama-200b-dolly--configuration_mosaic_gpt.MosaicGPTConfig",
+    "AutoModelForCausalLM": "mosaicml/mpt-1b-redpajama-200b-dolly--mosaic_gpt.MosaicGPT"
+  },
+  "d_model": 2048,
+  "emb_init_std": null,
+  "emb_init_uniform_lim": null,
+  "emb_pdrop": 0,
+  "embedding_fraction": 1.0,
+  "fan_mode": "fan_in",
+  "init_device": "cpu",
+  "init_div_is_residual": true,
+  "init_gain": 0,
+  "init_nonlinearity": "relu",
+  "init_std": 0.02,
+  "logit_scale": null,
+  "low_precision_layernorm": true,
+  "max_seq_len": 2048,
+  "mlp_ratio": 4,
+  "model_type": "mosaic_gpt",
+  "n_heads": 16,
+  "n_layers": 24,
+  "no_bias": true,
+  "param_init_fn": "kaiming_normal_",
+  "prefix_lm": false,
+  "resid_pdrop": 0,
+  "softmax_scale": null,
+  "tokenizer_name": "EleutherAI/gpt-neox-20b",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "use_cache": false,
+  "verbose": 0,
+  "vocab_size": 50432
+}