Upload MPTForCausalLM

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "vinai/PhoGPT-7B5-Instruct",
+  "architectures": [
+    "MPTForCausalLM"
+  ],
+  "attn_config": {
+    "alibi": true,
+    "alibi_bias_max": 8,
+    "attn_impl": "torch",
+    "attn_pdrop": 0.0,
+    "attn_type": "multihead_attention",
+    "attn_uses_sequence_id": false,
+    "clip_qkv": null,
+    "prefix_lm": false,
+    "qk_ln": false,
+    "softmax_scale": null
+  },
+  "auto_map": {
+    "AutoConfig": "vinai/PhoGPT-7B5-Instruct--configuration_mpt.MPTConfig",
+    "AutoModelForCausalLM": "vinai/PhoGPT-7B5-Instruct--modeling_mpt.MPTForCausalLM"
+  },
+  "d_model": 4096,
+  "emb_pdrop": 0.0,
+  "embedding_fraction": 1.0,
+  "expansion_ratio": 4,
+  "fc_type": "torch",
+  "ffn_config": {
+    "fc_type": "torch",
+    "ffn_type": "mptmlp"
+  },
+  "init_config": {
+    "emb_init_std": null,
+    "emb_init_uniform_lim": null,
+    "fan_mode": "fan_in",
+    "init_div_is_residual": true,
+    "init_gain": 0.0,
+    "init_nonlinearity": "relu",
+    "init_std": null,
+    "name": "kaiming_normal_",
+    "verbose": 0
+  },
+  "init_device": "cpu",
+  "learned_pos_emb": false,
+  "logit_scale": null,
+  "max_seq_len": 2048,
+  "model_type": "mpt",
+  "n_heads": 32,
+  "n_layers": 32,
+  "no_bias": false,
+  "norm_type": "low_precision_layernorm",
+  "resid_pdrop": 0.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 250880
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.34.1",
+  "use_cache": false
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed57a205ed0f731368b052194e72ab90d10771e626d943b3938abdab7ce209f0
+size 9976262183

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d829992ef9020bfce172388e1a40592071aa596583e57d19648d3e5f48b30db
+size 4967410550

pytorch_model.bin.index.json

@@ -0,0 +1,394 @@
+{
+  "metadata": {
+    "total_size": 14943535104
+  },
+  "weight_map": {
+    "transformer.blocks.0.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.19.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.19.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.20.attn.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.20.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.20.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.20.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.20.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.20.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.20.ffn.up_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.20.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.20.norm_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.20.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.20.norm_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.20.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.21.attn.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.21.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.21.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.21.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.21.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.21.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.21.ffn.up_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.21.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.21.norm_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.21.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.21.norm_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.21.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.22.attn.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.22.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.22.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.22.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.22.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.22.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.22.ffn.up_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.22.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.22.norm_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.22.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.22.norm_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.22.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.attn.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.ffn.up_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.norm_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.norm_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.attn.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.ffn.up_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.norm_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.norm_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.attn.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.ffn.up_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.norm_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.norm_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.attn.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.ffn.up_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.norm_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.norm_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.attn.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.ffn.up_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.norm_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.norm_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.attn.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.ffn.up_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.norm_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.norm_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.attn.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.ffn.up_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.norm_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.norm_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.3.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.30.attn.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.ffn.up_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.norm_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.norm_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.attn.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.ffn.down_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.ffn.up_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.norm_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.norm_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.4.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.attn.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.ffn.down_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.ffn.up_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.norm_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.norm_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.norm_f.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.norm_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}