Upload OLMoForCausalLM

README.md

@@ -1,9 +1,9 @@
 ---
+language:
+- en
 license: apache-2.0
 datasets:
 - allenai/dolma
-language:
-- en
 ---
 
 

config.json

@@ -1,27 +1,55 @@
 {
+  "_name_or_path": "allenai/OLMo-7B-Twin-2T",
+  "activation_type": "swiglu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
   "architectures": [
     "OLMoForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
+  "attention_layer_norm": false,
+  "attention_layer_norm_with_affine": false,
+  "auto_map": {
+    "AutoConfig": "allenai/OLMo-7B-Twin-2T--configuration_olmo.OLMoConfig",
+    "AutoModelForCausalLM": "allenai/OLMo-7B-Twin-2T--modeling_olmo.OLMoForCausalLM",
+    "AutoTokenizer": [
+      "allenai/OLMo-7B-Twin-2T--tokenization_olmo_fast.OLMoTokenizerFast",
+      "allenai/OLMo-7B-Twin-2T--tokenization_olmo_fast.OLMoTokenizerFast"
+    ]
+  },
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
   "clip_qkv": null,
-  "eos_token_id": 0,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 2048,
+  "d_model": 4096,
+  "embedding_dropout": 0.0,
+  "embedding_size": 50304,
+  "eos_token_id": 50279,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "meta",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": false,
+  "max_sequence_length": 2048,
+  "mlp_hidden_size": 22016,
+  "mlp_ratio": 4,
   "model_type": "olmo",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
+  "multi_query_attention": false,
+  "n_heads": 32,
+  "n_kv_heads": null,
+  "n_layers": 32,
   "pad_token_id": 1,
-  "pretraining_tp": 1,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.39.3",
   "use_cache": true,
-  "vocab_size": 50304
+  "vocab_size": 50280,
+  "weight_tying": false
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "eos_token_id": 0,
+  "eos_token_id": 50279,
   "pad_token_id": 1,
-  "transformers_version": "4.40.0.dev0"
+  "transformers_version": "4.39.3"
 }

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f32bc00a0b6bf7a7ee0dd3e8e170dd165a977710fada7e8d4f5f7682b6cf74f
-size 4938797232
+oid sha256:38896a77697663bf47eb8cc031ec9cf731ab66f5f62fe4d555bae2fefedeaf8c
+size 4938795616

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339f08b625d6fd9ede814e143944c8cff0d6dbd34b80a15366cc1fcf3832bca8
-size 4991226840
+oid sha256:e5a7e402b3c73b34699a19f5514b4b01db5b497e7f5e5206fc88fdcb66d5468b
+size 4857006944

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5abe75835342732ed5342ad46ff18df9215e15fb863a3b37d09b71eb17783d7
-size 4924117904
+oid sha256:6b654c915fa8ad84d4405fbfe2472d9b2b80f73af9009338942508de1ba7493c
+size 4857006960

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:567d2e47a0f282c68dc5e3ff319c0c7e60c1a4003752b165b5fcb51cbf321d04
-size 4857008920
+oid sha256:2754680e6f6f24a3cf0dbbc191f5e62e987af814cbf99aec595f8d6bbf27cd20
+size 4857006960

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:647d690f164a6accf2336df347b6b3b33c2a23c56ef97869deb9d64994ebafbf
-size 4857008920
+oid sha256:950f1f5989192a94d4b7f136f2ce5270ad6bc3e819f9c94d3d7bb140262ac62a
+size 4857006960

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:510298bf0286af20a27b79fdc0af72fe328848d8febaeaf1d6021a4751fd56d1
-size 2984249384
+oid sha256:30fe3e45fbbc699da814d3632e9a53ebcb047bfce0dc8db3eb7de20373542bde
+size 3185575352

model.safetensors.index.json

@@ -3,231 +3,135 @@
     "total_size": 27552382976
   },
   "weight_map": {
-    "lm_head.weight": "model-00006-of-00006.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors"
+    "model.transformer.blocks.0.att_proj.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.0.attn_out.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.0.ff_out.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.0.ff_proj.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.1.att_proj.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.1.attn_out.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.1.ff_out.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.1.ff_proj.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.10.att_proj.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.10.attn_out.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.10.ff_out.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.10.ff_proj.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.11.att_proj.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.11.attn_out.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.11.ff_out.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.11.ff_proj.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.12.att_proj.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.12.attn_out.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.12.ff_out.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.12.ff_proj.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.13.att_proj.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.13.attn_out.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.13.ff_out.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.13.ff_proj.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.14.att_proj.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.14.attn_out.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.14.ff_out.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.14.ff_proj.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.15.att_proj.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.15.attn_out.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.15.ff_out.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.15.ff_proj.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.16.att_proj.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.16.attn_out.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.16.ff_out.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.16.ff_proj.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.17.att_proj.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.17.attn_out.weight": "model-00003-of-00006.safetensors",
+    "model.transformer.blocks.17.ff_out.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.17.ff_proj.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.18.att_proj.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.18.attn_out.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.18.ff_out.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.18.ff_proj.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.19.att_proj.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.19.attn_out.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.19.ff_out.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.19.ff_proj.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.2.att_proj.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.2.attn_out.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.2.ff_out.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.2.ff_proj.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.20.att_proj.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.20.attn_out.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.20.ff_out.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.20.ff_proj.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.21.att_proj.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.21.attn_out.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.21.ff_out.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.21.ff_proj.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.22.att_proj.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.22.attn_out.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.22.ff_out.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.22.ff_proj.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.23.att_proj.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.23.attn_out.weight": "model-00004-of-00006.safetensors",
+    "model.transformer.blocks.23.ff_out.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.23.ff_proj.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.24.att_proj.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.24.attn_out.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.24.ff_out.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.24.ff_proj.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.25.att_proj.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.25.attn_out.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.25.ff_out.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.25.ff_proj.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.26.att_proj.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.26.attn_out.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.26.ff_out.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.26.ff_proj.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.27.att_proj.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.27.attn_out.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.27.ff_out.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.27.ff_proj.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.28.att_proj.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.28.attn_out.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.28.ff_out.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.28.ff_proj.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.29.att_proj.weight": "model-00006-of-00006.safetensors",
+    "model.transformer.blocks.29.attn_out.weight": "model-00005-of-00006.safetensors",
+    "model.transformer.blocks.29.ff_out.weight": "model-00006-of-00006.safetensors",
+    "model.transformer.blocks.29.ff_proj.weight": "model-00006-of-00006.safetensors",
+    "model.transformer.blocks.3.att_proj.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.3.attn_out.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.3.ff_out.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.3.ff_proj.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.30.att_proj.weight": "model-00006-of-00006.safetensors",
+    "model.transformer.blocks.30.attn_out.weight": "model-00006-of-00006.safetensors",
+    "model.transformer.blocks.30.ff_out.weight": "model-00006-of-00006.safetensors",
+    "model.transformer.blocks.30.ff_proj.weight": "model-00006-of-00006.safetensors",
+    "model.transformer.blocks.31.att_proj.weight": "model-00006-of-00006.safetensors",
+    "model.transformer.blocks.31.attn_out.weight": "model-00006-of-00006.safetensors",
+    "model.transformer.blocks.31.ff_out.weight": "model-00006-of-00006.safetensors",
+    "model.transformer.blocks.31.ff_proj.weight": "model-00006-of-00006.safetensors",
+    "model.transformer.blocks.4.att_proj.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.4.attn_out.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.4.ff_out.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.4.ff_proj.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.5.att_proj.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.5.attn_out.weight": "model-00001-of-00006.safetensors",
+    "model.transformer.blocks.5.ff_out.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.5.ff_proj.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.6.att_proj.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.6.attn_out.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.6.ff_out.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.6.ff_proj.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.7.att_proj.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.7.attn_out.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.7.ff_out.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.7.ff_proj.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.8.att_proj.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.8.attn_out.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.8.ff_out.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.8.ff_proj.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.9.att_proj.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.9.attn_out.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.9.ff_out.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.blocks.9.ff_proj.weight": "model-00002-of-00006.safetensors",
+    "model.transformer.ff_out.weight": "model-00006-of-00006.safetensors",
+    "model.transformer.wte.weight": "model-00001-of-00006.safetensors"
   }
 }