Upload LlamaForCausalLM (#3)

- Upload LlamaForCausalLM (1a05b7b1070bd1fab0f2bca687e986997d7af896)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openlm-research/open_llama_3b",
+  "_name_or_path": "hf_output_final/",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -13,11 +13,14 @@
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 26,
+  "num_key_value_heads": 32,
   "pad_token_id": 0,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.30.2",
+  "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 52000
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.30.2"
+  "transformers_version": "4.31.0"
 }

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42617b1733f6f55a66328ff69e343cf4a70465b3e3776b87bdb4c886bd8fd663
-size 9972241191
+oid sha256:e4991c881fc6493c14ddd4055a60b5e2b16d8bb2298026721cbdea2af933d3cf
+size 9972237073

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be39d7611ece4274b33a7326fa6dd214815bd3d13cd189045385bb718b3fdcea
-size 4245748053
+oid sha256:f151a798ef2fb9613d50d6e3c19eb7887f7ebe493664af08acf32a212301fa89
+size 4245745796

pytorch_model.bin.index.json

@@ -106,9 +106,9 @@
     "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
     "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",