Upload LlamaForCausalLM

config.json

@@ -1,22 +1,24 @@
 {
-  "_name_or_path": "/fsx/mistral-7b-pretrain/checkpoint-1000/",
+  "_name_or_path": "/fsx/llama2-7b-pretrain/checkpoint-1000",
   "architectures": [
-    "MistralForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
-  "model_type": "mistral",
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
   "rope_theta": 10000.0,
-  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.34.0",

generation_config.json

@@ -1,6 +1,10 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
+  "do_sample": true,
   "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.34.0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f7e7fa18a841bc304c2bc18526a8b3ecaaa6732352200d74483f68e52ab8e72
-size 9942981696
+oid sha256:ce2b3e4e77ea3a33ba84da66e68512739525e74e3046ffc0969374b2c3e9f9a0
+size 9976570520

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e75a5484d4163faf2bcf615b2eaba6dd92aa97ac982aa2c60784c66f672f8e
-size 4540516344
+oid sha256:56cf9830abdde60dfe3ea0cb159a7243612e463cf4c4b31a75325e3412bf21c9
+size 3500294544

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14483464192
+    "total_size": 13476831232
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
@@ -140,24 +140,24 @@
     "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",