Upload LlamaForCausalLM

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "hf_cache/Llama-3.3-70B-Instruct-f16",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f431f997e7a91447b5d7426895fa15cdfc9063dc4731284dbc59fb59cebfd35d
+size 4969219128

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e585543d3ee27aae42ab5966d6b5c988706aece60dd24d879354f5c093602b1d
+size 4890226896

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe17a77f94367bd68addcd88db81570298637f659aed2692ce7f93013d345c3
+size 4890226992

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4af91dee0dbbe93c8e00f17c1c2a3ab00d137e72c64fcb3cf81d353cba61925c
+size 4890226992

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc9e29c1b7bbf72a9b922dd0e0973e02bd1ab78ae00e151664a1c11cdddd2629
+size 4890226992

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54c0f54b82a4dcf98a8434923244974b0efb0d8b5a8e001bf195e49860e1a65
+size 4890226992

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f204f3fdd8dcf8ebb5f3a09f54e97754f339ccab2ada0a32a490ddddf92a0f
+size 4890226992

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f0d0892abaf5bbd28040ee99e68fc89208632bd52cb52f3a89d611c9ca08a78
+size 3356068840

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0349dd5ce2807e440204d54df109b7540c0b90fc9a450097d47ccde5de358c7a
+size 2101346432