Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+compiled/1e9b0068b0aa89cb97dc.neff filter=lfs diff=lfs merge=lfs -text
+compiled/ad7a14c39e03676c5fea.neff filter=lfs diff=lfs merge=lfs -text

compiled/1e9b0068b0aa89cb97dc.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f83276298c68f54872f97012ac7edd1c0ef99669d523287caeff0eb345f6db11
+size 11131904

compiled/ad7a14c39e03676c5fea.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:782dd2f71e4ab657895315c94ad836590c31623303344a3dc4067570c210d13b
+size 10701824

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
+  "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",
+  "neuron": {
+    "auto_cast_type": "bf16",
+    "batch_size": 8,
+    "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
+    "checkpoint_revision": "008f3f3919bc6605cac0c6cd092aeb97b538c71b",
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.16.372.0+4a9b2326",
+    "num_cores": 16,
+    "sequence_length": 32,
+    "task": "text-generation"
+  },
+  "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": "bfloat16",
+  "transformers_version": "4.43.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.43.2"
+}