Upload LlamaForCausalLM

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "adapter_dim": 64,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_camelidae.CamelidaeConfig",
+    "AutoModelForCausalLM": "modeling_camelidae.LlamaForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "moe_dtype": "bfloat16",
+  "moe_scaling": 0.25,
+  "num_attention_heads": 32,
+  "num_clusters": 4,
+  "num_experts": 8,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "topk": 2,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "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.dev0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9459a37c109f2000b38eefc12edda703fb3aca0f50efd14848a08f8a9fced685
+size 9978720339

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4675b272a23bf1da707519206ef4da4b08d466d7ef9d8d2eabbe9f62c323b65e
+size 4581158713