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": 10,
+ "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 sha256:863b81c25a1f775d5a3b3c8efa6b9db61f166cac3873fed0207b0cdb2963917c
+size 10000845059

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55395b1b4ed23496149c0854237f9ebcc869a32f38157d9ed89eed2a41a11f9
+size 6183463067