Upload LlamaForCausalLM

config.json

@@ -1,29 +1,28 @@
 {
-  "_name_or_path": "/finetuning-subnet/local-models/training/2024-02-02_00-17-25",
+  "_name_or_path": "/finetuning-subnet/local-models/training/2024-02-02_01-44-09",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
+  "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
+  "hidden_size": 4,
+  "initializer_range": 0.0,
+  "intermediate_size": 4,
+  "max_position_embeddings": 2048,
   "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
+  "num_attention_heads": 1,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 1,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
-  "use_cache": false,
-  "vocab_size": 32002
+  "use_cache": true,
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "transformers_version": "4.36.2",
-  "use_cache": false
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1dd1f04ba6a6594915c590313ace9321f03fb0f04aeb3f4d4e25185b7b16d5c
+size 516936