Upload LlamaForCausalLM

config.json

@@ -4,24 +4,24 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "dtype": "bfloat16",
-  "eos_token_id": 128009,
-  "head_dim": 128,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 2,
   "hidden_act": "silu",
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
-  "max_position_embeddings": 8192,
+  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 500000.0,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "transformers_version": "4.57.0.dev0",
   "use_cache": true,

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 128000,
-  "eos_token_id": 128009,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.57.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46e4ac2796c5cc43328086b71bf67c89e268d6619e68a251911bb673dbb9a550
-size 4158696
+oid sha256:8b1c8130bd3fe52a4b5b1d66e41451a5b37c01bc7fb6c6f4d657ec3a91e1fc35
+size 8218384