Upload LlamaForCausalLM

config.json

@@ -1,30 +1,30 @@
 {
   "architectures": [
-    "Qwen3ForCausalLM"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "bos_token_id": 1,
   "eos_token_id": 32001,
-  "head_dim": 128,
+  "head_dim": 80,
   "hidden_act": "silu",
   "hidden_size": 480,
   "initializer_range": 0.02,
   "intermediate_size": 1920,
   "max_position_embeddings": 2048,
-  "max_window_layers": 28,
-  "model_type": "qwen3",
+  "mlp_bias": false,
+  "model_type": "llama",
   "num_attention_heads": 6,
   "num_hidden_layers": 32,
   "num_key_value_heads": 2,
   "pad_token_id": 32003,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "sliding_window": 4096,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.51.3",
   "use_cache": true,
-  "use_sliding_window": false,
   "vocab_size": 32018
 }

generation_config.json

@@ -1,5 +1,6 @@
 {
   "_from_model_config": true,
+  "bos_token_id": 1,
   "eos_token_id": 32001,
   "pad_token_id": 32003,
   "transformers_version": "4.51.3"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd11ad42d9687e54e7b80bded8c61cbbc9a0cb32cab77657c81bb33b884b19aa
-size 541394944
+oid sha256:7d8bc9cee9bf614f544b87dae1f3d4bb6870b721fd62e7283d8b34c20fe79728
+size 494169296