Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "yosefw/llama-3.2-amharic-32k-1024-v4",
+  "_name_or_path": "yosefw/llama-3.2-amharic-32k-1024-v6",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -7,24 +7,24 @@
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "eos_token_id": 1,
-  "head_dim": 64,
+  "head_dim": 96,
   "hidden_act": "silu",
-  "hidden_size": 2048,
+  "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "max_position_embeddings": 1024,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 8,
-  "num_key_value_heads": 32,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 14,
+  "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.2",
+  "transformers_version": "4.47.1",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 1,
-  "transformers_version": "4.46.2"
+  "transformers_version": "4.47.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:642f390e6774eb7adbc3a6c06a4d04dbbeb126b969f578249e3dc408eb1b6b3d
-size 1604468936
+oid sha256:7d442021810436ab37a4e56b7ef21da17dc213948eb72fd77cfbf8a3119d3b6c
+size 1650127032