Upload LlamaForCausalLM

config.json

@@ -1,16 +1,16 @@
 {
-  "_name_or_path": "michaelbenayoun/llama-2-tiny-16layers-random",
+  "_name_or_path": "michaelbenayoun/llama-2-tiny-4kv-heads-4layers-random",
   "architectures": [
-    "LlamaModel"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 32,
+  "hidden_size": 128,
   "initializer_range": 0.02,
-  "intermediate_size": 32,
+  "intermediate_size": 128,
   "is_decoder": true,
   "max_position_embeddings": 4096,
   "model_type": "llama",
@@ -24,7 +24,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.40.0",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb426491748f8f503eb347e0b534e3ad8a3a2bf9b17ad7bb58f380b67b3a2999
-size 4186920
+oid sha256:20a817fc0897bdaf27e8a20fdfb8189c32c11d7ce158324a8c7c5fcc9dadcd50
+size 34153080