Upload LlamaForCausalLM

README.md

@@ -1,3 +1,6 @@
+---
+{}
+---
 Small dummy LLama2-type Model useable for Unit/Integration tests. Suitable for CPU only machines, see [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio/blob/main/tests/integration/test_integration.py) for an example integration test.
 
 Model was created as follows:

config.json

@@ -4,13 +4,14 @@
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 12,
   "initializer_range": 0.02,
   "intermediate_size": 24,
-  "max_position_embeddings": 32,
+  "max_position_embeddings": 1024,
   "model_type": "llama",
   "num_attention_heads": 2,
   "num_hidden_layers": 2,
@@ -21,7 +22,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.38.1",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.34.0"
+  "transformers_version": "4.38.1"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5108f9b61c4c32b2ae72fd11c85535054ea4ffef80fa0fb8a2cd7c5d0e7de717
+size 3085952