Upload optimized model

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "cilantro9246/sn9-op-1",
+  "_attn_implementation": "eager",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6112,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c84330509262ed356903a60ff36f9d57c4d3d4bd2d718ed52824ae46dc199850
+size 3079341512