Upload LlamaForCausalLM

README.md

@@ -8,6 +8,7 @@ tags:
 - unsloth
 - llama
 - trl
+- sft
 base_model: unsloth/llama-3-8b-bnb-4bit
 ---
 

adapter_config.json

@@ -1,32 +1,32 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "bias": "none",
   "fan_in_fan_out": false,
-  "inference_mode": true,
+  "inference_mode": false,
   "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
-  "revision": "unsloth",
+  "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
+    "gate_proj",
     "v_proj",
+    "o_proj",
     "q_proj",
-    "gate_proj",
+    "up_proj",
     "down_proj",
-    "up_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea3e771eab648f2c4da7492e2a7bfb98f05395204314ab98ff94692aec02013
+oid sha256:4a8397268e3b273d7002af410b40635f3921b561e996966f017a88dd7346aa0a
 size 167832240

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.41.2"
+}