sandeepaffine
/

unsloth-meta-llama-Llama-2-7b-chat-hf_test-8bit

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

sandeepaffine commited on Aug 16, 2024

Commit

182ef10

·

verified ·

1 Parent(s): 2f4d576

Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

Files changed (1) hide show

adapter_config.json +5 -5

adapter_config.json CHANGED Viewed

@@ -15,8 +15,8 @@
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
-    "lm_head",
-    "embed_tokens"
   ],
   "peft_type": "LORA",
   "r": 128,
@@ -24,12 +24,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "o_proj",
     "gate_proj",
     "q_proj",
-    "v_proj",
     "down_proj",
-    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
   ],
   "peft_type": "LORA",
   "r": 128,
   "revision": null,
   "target_modules": [
     "k_proj",
+    "up_proj",
     "gate_proj",
     "q_proj",
     "down_proj",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,