armanibadboy/llama3.1-kazllm-8b-by-arman-ver3

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
+base_model: unsloth/Meta-Llama-3.1-8B-Instruct
 library_name: transformers
 model_name: outputs
 tags:
@@ -12,7 +12,7 @@ licence: license
 
 # Model Card for outputs
 
-This model is a fine-tuned version of [unsloth/meta-llama-3.1-8b-instruct-bnb-4bit](https://huggingface.co/unsloth/meta-llama-3.1-8b-instruct-bnb-4bit).
+This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/meta-llama-3.1-8b-instruct-bnb-4bit",
+  "base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -17,22 +17,19 @@
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "embed_tokens",
-    "lm_head"
-  ],
+  "modules_to_save": null,
   "peft_type": "LORA",
   "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
-    "k_proj",
     "up_proj",
     "v_proj",
+    "q_proj",
+    "down_proj",
     "o_proj",
-    "down_proj"
+    "k_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab18236dd4b5c647caccf4ea8bc2ec9bc209111a2d736657c3655101ab4e278
-size 2436951232
+oid sha256:bb5e7e7bc21a0f026bb256e385559ffb782183c7489f14d67d0fff098560a3df
+size 335604696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff8c9eb231f7cc1f2d0cde7fb3e634ba8566ba1ea82c012025f11b3cbbea67d
+oid sha256:969b4e450867fd29aefe7cae901621bd298c839b278137531f31d92a91a19102
 size 5560