Upload model

README.md

@@ -1,12 +1,6 @@
 ---
-base_model: unsloth/Llama-3.2-3B-Instruct
 library_name: transformers
-language:
-- en
-- ms
-- id
-- ta
-- zh
+tags: []
 ---
 
 # Llama-3.2-3B-Malaysian-Reasoning LoRA
@@ -17,6 +11,6 @@ Full README at [mesolitica/Llama-3.2-3B-Malaysian-Reasoning](https://huggingface
 
 ## Merging
 
-Because Llama 3.2 3B is using tied weight embedding, so merging required to clone embedding into lm head after that `addmm` as usual, script at https://github.com/mesolitica/malaya/blob/master/session/small-malaysian-reasoning/merge-3b.ipynb
+Because Llama 3.2 3B is using tied weight embedding, so merging required to clone embedding into lm head, script at https://github.com/mesolitica/malaya/blob/master/session/small-malaysian-reasoning/merge-3b.ipynb
 
 If the model is not a tied weight, you can use default `merge_and_unload` function from PEFT or unsloth.

adapter_config.json

@@ -23,14 +23,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
     "down_proj",
-    "embed_tokens",
-    "lm_head",
-    "v_proj",
     "k_proj",
+    "gate_proj",
+    "embed_tokens",
     "up_proj",
+    "v_proj",
+    "lm_head",
+    "o_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:116678e3ee5899352cfcb86b2a8ef828a19bf36eaa601e2149555f2d43abc906
+oid sha256:b08bdc1217aed1d16721c796e997a4336aa2ce5c10b90ccd15bb6e1f88d117aa
 size 3401110784