Upload LlamaForCausalLM

config.json

@@ -1,16 +1,12 @@
 {
-  "_name_or_path": "/root/models/all_inst",
+  "_name_or_path": "unsloth/Llama-3.2-3B",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
+  "eos_token_id": 128001,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 3072,
@@ -26,7 +22,7 @@
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": false,

generation_config.json

@@ -1,12 +1,6 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "temperature": 0.6,
-  "top_p": 0.9,
+  "eos_token_id": 128001,
   "transformers_version": "4.45.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43324df479559713cd3f5c819a490de801e330dcce220f306bcbc96a4e353fb2
-size 2373931428
+oid sha256:aa16a7dfd7059a9453cf0afb308591641fbf377d98f2dfc63af5fe4e538e5d4e
+size 3161936508