Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -18,7 +18,10 @@
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
     "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
@@ -35,7 +38,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.1",
-  "unsloth_version": "2024.4",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -1,9 +1,9 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128009
-  ],
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.40.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:042662b7762a43ff7b1af8ae19534ed2f65cf9e2c5f72d1aaa64e133fae216fe
+oid sha256:fcd90a05ae86858f8775ecd4dab8db5a9dcb29b3158c6b4cc5420b9650fb85ff
 size 5702746405