Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./merged_archae_metadata_model",
+  "_name_or_path": "HuggingFaceTB/SmolLM-135M",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -19,26 +19,11 @@
   "num_hidden_layers": 30,
   "num_key_value_heads": 3,
   "pretraining_tp": 1,
-  "quantization_config": {
-    "_load_in_4bit": false,
-    "_load_in_8bit": true,
-    "bnb_4bit_compute_dtype": "float32",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": false,
-    "load_in_8bit": true,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": true,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 49152

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b31b913dc138d9ef85a3624d265ad0ba6c4112fcc2891457b7f26b6638e55862
-size 163557570
+oid sha256:0b3ab54fb01c73032b0fad97a580359e8fe53ec9a4840639a2d6501b437f3de5
+size 538090408