Upload folder using huggingface_hub

config.json

@@ -1,5 +1,4 @@
 {
-  "_attn_implementation_autoset": true,
   "_name_or_path": "NousResearch/Llama-3.2-1B",
   "architectures": [
     "LlamaForCausalLM"
@@ -20,21 +19,6 @@
   "num_hidden_layers": 16,
   "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": "bfloat16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "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": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 32.0,
@@ -45,8 +29,8 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.47.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b59fa590323f4e8f52c7d054782877b00ec7e81ba6458dd97f40739ad64f50f
+size 4943274328