Update config.json

config.json

@@ -1,6 +1,6 @@
 {
  "_name_or_path": "liemo/open-lilm-v2-q4",
- "architectures": [
+ "architectures": [
  "LlamaForCausalLM"
  ],
  "attention_bias": false,
@@ -19,6 +19,21 @@
  "num_key_value_heads": 4,
  "pad_token_id": 0,
  "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,
+ "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-06,
  "rope_scaling": null,
  "rope_theta": 5000000.0,
@@ -27,4 +42,4 @@
  "transformers_version": "4.42.4",
  "use_cache": false,
  "vocab_size": 64960
-}
+}