Upload LlamaForCausalLM

config.json

@@ -11,12 +11,24 @@
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 5632,
-  "max_position_embeddings": 8192,
+  "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 22,
   "num_key_value_heads": 4,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "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": null,
   "rope_theta": 10000.0,

generation_config.json

@@ -1,7 +1,7 @@
 {
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "max_length": 8192,
+  "max_length": 2048,
   "pad_token_id": 0,
   "transformers_version": "4.36.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e87fbd5c27d4680f69da63a2860265f59ca449f593dd1a4c469f4ddf5f8c686
+oid sha256:81d8a3e955b93452c7b0ad3eeddb7074dcf4faf2970ecd4a04461bcad69f6ade
 size 4400216536