Upload LlamaForCausalLM

config.json

@@ -15,9 +15,20 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "pad_token_id": -1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float32",
+    "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
+  },
   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.30.2",
   "use_cache": true,
   "vocab_size": 32000

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:066344301a1864a4d77ff9389c4413241147420c4758b4e372d4d2bdb8710f0b
+size 7006454217