Upload MistralForCausalLM

config.json

@@ -16,27 +16,12 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "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": 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": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-05,
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.46.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32768
 }

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad8f0e50e9694d3ac04eb4fba7ecb6979158f863cbb5d63d145244961067380
+size 4949453696

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef6222c9cf17a21b2e013524428de14aa3b00046119d4174da60d48c1a27f636
+size 4999819232

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32cc759d32eab29ee024baa0d1b9e65ec2c15f2529d09ad0727d4b33a6aa9d9e
+size 4546807712