Upload 5 files

mistral-instruct-inference.yaml

@@ -0,0 +1,28 @@
+transforms: [sentencepiece]
+
+#### Subword
+src_subword_model: "tokenizer.model"
+tgt_subword_model: "tokenizer.model"
+
+# Model info
+model: "mistral-onmt-awq.pt"
+
+
+# Inference
+seed: 42
+max_length: 256
+gpu: 0
+batch_type: sents
+batch_size: 4
+world_size: 1
+gpu_ranks: [0]
+#parallel_mode: "tensor_parallel"
+precision: fp16
+#random_sampling_topk: 1
+#random_sampling_topp: 0.6
+#random_sampling_temp: 0.9
+beam_size: 1
+n_best: 1
+profile: false
+report_time: true
+src: None

mistral-onmt-awq.00.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208f0b8ae23786d652d6508e694daa33bc762d4d1831ba7e25d9c6f9c447f9f8
+size 4150957864

mistral-onmt-awq.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dc7687165b3e4a673bbf8024122c6b5527b345afe9e2efd8bf321da42a5400e
+size 1053892

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443