Upload 5 files

Mistral-7B-instruct-onmt-awq-gemm.00.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65bb17c50d659525fc657a8e36669452d9f2ad07c60f9998d3132d971ca40986
+size 4150957864

Mistral-7B-instruct-onmt-awq-gemm.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f53362911e0907982fbae27a31545217d71bd25e576e9935a7ba6d3ad97ff46c
+size 1054088

mistral-7b-awq-gemm-onmt-inference.yaml

@@ -0,0 +1,30 @@
+transforms: [sentencepiece]
+
+#### Subword
+src_subword_model: "/mnt/InternalCrucial4/dataAI/mistral-7B/mistral-instruct-v0.2/tokenizer.model"
+tgt_subword_model: "/mnt/InternalCrucial4/dataAI/mistral-7B/mistral-instruct-v0.2/tokenizer.model"
+
+# Model info
+model: "/mnt/InternalCrucial4/dataAI/mistral-7B/mistral-instruct-v0.2/Mistral-7B-instruct-onmt-awq-gemm.pt"
+
+# Inference
+seed: 42
+max_length: 256
+gpu: 0
+batch_type: sents
+batch_size: 60
+world_size: 1
+gpu_ranks: [0]
+#parallel_mode: "tensor_parallel"
+#quant_layers: ['w_1', 'w_2', 'w_3', 'linear_values', 'linear_query', 'linear_keys', 'final_linear']
+#quant_type: "bnb_NF4"
+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
+#tgt: None

tokenizer.model

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