rename file

Signed-off-by: minmingzhu <[email protected]>

Author: minmingzhu

.github/workflows/workflow_inference.yml

@@ -34,7 +34,7 @@ jobs:
     name: inference
     strategy:
       matrix:
-        model: [ gpt-j-6b, gpt2, bloom-560m, opt-125m, mpt-7b, mistral-7b-v0.1, mpt-7b-bigdl, neural-chat-7b-v3-1, CodeLlama-7b-hf, falcon-7b, starcoder, llama-2-7b-chat-hf, llama-2-7b-chat-hf-vllm, mixtral-8x7B-Instruct-v0.1 ]
+        model: [ gpt-j-6b, gpt2, bloom-560m, opt-125m, mpt-7b, mistral-7b-v0.1, mpt-7b-bigdl, neural-chat-7b-v3-1, CodeLlama-7b-hf, falcon-7b, starcoder, llama-2-7b-chat-hf, llama-2-7b-chat-hf-vllm, mixtral-8x7b-Instruct-v0.1 ]
         isPR:
           - ${{inputs.ci_type == 'pr'}}
 
@@ -46,7 +46,7 @@ jobs:
           - { model: "mistral-7b-v0.1"}
           - { model: "mpt-7b-bigdl"}
           - { model: "llama-2-7b-chat-hf-vllm"}
-          - { model: "mixtral-8x7B-Instruct-v0.1"}
+          - { model: "mixtral-8x7b-Instruct-v0.1"}
           - dtuner_model: nathan0/mpt-7b-deltatuner-model
             model: mpt-7b
 

llm_on_ray/finetune/models/mixtral-8x7B-Instruct-v0.1.yaml renamed to llm_on_ray/finetune/models/mixtral-8x7b-Instruct-v0.1.yaml

@@ -1,6 +1,6 @@
 port: 8000
-name: Mixtral-8x7B-Instruct-v0.1
-route_prefix: /Mixtral-8x7B-Instruct-v0.1
+name: mixtral-8x7b-Instruct-v0.1
+route_prefix: /mixtral-8x7b-Instruct-v0.1
 num_replicas: 1
 cpus_per_worker: 24
 gpus_per_worker: 0