Update README.md

README.md

@@ -1,15 +1,49 @@
 ---
 license: apache-2.0
+datasets:
+- Open-Orca/SlimOrca
+pipeline_tag: text-generation
 ---
 
 Obtained from freecs/ThetaWave-7B after SFT fine tuning.
 
 Open-Orca/SlimOrca datasets were used.
 
-If the performance is better, more model details will be released...
+This model does not support system_prompt at the moment because it follows the chat_template of mistral, the next version is under training and ready to change to chatml template to support system_prompt.
 
+More model details will be released...
 
-Try it:
+Vllm deployment command
+```
+# Single graphics card
+python /path/to/vllm/vllm/entrypoints/openai/api_server.py \
+--model '/path/to/ThetaWave-7B-sft' \
+--tokenizer '/path/to/ThetaWave-7B-sft' \
+--tokenizer-mode auto \
+--dtype float16 \
+--enforce-eager \
+--host 0.0.0.0 \
+--port 6000 \
+--disable-log-stats \
+--disable-log-requests
+
+# Dual graphics cards
+python /path/to/vllm/vllm/entrypoints/openai/api_server.py \
+--model '/path/to/ThetaWave-7B-sft' \
+--tokenizer '/path/to/ThetaWave-7B-sft' \
+--tokenizer-mode auto \
+--dtype float16 \
+--enforce-eager \
+--tensor-parallel-size 2 \
+--worker-use-ray \
+--engine-use-ray \
+--host 0.0.0.0 \
+--port 6000 \
+--disable-log-stats \
+--disable-log-requests
+```
+
+Try it directly:
 ```
 from transformers import AutoModelForCausalLM, AutoTokenizer