Feature Request: update the model list in run-llm.sh
alabulei1 opened this issue · comments
alabulei1 commented
Summary
The run-llm.sh
command is a tool that helps developers get started quickly. I believe we should only support the latest versions of these models. We will provide the full model list on the model.md
file. https://github.com/second-state/LlamaEdge/blob/main/models.md
Appendix
No response
alabulei1 commented
How about the following list?
- Llama-2-7B-Chat
- Llama-2-13B-Chat
- Mistral-7B-Instruct-v0.2
- Mixtral-8x7B-Instruct-v0.1
- TinyLlama-1.1B-Chat-v1.0
- OpenChat-3.5-0106
- OpenHermes-2.5-Mistral-7B
- Starling-LM-7B-alpha
- Deepseek-Coder-6.7B
- Deepseek-LLM-7B-Chat
- SOLAR-10.7B-Instruct-v1.0
- Orca-2-13B
- MistralLite-7B
- Yi-34B
- Wizard-Vicuna
- Calm2-7B-Chat
- ELYZA-japanese-Llama-2-7b-instruct
- Zephyr-7B-Alpha
- dolphin-2.6-phi-2
- Dolphin-2.2-Mistral-7B
- Neural-Chat-7B-v3-1
- WizardLM-1.0-Uncensored-CodeLlama-34B
- WizardLM-7B-V1.0-Uncensored
- WizardLM-13B-V1.0-Uncensored
- WizardCoder-Python-7B-V1.0
- Zephyr-7B-Alpha
- CausalLM-14B
- Baichuan2-13B-Chat
- BELLE-Llama2-13B-Chat