add model suppoerts
This commit is contained in:
parent
f72945fc0d
commit
4c796180fd
1 changed files with 55 additions and 18 deletions
|
@ -50,24 +50,61 @@ The llama.cpp CANN backend is designed to support Ascend NPU. It utilize the abi
|
||||||
|
|
||||||
## Model Supports
|
## Model Supports
|
||||||
|
|
||||||
| Model Name | Status |
|
| model name | FP16 | Q8_0 | Q4_0 |
|
||||||
|:-----------------------------:|:-------:|
|
|:----------------------------|:-----:|:----:|:----:|
|
||||||
| Baichuan | Support |
|
| AquilaChat2-7B | √ | √ | √ |
|
||||||
| Baichuan 2 | Support |
|
| Baichuan-7b | √ | √ | √ |
|
||||||
| Bloom | Support |
|
| Baichuan2-7B-Chat | √ | √ | √ |
|
||||||
| Falcon 2 | Support |
|
| bitnet_b1_58-large | √ | √ | √ |
|
||||||
| Gpt 2 | Support |
|
| bloom-560m | √ | x | √ |
|
||||||
| InternLM 2 | Support |
|
| bloomz-alpaca-560m | √ | x | √ |
|
||||||
| Llama 2 | Support |
|
| c4ai-command-r-35B-v01 | x | x | x |
|
||||||
| Llama 3 | Support |
|
| chatglm3-6B | x | x | x |
|
||||||
| Mamba | Support |
|
| chinese-alpaca-2-1.3b | √ | √ | √ |
|
||||||
| Mistral 7B | Support |
|
| CodeShell-7B | √ | √ | √ |
|
||||||
| OLMo | Support |
|
| deepseek-ai_deepseek-coder-1.3B-base | x | x | x |
|
||||||
| Phi 3 | Support |
|
| deepseek-ai_DeepSeek-V2-Lite | x | x | x |
|
||||||
| Qwen 2 | Support |
|
| deepseek-coder-6.7B-instruct | x | x | x |
|
||||||
| Refact | Support |
|
| DeepSeek-V2-Lite-64x1.5B | x | x | x |
|
||||||
| Starcoder | Support |
|
| falcon-7b-instruct | √ | √ | √ |
|
||||||
| Yi | Support |
|
| flan-t5-large | √ | √ | √ |
|
||||||
|
| gemma-2-9b-it | √ | √ | √ |
|
||||||
|
| glm-4-9B | x | x | x |
|
||||||
|
| gpt2 | √ | √ | √ |
|
||||||
|
| Gpt2-163M | √ | √ | √ |
|
||||||
|
| granite-3B-code-instruct | √ | √ | √ |
|
||||||
|
| GritLM-7B | √ | √ | √ |
|
||||||
|
| internlm2_5-7b-chat | √ | √ | √ |
|
||||||
|
| koala-7B-HF | √ | √ | √ |
|
||||||
|
| Llama-2-7b-chat-hf | √ | √ | √ |
|
||||||
|
| Llama-3-Smaug-8B | √ | √ | √ |
|
||||||
|
| Llama2-Chinese-7b-Chat | √ | √ | √ |
|
||||||
|
| Llama3-8B | √ | √ | √ |
|
||||||
|
| Llama3-8b-chinese | √ | √ | √ |
|
||||||
|
| mamba-130m-hf | √ | √ | √ |
|
||||||
|
| Mistral-7B-Instruct-v0.2 | √ | √ | √ |
|
||||||
|
| Mixtral-8x7B-Instruct-v0.1 | x | √ | √ |
|
||||||
|
| mpt-7B | √ | √ | √ |
|
||||||
|
| OLMo-1B-hf | √ | √ | √ |
|
||||||
|
| OpenELM-3B-Instruct | √ | √ | √ |
|
||||||
|
| Orion-14b-base | √ | √ | √ |
|
||||||
|
| phi1 | x | x | x |
|
||||||
|
| phi2 | x | x | x |
|
||||||
|
| Phi-3-mini-4k-instruct | √ | √ | √ |
|
||||||
|
| plamo-13b | √ | √ | √ |
|
||||||
|
| pythia-70M | x | x | x |
|
||||||
|
| Qwen-7B | √ | √ | √ |
|
||||||
|
| Qwen2-1.5B-Instruct | √ | x | √ |
|
||||||
|
| Refact-1_6B-fim | √ | √ | √ |
|
||||||
|
| SmolLM-135M | √ | √ | √ |
|
||||||
|
| stablelm-zephyr | x | x | x |
|
||||||
|
| stablelm-2-zephyr-1_6b | x | x | x |
|
||||||
|
| starcoderbase-1b | √ | √ | √ |
|
||||||
|
| starcoder2-3b | √ | √ | √ |
|
||||||
|
| vigogne-7b-chat | √ | √ | √ |
|
||||||
|
| xverse-7b-chat | √ | √ | √ |
|
||||||
|
| Yi-6b-Chat | √ | √ | √ |
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
## DataType Supports
|
## DataType Supports
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue