8000 Update of model support · ggml-org/llama.cpp@8023706 · GitHub
[go: up one dir, main page]
Skip to content

Commit 8023706

Browse files
bachelor-doubachelor-dou
committed
Update of model support
1 parent 7da4e6d commit 8023706

File tree

1 file changed

+70
-186
lines changed

1 file changed

+70
-186
lines changed

‎docs/backend/CANN.md

Lines changed: 70 additions & 186 deletions
Original file line numberDiff line numberDiff line change
@@ -58,193 +58,77 @@ The llama.cpp CANN backend is designed to support Ascend NPU. It utilize the abi
5858

5959
| Model Name | FP16 | Q8_0 | Q4_0 |
6060
|:----------------------------|:-----:|:----:|:----:|
61-
| AquilaChat2-7B | √ | √ | √ |
62-
| Baichuan-7b | √ | √ | √ |
63-
| Baichuan2-7B-Chat | √ | √ | √ |
64-
| bitnet_b1_58-large | √ | √ | √ |
65-
| bloom-560m | √ | x | √ |
66-
| bloomz-alpaca-560m | √ | x | √ |
67-
| c4ai-command-r-35B-v01 | x | x | x |
68-
| chatglm3-6B | x | x | x |
69-
| chinese-alpaca-2-1.3b | √ | √ | √ |
70-
| CodeShell-7B | √ | √ | √ |
71-
| deepseek-ai_deepseek-coder-1.3B-base | x | x | x |
72-
| deepseek-ai_DeepSeek-V2-Lite | x | x | x |
73-
| deepseek-coder-6.7B-instruct | x | x | x |
74-
| DeepSeek-V2-Lite-64x1.5B | x | x | x |
75-
| falcon-7b-instruct | √ | √ | √ |
76-
| flan-t5-large | √ | √ | √ |
77-
| gemma-2-9b-it | √ | √ | √ |
78-
| glm-4-9B | x | x | x |
79-
| gpt2 | √ | √ | √ |
80-
| Gpt2-163M | √ | √ | √ |
81-
| granite-3B-code-instruct | √ | √ | √ |
61+
| Llama-2 | √ | √ | √ |
62+
| Llama-3 | √ | √ | √ |
63+
| Mistral-7B | √ | √ | √ |
64+
| Mistral MOE | x | x | x |
65+
| DBRX | x | x | x |
66+
| Falcon | √ | √ | √ |
67+
| Chinese LLaMA/Alpaca | √ | √ | √ |
68+
| Vigogne(French) | √ | √ | √ |
69+
| BERT | √ | √ | √ |
70+
| Koala | √ | √ | √ |
71+
| Baichuan | √ | √ | √ |
72+
| Aquila 1 & 2 | √ | √ | √ |
73+
| Starcoder models | √ | √ | √ |
74+
| Refact | √ | √ | √ |
75+
| MPT | √ | √ | √ |
76+
| Bloom | √ | √ | √ |
77+
| Yi models | √ | √ | √ |
78+
| stablelm models | √ | √ | √ |
79+
| DeepSeek models | x | x | x |
80+
| Qwen models | √ | √ 6D40 | √ |
81+
| PLaMo-13B | √ | √ | √ |
82+
| Phi models | √ | √ | √ |
83+
| PhiMoE | x | x | x |
84+
| GPT-2 | √ | √ | √ |
85+
| Orion | √ | √ | √ |
86+
| InternlLM2 | √ | √ | √ |
87+
| CodeShell | √ | √ | √ |
88+
| Gemma | √ | √ | √ |
89+
| Mamba | √ | √ | √ |
90+
| Xverse | √ | √ | √ |
91+
| command-r models | √ | √ | √ |
92+
| Grok-1 | x | x | x |
93+
| SEA-LION | √ | √ | √ |
8294
| GritLM-7B | √ | √ | √ |
83-
| internlm2_5-7b-chat | √ | √ | √ |
84-
| koala-7B-HF | √ | √ | √ |
85-
| Llama-2-7b-chat-hf | √ | √ | √ |
86-
| Llama-3-Smaug-8B | √ | √ | √ |
87-
| Llama2-Chinese-7b-Chat | √ | √ | √ |
88-
| Llama3-8B | √ | √ | √ |
89-
| Llama3-8b-chinese | √ | √ | √ |
90-
| mamba-130m-hf | √ | √ | √ |
91-
| Mistral-7B-Instruct-v0.2 | √ | √ | √ |
92-
| Mixtral-8x7B-Instruct-v0.1 | x | √ | √ |
93-
| mpt-7B | √ | √ | √ |
94-
| OLMo-1B-hf | √ | √ | √ |
95-
| OpenELM-3B-Instruct | √ | √ | √ |
96-
| Orion-14b-base | √ | √ | √ |
97-
| phi1 | x | x | x |
98-
| phi2 | x | x | x |
99-
| Phi-3-mini-4k-instruct | √ | √ | √ |
100-
| plamo-13b | √ | √ | √ |
101-
| pythia-70M | x | x | x |
102-
| Qwen-7B | √ | √ | √ |
103-
| Qwen2-1.5B-Instruct | √ | x | √ |
104-
| Refact-1_6B-fim | √ | √ | √ |
105-
| SmolLM-135M | √ | √ | √ |
106-
| stablelm-zephyr | x | x | x |
107-
| stablelm-2-zephyr-1_6b | x | x | x |
108-
| starcoderbase-1b | √ | √ | √ |
109-
| starcoder2-3b | √ | √ | √ |
110-
| vigogne-7b-chat | √ | √ | √ |
111-
| xverse-7b-chat | √ | √ | √ |
112-
| Yi-6b-Chat | √ | √ | √ |
113-
| snowflake-arctic-embed | √ | × | × |
114-
| all-minilm | √ | × | × |
115-
| granite-embedding | √ | × | × |
116-
| smollm | √ | √ | √ |
117-
| smollm2 | √ | √ | √ |
118-
| nomic-embed-text | √ | × | × |
119-
| qwen2 | √ | √ | √ |
120-
| reader-lm | √ | √ | √ |
121-
| qwen2.5 | √ | √ | √ |
122-
| qwen2.5-coder | √ | √ | √ |
123-
| qwen | √ | √ | √ |
124-
| paraphrase-multilingual | √ | × | × |
125-
| tinydolphin | √ | √ | √ |
126-
| tinyllama | √ | √ | √ |
127-
| mxbai-embed-large | √ | × | × |
128-
| bge-large | √ | × | × |
129-
| starcoder | √ | √ | √ |
130-
| granite3-moe | √ | √ | √ |
131-
| llama3 | √ | √ | √ |
132-
| deepseek-coder | √ | √ | √ |
133-
| granite3 | √ | √ | √ |
134-
| moondream | √ | √ | √ |
135-
| yi-coder | √ | √ | √ |
136-
| llama-guard3 | √ | √ | √ |
137-
| qwen2-math | √ | √ | √ |
138-
| stablelm2 | × | √ | √ |
139-
| sailor2 | √ | √ | × |
140-
| gemma3 | √ | √ | × |
141-
| internlm2 | √ | √ | √ |
142-
| bge-m3 | √ | × | × |
143-
| granite3-dense | √ | √ | √ |
144-
| codegemma | √ | √ | √ |
145-
| phi | √ | √ | √ |
146-
| dolphin-phi | × | √ | √ |
147-
| stable-code | √ | √ | √ |
148-
| stablelm-zephyr | √ | √ | √ |
149-
| gemma2 | √ | √ | √ |
150-
| shieldgemma | × | √ | √ |
151-
| gemma | √ | √ | √ |
152-
| starcoder2 | √ | √ | √ |
153-
| falcon3 | √ | √ | × |
154-
| deepseek-r1 | √ | √ | × |
155-
| deepscaler | √ | √ | × |
156-
| hermes3 | √ | √ | √ |
157-
| orca-mini | √ | √ | √ |
158-
| granite-code | √ | √ | √ |
159-
| opencoder | √ | √ | × |
160-
| nuextract | √ | √ | √ |
161-
| phi3 | √ | √ | √ |
162-
| phi3.5 | √ | √ | √ |
163-
| nemotron-mini | √ | √ | √ |
164-
| granite3-guardian | √ | √ | × |
165-
| exaone3.5 | √ | √ | × |
166-
| exaone-deep | √ | √ | × |
167-
| yi | √ | √ | √ |
168-
| smallthinker | √ | √ | × |
169-
| yarn-llama2 | √ | √ | √ |
170-
| xwinlm | √ | √ | √ |
171-
| wizard-vicuna-uncensored | √ | √ | √ |
172-
| vicuna | √ | √ | √ |
173-
| stable-beluga | √ | √ | √ |
174-
| nous-hermes | √ | √ | √ |
175-
| medllama2 | √ | √ | √ |
176-
| llama2-uncensored | √ | √ | √ |
177-
| meditron | √ | √ | √ |
178-
| llava | √ | √ | √ |
179-
| magicoder | √ | √ | √ |
180-
| wizardlm | √ | √ | √ |
181-
| wizard-math | √ | √ | √ |
182-
| wizardcoder | √ | √ | √ |
183-
| orca2 | √ | √ | √ |
184-
| codellama | √ | √ | √ |
185-
| duckdb-nsql | √ | √ | √ |
186-
| llama2 | √ | √ | √ |
187-
| deepseek-llm | √ | √ | √ |
188-
| phi4-mini | √ | √ | × |
189-
| samantha-mistral | × | √ | √ |
190-
| yarn-mistral | √ | √ | √ |
191-
| sqlcoder | √ | √ | √ |
192-
| neural-chat | √ | √ | √ |
193-
| bakllava | √ | √ | √ |
194-
| wizardlm2 | √ | √ | √ |
195-
| dolphin-mistral | √ | √ | √ |
196-
| mistral-openorca | √ | √ | √ |
197-
| openhermes | √ | √ | √ |
198-
| mistrallite | √ | √ | √ |
199-
| notus | √ | √ | √ |
200-
| zephyr | √ | √ | √ |
201-
| mistral | √ | √ | √ |
202-
| openchat | √ | √ | √ |
203-
| mathstral | √ | √ | √ |
204-
| codeqwen | √ | √ | √ |
205-
| falcon | √ | √ | √ |
206-
| dolphincoder | √ | √ | √ |
207-
| minicpm-v | √ | √ | √ |
208-
| bespoke-minicheck | √ | √ | √ |
209-
| llama3-chatqa | √ | √ | √ |
210-
| llama3-gradient | √ | √ | √ |
211-
| dolphin-llama3 | √ | √ | √ |
212-
| llama3-groq-tool-use | × | √ | √ |
213-
| llama-pro | √ | √ | √ |
214-
| aya | × | √ | √ |
215-
| aya-expanse | √ | √ | √ |
216-
| codegeex4 | × | √ | √ |
217-
| glm4 | √ | √ | √ |
218-
| solar | √ | √ | √ |
219-
| nous-hermes2 | √ | √ | √ |
220-
| falcon2 | √ | √ | √ |
221-
| mistral-nemo | √ | √ | √ |
222-
| llama2-chinese | √ | √ | × |
223-
| wizard-vicuna | √ | √ | √ |
224-
| codeup | √ | √ | √ |
225-
| open-orca-platypus2 | √ | √ | √ |
226-
| nexusraven | √ | √ | √ |
227-
| everythinglm | √ | √ | √ |
228-
| llava-phi3 | √ | × | × |
229-
| starling-lm | √ | √ | × |
230-
| olmo2 | √ | √ | × |
231-
| marco-o1 | × | √ | × |
232-
| openthinker | √ | â 1241 ˆš | × |
233-
| dolphin3 | √ | √ | × |
234-
| tulu3 | √ | √ | × |
235-
| command-r7b | √ | √ | × |
236-
| command-r7b-arabic | √ | √ | × |
237-
| deepseek-v2 | × | √ | √ |
238-
| deepseek-coder-v2 | × | √ | √ |
239-
| codestral | × | √ | √ |
240-
| mistral-small | × | √ | √ |
241-
| wizardlm-uncensored | √ | √ | × |
242-
| phi4 | × | √ | × |
243-
| llava-llama3 | √ | × | × |
244-
| command-r | × | × | √ |
245-
| phind-codellama | × | × | √ |
246-
| codebooga | × | × | √ |
247-
| alfred | × | × | √ |
95+
| OLMo | √ | √ | √ |
96+
| OLMo 2 | √ | √ | √ |
97+
| OLMoE | x | x | x |
98+
| Granite models | √ | √ | √ |
99+
| GPT-NeoX + Pythia | x | x | x |
100+
| Snowflake-Arctic MoE | x | × | × |
101+
| Smaug | √ | √ | √ |
102+
| Poro 34B | √ | √ | √ |
103+
| Bitnet b1.58 models | √ | √ | √ |
104+
| Flan-T5 | √ | √ | √ |
105+
| Open Elm models | √ | √ | √ |
106+
| chatGLM3-6B + ChatGLM4-9b + GLMEdge-1.5b + GLMEdge-4b | √ | √ | √ |
107+
| GLM-4-0414 | √ | √ | √ |
108+
| SmolLM | √ | √ | √ |
109+
| EXAONE-3.0-7.8B-Instruct | √ | √ | √ |
110+
| FalconMamba Models | √ | √ | √ |
111+
| Jais Models | x | x | x |
112+
| Bielik-11B-v2.3 | √ | √ | √ |
113+
| RWKV-6 | x | x | x |
114+
| QRWKV-6 | x | x | x |
115+
| GigaChat-20B-A3B | x | x | x |
116+
| Trillion-7B-preview | √ | √ | √ |
117+
| Ling models | √ | √ | √ |
118+
119+
120+
**Multimodal**
121+
| LLaVA 1.5 models, LLaVA 1.6 models | √ | √ | √ |
122+
| BakLLaVA | x | x | x |
123+
| Obsidian | x | x | x |
124+
| ShareGPT4V | x | x | x |
125+
| MobileVLM 1.7B/3B models | x | x | x |
126+
| Yi-VL | x | x | x |
127+
| Mini CPM | √ | √ | √ |
128+
| Moondream | √ | √ | √ |
129+
| Bunny | x | x | x |
130+
| GLM-EDGE | x | x | x |
131+
| Qwen2-VL | √ | √ | √ |
248132

249133

250134

0 commit comments

Comments
 (0)
0