AFS available model
Version：20250425
| Model Series | Model String for API | Context length | Public mode | Applicable API |
|---|---|---|---|---|
| FFM | ||||
| Llama3.3-FFM-70B-32K | llama3.3-ffm-70b-32k-chat | 32K | O | Conversation Tool Call |
| Llama3.2-FFM-11B-V-32K | llama3.2-ffm-11b-v-32k-chat | 32K | O | VLMs API |
| Llama3.1-FFM-70B-32K | llama3.1-ffm-70b-32k-chat | 32K | O | Conversation Tool Call |
| Llama3.1-FFM-8B-32K | llama3.1-ffm-8b-32k-chat | 32K | O | |
| Llama3-FFM-70B | llama3-ffm-70b-chat | 8K | X | Conversation Tool Call |
| Llama3-FFM-8B | llama3-ffm-8b-chat | 8K | X | |
| FFM-Mixtral-8x7B | ffm-mixtral-8x7b-32k-instruct | 32K | X | Conversation Tool Call |
| FFM-Mistral-7B | ffm-mistral-7b-32k-instruct | 32K | X | |
| FFM-Mistral-7B-4K | ffm-mistral-7b-4k-instruct | 4K | X | |
| FFM-Llama2-v2-70B | ffm-llama2-70b-chat-exp | 4K | X | Conversation Tool Call |
| FFM-Llama2-v2-13B | ffm-llama2-13b-chat-exp | 4K | X | |
| FFM-Llama2-v2-7B | ffm-llama2-7b-chat-exp | 4K | X | |
| FFM-Llama2-70B | ffm-llama2-70b-chat | 4K | X | Conversation |
| FFM-Llama2-13B | ffm-llama2-13b-chat | 4K | X | |
| FFM-Llama2-7B | ffm-llama2-7b-chat | 4K | X | |
| FFM-embedding-v2.1 | ffm-embedding-v2.1 | 8K | O | Embedding |
| FFM-embedding-v2 | ffm-embedding-v2 | 8K | O | Embedding |
| FFM-embedding | ffm-embedding | 2K | X | Embedding |
| TAIDE | ||||
| TAIDE-LX-7B | taide-lx-7b-chat | 4K | O | Conversation |
| Meta Llama | ||||
| Meta-Llama3.3-70B-Instruct-32K | meta-llama3.3-70b-inst-32k | 32K | O | Conversation |
| Meta-Llama3.1-70B-32K | meta-llama31-70b-inst | 32K | X | Conversation |
| Meta-Llama3.1-8B-32K | meta-llama31-8b-inst | 32K | X | |
| Meta-CodeLlama-34B | meta-codellama-34b-instruct | 8K | X | Conversation Code Infilling |
| Meta-CodeLlama-13B | meta-codellama-13b-instruct | 8K | X | |
| Meta-CodeLlama-7B | meta-codellama-7b-instruct | 8K | X | |
| Meta-Llama2-70B | meta-llama2-70b-chat | 4K | X | Conversation |
| Meta-Llama2-13B | meta-llama2-13b-chat | 4K | X | |
| Meta-Llama2-7B | meta-llama2-7b-chat | 4K | X | |
| Qwen | ||||
| Qwen2.5-coder-7B-32k | qwen2.5-coder-7b-32k | 32K | O | Code Infilling |
| JinaAI | ||||
| Jina-embeddings-v2-base-code | jina-embeddings-v2-base-code | 8K | O | Embedding |
| BAAI | ||||
| BAAI-bge-reranker-v2-m3 | bge-reranker-v2-m3 | 8K | O | Rerank |
caution
Please note that by using the LLMs on AFS, you agree to comply with the official license of the models.