Model reference · open weights
deepseek-coder is an open-weight language model from deepseek-ai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
1. Introduction of Deepseek-Coder-7B-Instruct v1.5 Deepseek-Coder-7B-Instruct-v1.5 is continue pre-trained from Deepseek-LLM 7B on 2T tokens by employing a window size of 4K and next token prediction objective, and then fine-tuned on 2B tokens of instruction data. - Home Page: DeepSeek - Repository: deepseek-ai/deepseek-coder - Chat With DeepSeek Coder: DeepSeek-Coder 2. Evaluation Results 3. How to Use Here give some examples of how to use our model. Chat Model Inference 4. License This code repository is licensed under the MIT License. The use of DeepSeek Coder models is subject to the Model License. DeepSeek Coder supports commercial use. See the LICENSE-MODEL for more details. 5. Contact If you have any questions, please raise an issue or contact us at service@deepseek.com.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | deepseek-ai |
|---|---|
| Type | Language models |
| Parameters (lead) | 6.9B |
| Context | 4k tokens |
| Variants | 5 |
| Runs with | transformers |
| Released | 2024-01-25 |
| Popularity | 822k downloads / month |
| Likes | 700 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| deepseek-coder-7b-instruct-v1.5 | 6.9B | BF16 | ~15.9 GB | ✓ | Weights ↗ |
| deepseek-coder-6.7b-instruct | 6.7B | BF16 | ~15.5 GB | ✓ | Weights ↗ |
| deepseek-coder-1.3b-instruct | 1.3B | BF16 | ~3.1 GB | ✓ | Weights ↗ |
| deepseek-coder-1.3b-base | — | BF16 | — | — | Weights ↗ |
| DeepSeek-Coder-V2-Instruct | 235.7B | BF16 | ~542.2 GB | — | Weights ↗ |
Using it via the API
Once AxForge deploys deepseek-coder for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (deepseek-coder below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-coder","messages":[{"role":"user","content":"Hello"}]}'
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗
Sources