1.2 KiB
1.2 KiB
| license | pipeline_tag | tags | inference | |||
|---|---|---|---|---|---|---|
| apache-2.0 | text-generation |
|
true |
Model Card for Mistral-7B-Instruct-v0.2
The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.
Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1
- 32k context window (vs 8k context in v0.1)
- Rope-theta = 1e6
- No Sliding-Window Attention
For full details of this model please read our paper and release blog post.
Instruction format
In order to leverage instruction fine-tuning, your prompt should be surrounded by [INST] and [/INST] tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
E.g.
text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"