Mistral readme (#994)

* Mistral: print the generated text.

* Add mistral to the readmes.

README.md

@@ -62,6 +62,8 @@ We also provide a some command line based examples using state of the art models
 - [LLaMA and LLaMA-v2](./candle-examples/examples/llama/): general LLM.
 - [Falcon](./candle-examples/examples/falcon/): general LLM.
 - [Phi-v1.5](./candle-examples/examples/phi/): a 1.3b general LLM with performance on par with LLaMA-v2 7b.
+- [Mistral7b-v0.1](./candle-examples/examples/mistral/): a 7b general LLM with
+  performance larger than all publicly available 13b models as of 2023-09-28.
 - [StarCoder](./candle-examples/examples/bigcode/): LLM specialized to code generation.
 - [Quantized LLaMA](./candle-examples/examples/quantized/): quantized version of
   the LLaMA model using the same quantization techniques as
@@ -149,6 +151,7 @@ If you have an addition to this list, please submit a pull request.
         - Falcon.
         - StarCoder.
         - Phi v1.5.
+        - Mistral 7b v0.1.
         - T5.
         - Bert.
     - Whisper (multi-lingual support).

candle-examples/examples/mistral/README.md

@@ -0,0 +1,37 @@
+# candle-mistral: 7b LLM with Apache 2.0 license weights
+
+- [Announcement Blog Post](https://mistral.ai/news/announcing-mistral-7b/).
+- [Model card](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the
+  HuggingFace Hub.
+
+```bash
+$ cargo run --example mistral --release --features cuda -- --prompt 'Write helloworld code in Rust' --sample-len 150
+
+Generated text:
+Write helloworld code in Rust
+=============================
+
+This is a simple example of how to write "Hello, world!" program in Rust.
+
+## Compile and run
+
+``bash
+$ cargo build --release
+   Compiling hello-world v0.1.0 (/home/user/rust/hello-world)
+    Finished release [optimized] target(s) in 0.26s
+$ ./target/release/hello-world
+Hello, world!
+``
+
+## Source code
+
+``rust
+fn main() {
+    println!("Hello, world!");
+}
+``
+
+## License
+
+This example is released under the terms
+```