Add Llama3 (#620)

Co-authored-by: Yaroslav Tarkan <[email protected]>

samples/cpp/beam_search_causal_lm/README.md

@@ -1,4 +1,4 @@
-# Text generation C++ sample that supports most popular models like LLaMA 2
+# Text generation C++ sample that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. It's only possible to change the device for inference to a differnt one, GPU for example, from the command line interface. The sample fearures `ov::genai::LLMPipeline` and configures it to use multiple beam grops. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 

samples/cpp/chat_sample/README.md

@@ -1,4 +1,4 @@
-# C++ chat_sample that supports most popular models like LLaMA 2
+# C++ chat_sample that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. For example, change the device for inference to GPU. The sample fearures `ov::genai::LLMPipeline` and configures it for the chat scenario. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 

samples/cpp/greedy_causal_lm/README.md

@@ -1,4 +1,4 @@
-# Text generation C++ greedy_causal_lm that supports most popular models like LLaMA 2
+# Text generation C++ greedy_causal_lm that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. For example, change the device for inference to GPU. The sample fearures `ov::genai::LLMPipeline` and configures it to run the simplest deterministic greedy sampling algorithm. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 

samples/cpp/multinomial_causal_lm/README.md

@@ -1,4 +1,4 @@
-# Text generation C++ multinomial_causal_lm that supports most popular models like LLaMA 2
+# Text generation C++ multinomial_causal_lm that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. For example, change the device for inference to GPU. The sample fearures `ov::genai::LLMPipeline` and configures it to run random sampling algorithm. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 

samples/cpp/prompt_lookup_decoding_lm/README.md

@@ -1,4 +1,4 @@
-# prompt_lookup_decoding_lm C++ sample that supports most popular models like LLaMA 2
+# prompt_lookup_decoding_lm C++ sample that supports most popular models like LLaMA 3
 
 [Prompt Lookup decoding](https://github.com/apoorvumang/prompt-lookup-decoding) is [assested-generation](https://huggingface.co/blog/assisted-generation#understanding-text-generation-latency) technique where the draft model is replaced with simple string matching the prompt to generate candidate token sequences. This method highly effective for input grounded generation (summarization, document QA, multi-turn chat, code editing), where there is high n-gram overlap between LLM input (prompt) and LLM output. This could be entity names, phrases, or code chunks that the LLM directly copies from the input while generating the output. Prompt lookup exploits this pattern to speed up autoregressive decoding in LLMs. This results in significant speedups with no effect on output quality.
 

samples/cpp/speculative_decoding_lm/README.md

@@ -1,4 +1,4 @@
-# speculative_decoding_lm C++ sample that supports most popular models like LLaMA 2
+# speculative_decoding_lm C++ sample that supports most popular models like LLaMA 3
 
 Speculative decoding (or [assisted-generation](https://huggingface.co/blog/assisted-generation#understanding-text-generation-latency) in HF terminology) is a recent technique, that allows to speed up token generation when an additional smaller draft model is used alonside with the main model.
 

samples/python/beam_search_causal_lm/README.md

@@ -1,4 +1,4 @@
-# Text generation Python sample that supports most popular models like LLaMA 2
+# Text generation Python sample that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. It's only possible to change the device for inference to a differnt one, GPU for example, from the command line interface. The sample fearures `openvino_genai.LLMPipeline` and configures it to use multiple beam grops. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 

samples/python/chat_sample/README.md

@@ -1,4 +1,4 @@
-# Python chat_sample that supports most popular models like LLaMA 2
+# Python chat_sample that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. For example, change the device for inference to GPU. The sample fearures `openvino_genai.LLMPipeline` and configures it for the chat scenario. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 

samples/python/greedy_causal_lm/README.md

@@ -1,4 +1,4 @@
-# Text generation Python greedy_causal_lm that supports most popular models like LLaMA 2
+# Text generation Python greedy_causal_lm that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. For example, change the device for inference to GPU. The sample fearures `openvino_genai.LLMPipeline` and configures it to run the simplest deterministic greedy sampling algorithm. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 

samples/python/multinomial_causal_lm/README.md

@@ -1,4 +1,4 @@
-# Text generation Python multinomial_causal_lm that supports most popular models like LLaMA 2
+# Text generation Python multinomial_causal_lm that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. For example, change the device for inference to GPU. The sample fearures `ov::genai::LLMPipeline` and configures it to run random sampling algorithm. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 

src/docs/SUPPORTED_MODELS.md

@@ -45,7 +45,19 @@
       </td>
     </tr>
     <tr>
-      <td rowspan="3" vertical-align="top"><code>LlamaForCausalLM</code></td>
+      <td rowspan="4" vertical-align="top"><code>LlamaForCausalLM</code></td>
+      <td>Llama 3</td>
+      <td>
+        <ul>
+          <li><a href="https://huggingface.co/meta-llama/Meta-Llama-3-8B"><code>meta-llama/Meta-Llama-3-8B</code></a></li>
+          <li><a href="https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct"><code>meta-llama/Meta-Llama-3-8B-Instruct</code></a></li>
+          <li><a href="https://huggingface.co/meta-llama/Meta-Llama-3-70B"><code>meta-llama/Meta-Llama-3-70B</code></a></li>
+          <li><a href="https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct"><code>meta-llama/Meta-Llama-3-70B-Instruct</code></a></li>
+        </ul>
+      </td>
+    </tr>
+    <tr>
+      <!-- <td><code>LlamaForCausalLM</code></td> -->
       <td>Llama 2</td>
       <td>
         <ul>