feat: Improvements in LLMs (#406)

## Description
Non-breaking changes.
Added tokenCallback. 
Added setter for tokenCallback.
Depracated responseCallback. 
Added filtering out pad and eos tokens so they never get to end user.

### Type of change

- [x] Bug fix (non-breaking change which fixes an issue)
- [x] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to not work as expected)
- [ ] Documentation update (improves or adds clarity to existing
documentation)

### Tested on

- [x] iOS
- [ ] Android

### Related issues

#367 - token callback and token callback setter

#383 - unwanted EOS tokens

### Checklist

- [x] I have performed a self-review of my code
- [ ] I have commented my code, particularly in hard-to-understand areas
- [x] I have updated the documentation accordingly
- [ ] My changes generate no new warnings - **they do - if you pass
`responseCallback` to `LLMModule` you will receive deprecation
warning.**

### Additional notes

<!-- Include any additional information, assumptions, or context that
reviewers might need to understand this PR. -->

Author: pweglik

docs/docs/natural-language-processing/useLLM.md

@@ -74,6 +74,7 @@ The code snippet above fetches the model from the specified URL, loads it into m
 | `generate()`       | `(messages: Message[], tools?: LLMTool[]) => Promise<void>`                 | Runs model to complete chat passed in `messages` argument. It doesn't manage conversation context.                                              |
 | `interrupt()`      | `() => void`                                                                | Function to interrupt the current inference.                                                                                                    |
 | `response`         | `string`                                                                    | State of the generated response. This field is updated with each token generated by the model.                                                  |
+| `token`            | `string`                                                                    | The most recently generated token.                                                                                                              |
 | `isReady`          | `boolean`                                                                   | Indicates whether the model is ready.                                                                                                           |
 | `isGenerating`     | `boolean`                                                                   | Indicates whether the model is currently generating a response.                                                                                 |
 | `downloadProgress` | `number`                                                                    | Represents the download progress as a value between 0 and 1, indicating the extent of the model file retrieval.                                 |
@@ -102,6 +103,7 @@ const useLLM: ({
 interface LLMType {
   messageHistory: Message[];
   response: string;
+  token: string;
   isReady: boolean;
   isGenerating: boolean;
   downloadProgress: number;
@@ -171,7 +173,7 @@ const llm = useLLM({
   tokenizerConfigSource: LLAMA3_2_TOKENIZER_CONFIG,
 });
 
-const handleGenerate = async () => {
+const handleGenerate = () => {
   const chat = [
     { role: 'system', content: 'You are a helpful assistant' },
     { role: 'user', content: 'Hi!' },
@@ -180,11 +182,11 @@ const handleGenerate = async () => {
   ];
 
   // Chat completion
-  await llm.generate(chat);
-  console.log('Llama says:', llm.response);
+  llm.generate(chat);
 };
 
 return (
+  <Button onPress={handleGenerate} title="Generate!" />
   <Text>{llm.response}</Text>
 )
 ```
@@ -228,7 +230,7 @@ const llm = useLLM({
   tokenizerConfigSource: HAMMER2_1_1_5B_TOKENIZER_CONFIG,
 });
 
-const handleGenerate = async () => {
+const handleGenerate = () => {
   const chat = [
     {
       role: 'system',
@@ -241,11 +243,18 @@ const handleGenerate = async () => {
   ];
 
   // Chat completion
-  await llm.generate(chat, TOOL_DEFINITIONS);
-  console.log('Hammer says:', llm.response);
-
-  // Parse response and call functions accordingly
+  llm.generate(chat, TOOL_DEFINITIONS);
 };
+
+useEffect(() => {
+  // Parse response and call tools accordingly
+  // ...
+}, [llm.response])
+
+return (
+  <Button onPress={handleGenerate} title="Generate!" />
+  <Text>{llm.response}</Text>
+)
 ```
 
 ## Managed LLM Chat
@@ -282,9 +291,9 @@ const llm = useLLM({
   tokenizerConfigSource: LLAMA3_2_TOKENIZER_CONFIG,
 });
 
-const send = async () => {
+const send = () => {
   const message = 'Hi, who are you?';
-  await llm.sendMessage(message);
+  llm.sendMessage(message);
 };
 ```
 
@@ -351,9 +360,9 @@ useEffect(() => {
     });
 }, []);
 
-const send = async () => {
+const send = () => {
   const message = `Hi, what's the weather like in Cracow right now?`;
-  await llm.sendMessage(message);
+  llm.sendMessage(message);
 };
 ```