Instructions to use AJKADZ/PHI_CODER with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use AJKADZ/PHI_CODER with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf AJKADZ/PHI_CODER:Q4_K_M # Run inference directly in the terminal: llama cli -hf AJKADZ/PHI_CODER:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf AJKADZ/PHI_CODER:Q4_K_M # Run inference directly in the terminal: llama cli -hf AJKADZ/PHI_CODER:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf AJKADZ/PHI_CODER:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf AJKADZ/PHI_CODER:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf AJKADZ/PHI_CODER:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf AJKADZ/PHI_CODER:Q4_K_M
Use Docker
docker model run hf.co/AJKADZ/PHI_CODER:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use AJKADZ/PHI_CODER with Ollama:
ollama run hf.co/AJKADZ/PHI_CODER:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use AJKADZ/PHI_CODER with Docker Model Runner:
docker model run hf.co/AJKADZ/PHI_CODER:Q4_K_M
- Lemonade
How to use AJKADZ/PHI_CODER with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull AJKADZ/PHI_CODER:Q4_K_M
Run and chat with the model
lemonade run user.PHI_CODER-Q4_K_M
List all available models
lemonade list
- Atomic Chat
File size: 5,980 Bytes
9b19fd8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 | // @ts-expect-error this package does not have typing
import TextLineStream from 'textlinestream';
import {
APIMessage,
APIMessageContentPart,
LlamaCppServerProps,
Message,
} from './types';
// ponyfill for missing ReadableStream asyncIterator on Safari
import { asyncIterator } from '@sec-ant/readable-stream/ponyfill/asyncIterator';
// eslint-disable-next-line @typescript-eslint/no-explicit-any
export const isString = (x: any) => !!x.toLowerCase;
// eslint-disable-next-line @typescript-eslint/no-explicit-any
export const isBoolean = (x: any) => x === true || x === false;
// eslint-disable-next-line @typescript-eslint/no-explicit-any
export const isNumeric = (n: any) => !isString(n) && !isNaN(n) && !isBoolean(n);
export const escapeAttr = (str: string) =>
str.replace(/>/g, '>').replace(/"/g, '"');
// wrapper for SSE
export async function* getSSEStreamAsync(fetchResponse: Response) {
if (!fetchResponse.body) throw new Error('Response body is empty');
const lines: ReadableStream<string> = fetchResponse.body
.pipeThrough(new TextDecoderStream())
.pipeThrough(new TextLineStream());
// @ts-expect-error asyncIterator complains about type, but it should work
for await (const line of asyncIterator(lines)) {
//if (isDev) console.log({ line });
if (line.startsWith('data:') && !line.endsWith('[DONE]')) {
const data = JSON.parse(line.slice(5));
yield data;
} else if (line.startsWith('error:')) {
const data = JSON.parse(line.slice(6));
throw new Error(data.message || 'Unknown error');
}
}
}
// copy text to clipboard
export const copyStr = (textToCopy: string) => {
// Navigator clipboard api needs a secure context (https)
if (navigator.clipboard && window.isSecureContext) {
navigator.clipboard.writeText(textToCopy);
} else {
// Use the 'out of viewport hidden text area' trick
const textArea = document.createElement('textarea');
textArea.value = textToCopy;
// Move textarea out of the viewport so it's not visible
textArea.style.position = 'absolute';
textArea.style.left = '-999999px';
document.body.prepend(textArea);
textArea.select();
document.execCommand('copy');
}
};
/**
* filter out redundant fields upon sending to API
* also format extra into text
*/
export function normalizeMsgsForAPI(messages: Readonly<Message[]>) {
return messages.map((msg) => {
if (msg.role !== 'user' || !msg.extra) {
return {
role: msg.role,
content: msg.content,
} as APIMessage;
}
// extra content first, then user text message in the end
// this allow re-using the same cache prefix for long context
const contentArr: APIMessageContentPart[] = [];
for (const extra of msg.extra ?? []) {
if (extra.type === 'context') {
contentArr.push({
type: 'text',
text: extra.content,
});
} else if (extra.type === 'textFile') {
contentArr.push({
type: 'text',
text: `File: ${extra.name}\nContent:\n\n${extra.content}`,
});
} else if (extra.type === 'imageFile') {
contentArr.push({
type: 'image_url',
image_url: { url: extra.base64Url },
});
} else if (extra.type === 'audioFile') {
contentArr.push({
type: 'input_audio',
input_audio: {
data: extra.base64Data,
format: /wav/.test(extra.mimeType) ? 'wav' : 'mp3',
},
});
} else {
throw new Error('Unknown extra type');
}
}
// add user message to the end
contentArr.push({
type: 'text',
text: msg.content,
});
return {
role: msg.role,
content: contentArr,
};
}) as APIMessage[];
}
/**
* recommended for DeepsSeek-R1, filter out content between <think> and </think> tags
*/
export function filterThoughtFromMsgs(messages: APIMessage[]) {
console.debug({ messages });
return messages.map((msg) => {
if (msg.role !== 'assistant') {
return msg;
}
// assistant message is always a string
const contentStr = msg.content as string;
return {
role: msg.role,
content:
msg.role === 'assistant'
? contentStr.split('</think>').at(-1)!.trim()
: contentStr,
} as APIMessage;
});
}
export function classNames(classes: Record<string, boolean>): string {
return Object.entries(classes)
.filter(([_, value]) => value)
.map(([key, _]) => key)
.join(' ');
}
export const delay = (ms: number) =>
new Promise((resolve) => setTimeout(resolve, ms));
export const throttle = <T extends unknown[]>(
callback: (...args: T) => void,
delay: number
) => {
let isWaiting = false;
return (...args: T) => {
if (isWaiting) {
return;
}
callback(...args);
isWaiting = true;
setTimeout(() => {
isWaiting = false;
}, delay);
};
};
export const cleanCurrentUrl = (removeQueryParams: string[]) => {
const url = new URL(window.location.href);
removeQueryParams.forEach((param) => {
url.searchParams.delete(param);
});
window.history.replaceState({}, '', url.toString());
};
export const getServerProps = async (
baseUrl: string,
apiKey?: string
): Promise<LlamaCppServerProps> => {
try {
const response = await fetch(`${baseUrl}/props`, {
headers: {
'Content-Type': 'application/json',
...(apiKey ? { Authorization: `Bearer ${apiKey}` } : {}),
},
});
if (!response.ok) {
throw new Error('Failed to fetch server props');
}
const data = await response.json();
return data as LlamaCppServerProps;
} catch (error) {
console.error('Error fetching server props:', error);
throw error;
}
};
|