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
|
from __future__ import annotations
import json, requests, re
from curl_cffi import requests as cf_reqs
from ..typing import CreateResult, Messages
from .base_provider import ProviderModelMixin, AbstractProvider
from .helper import format_prompt
class HuggingChat(AbstractProvider, ProviderModelMixin):
url = "https://huggingface.co/chat"
working = True
supports_stream = True
default_model = "meta-llama/Meta-Llama-3.1-70B-Instruct"
models = [
'meta-llama/Meta-Llama-3.1-70B-Instruct',
'CohereForAI/c4ai-command-r-plus-08-2024',
'Qwen/Qwen2.5-72B-Instruct',
'NousResearch/Hermes-3-Llama-3.1-8B',
'mistralai/Mistral-Nemo-Instruct-2407',
'microsoft/Phi-3.5-mini-instruct',
]
model_aliases = {
"llama-3.1-70b": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"command-r-plus": "CohereForAI/c4ai-command-r-plus-08-2024",
"qwen-2-72b": "Qwen/Qwen2.5-72B-Instruct",
"hermes-3": "NousResearch/Hermes-3-Llama-3.1-8B",
"mistral-nemo": "mistralai/Mistral-Nemo-Instruct-2407",
"phi-3.5-mini": "microsoft/Phi-3.5-mini-instruct",
}
@classmethod
def get_model(cls, model: str) -> str:
if model in cls.models:
return model
elif model in cls.model_aliases:
return cls.model_aliases[model]
else:
return cls.default_model
@classmethod
def create_completion(
cls,
model: str,
messages: Messages,
stream: bool,
**kwargs
) -> CreateResult:
model = cls.get_model(model)
if model in cls.models:
session = cf_reqs.Session()
session.headers = {
'accept': '*/*',
'accept-language': 'en',
'cache-control': 'no-cache',
'origin': 'https://huggingface.co',
'pragma': 'no-cache',
'priority': 'u=1, i',
'referer': 'https://huggingface.co/chat/',
'sec-ch-ua': '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"macOS"',
'sec-fetch-dest': 'empty',
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
}
print(model)
json_data = {
'model': model,
}
response = session.post('https://huggingface.co/chat/conversation', json=json_data)
conversationId = response.json()['conversationId']
response = session.get(f'https://huggingface.co/chat/conversation/{conversationId}/__data.json?x-sveltekit-invalidated=11',)
data: list = (response.json())["nodes"][1]["data"]
keys: list[int] = data[data[0]["messages"]]
message_keys: dict = data[keys[0]]
messageId: str = data[message_keys["id"]]
settings = {
"inputs": format_prompt(messages),
"id": messageId,
"is_retry": False,
"is_continue": False,
"web_search": False,
"tools": []
}
headers = {
'accept': '*/*',
'accept-language': 'en',
'cache-control': 'no-cache',
'origin': 'https://huggingface.co',
'pragma': 'no-cache',
'priority': 'u=1, i',
'referer': f'https://huggingface.co/chat/conversation/{conversationId}',
'sec-ch-ua': '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"macOS"',
'sec-fetch-dest': 'empty',
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
}
files = {
'data': (None, json.dumps(settings, separators=(',', ':'))),
}
response = requests.post(f'https://huggingface.co/chat/conversation/{conversationId}',
cookies=session.cookies,
headers=headers,
files=files,
)
first_token = True
for line in response.iter_lines():
line = json.loads(line)
if "type" not in line:
raise RuntimeError(f"Response: {line}")
elif line["type"] == "stream":
token = line["token"]
if first_token:
token = token.lstrip().replace('\u0000', '')
first_token = False
else:
token = token.replace('\u0000', '')
yield token
elif line["type"] == "finalAnswer":
break
|
