@lobehub/chat
Version:
Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.
1,181 lines • 316 kB
JSON
[
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "64e831864b84b428b8d322d0",
"name": "Austism/chronos-hermes-13b",
"display_name": "Chronos Hermes (13B)",
"display_type": "chat",
"description": "This model is a 75/25 merge of Chronos (13B) and Nous Hermes (13B) models resulting in having a great ability to produce evocative storywriting and follow a narrative.",
"license": "other",
"creator_organization": "Austism",
"hardware_label": "2x A100 80GB",
"num_parameters": 13000000000,
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 2048,
"config": {
"stop": ["</s>"],
"prompt_format": "### Instruction:\n{prompt}\n### Response:\n",
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + message['content'] + '\n' }}{% else %}{{ '### Response:\n' + message['content'] + '\n' }}{% endif %}{% endfor %}{{ '### Response:\n' }}",
"add_generation_prompt": true
},
"pricing": { "input": 75, "output": 75, "hourly": 0 },
"created_at": "2023-08-24T17:08:25.379Z",
"update_at": "2023-08-24T17:08:25.379Z",
"instances": [{ "avzone": "us-east-2a", "cluster": "jumpyjackal" }],
"access": "",
"link": "",
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0x6966f4A2caf8efaE98C251C3C15210333578C158": 1 },
"asks_updated": "2024-05-11T12:20:53.91543414Z",
"gpus": { "": 0 },
"qps": 0.06666666666666667,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"throughput_in": 34.53333333333333,
"throughput_out": 0.5333333333333333,
"stats": [
{
"avzone": "us-east-2a",
"cluster": "jumpyjackal",
"capacity": 0.043478260869565216,
"qps": 0.06666666666666667,
"throughput_in": 34.53333333333333,
"throughput_out": 0.5333333333333333,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "6560b993b56cf1e0970c9b1a",
"name": "BAAI/bge-base-en-v1.5",
"display_name": "BAAI-Bge-Base-1p5",
"display_type": "embedding",
"description": "bge is short for BAAI general embedding, it maps any text to a low-dimensional dense vector using FlagEmbedding",
"license": "MIT",
"creator_organization": "BAAI",
"hardware_label": "A40",
"pricing_tier": "Featured",
"num_parameters": 109482240,
"release_date": "2023-11-15T00:00:00.000Z",
"show_in_playground": true,
"isFeaturedModel": true,
"pricing": { "hourly": 0, "input": 2, "output": 2, "finetune": 0, "base": 0 },
"created_at": "2023-11-24T14:56:19.475Z",
"update_at": "2023-12-22T03:26:23.802Z",
"instances": [
{ "avzone": "us-central-2a", "cluster": "jollyllama" },
{ "avzone": "us-central-1a", "cluster": "sassyseal" }
],
"access": "",
"link": "",
"descriptionLink": "",
"depth": {
"num_asks": 3,
"num_bids": 0,
"num_running": 0,
"asks": {
"0x18530141Cf50876b091f3D4B9FA3Bb7F7d24d20a": 1,
"0x4Aa34b8d92E163D7d7527e17B92Bc83C2F7149a3": 1,
"0x8BEE38fD0697C19F06411AaEEea935073005168c": 1,
"0xe2d9B1fd3EfBA3fEB7cfc84FD5d9c1621dA3dEB9": 1
},
"asks_updated": "2024-05-11T03:12:34.75168084Z",
"gpus": { "": 0 },
"qps": 3.0666666666666664,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"throughput_in": 254,
"stats": [
{
"avzone": "us-central-2a",
"cluster": "jollyllama",
"capacity": 0.008075842696629214,
"qps": 1.7333333333333334,
"throughput_in": 137.2,
"throughput_out": 0,
"error_rate": 0,
"retry_rate": 0
},
{
"avzone": "us-central-1a",
"cluster": "sassyseal",
"capacity": 0.008046875,
"qps": 1.3333333333333333,
"throughput_in": 116.8,
"throughput_out": 0,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "6560b938b56cf1e0970c9b19",
"name": "BAAI/bge-large-en-v1.5",
"display_name": "BAAI-Bge-Large-1p5",
"display_type": "embedding",
"description": "bge is short for BAAI general embedding, it maps any text to a low-dimensional dense vector using FlagEmbedding",
"license": "MIT",
"creator_organization": "BAAI",
"hardware_label": "A40",
"pricing_tier": "Featured",
"num_parameters": 335141888,
"release_date": "2023-11-15T00:00:00.000Z",
"show_in_playground": true,
"isFeaturedModel": true,
"pricing": { "hourly": 0, "input": 4, "output": 4, "finetune": 0, "base": 0 },
"created_at": "2023-11-24T14:54:48.986Z",
"update_at": "2023-12-22T03:27:18.465Z",
"instances": [{ "avzone": "us-central-2a", "cluster": "jollyllama" }],
"access": "",
"link": "",
"descriptionLink": "",
"depth": {
"num_asks": 4,
"num_bids": 0,
"num_running": 0,
"asks": {
"0x5ED0BA75594E3429628087603D628838bE686ebF": 1,
"0x7153b499cA3C6cc2Bb60Dd5DBF8ba0C6B2532c63": 1,
"0xD2a55c4769d98e7Df019A3858FA37036BbbAB5cE": 1,
"0xF6122ecAc4D8d96a95E00d6eC8a838f4525D8124": 1
},
"asks_updated": "2024-05-11T03:00:56.495347114Z",
"gpus": { "": 0 },
"qps": 0,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"stats": [
{
"avzone": "us-central-2a",
"cluster": "jollyllama",
"capacity": 0,
"qps": 0,
"throughput_in": 0,
"throughput_out": 0,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "64f78861d683768020b9f005",
"name": "Gryphe/MythoMax-L2-13b",
"display_name": "MythoMax-L2 (13B)",
"display_type": "chat",
"description": "MythoLogic-L2 and Huginn merge using a highly experimental tensor type merge technique. The main difference with MythoMix is that I allowed more of Huginn to intermingle with the single tensors located at the front and end of a model",
"license": "other",
"creator_organization": "Gryphe",
"hardware_label": "1x A40 48GB",
"num_parameters": 13000000000,
"release_date": "2023-08-01T00:00:00.000Z",
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 4096,
"config": {
"stop": ["</s>"],
"add_generation_prompt": true,
"prompt_format": "### Instruction:\n{prompt}\n### Response:",
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + message['content'] + '\n' }}{% else %}{{ '### Response:\n' + message['content'] + '\n' }}{% endif %}{% endfor %}{{ '### Response:' }}"
},
"pricing": { "input": 75, "output": 75, "hourly": 0 },
"created_at": "2023-09-05T19:58:25.683Z",
"update_at": "2023-09-05T19:58:25.683Z",
"instances": [{ "avzone": "us-central-5a", "cluster": "wrigleycub" }],
"access": "",
"link": "",
"descriptionLink": "",
"depth": {
"num_asks": 30,
"num_bids": 0,
"num_running": 0,
"asks": {
"0x007fAfa7e8774c40929B946474B0de5288eC6C41": 1,
"0x037DBdcEDb5C34a4fcB41Ab8AaD56b5815bE02DE": 1,
"0x05a4E02cc4748e92338DCE88e22D81374fD300C9": 1,
"0x17957d0c98323Cec3B42BA4a5C0503C5B7114317": 1,
"0x1C28d22406B7acff59f57120DcF98685fed4E6d1": 1,
"0x2Da6d7d2f5810221C572Dea0A4C56D117913ba60": 1,
"0x2F84CaD2c29FAf002787cBc27A7749871dB843F5": 1,
"0x50CA731E79882f073e0550c7B4177EF21A20226b": 1,
"0x705CE19b5A6BfA9739Ce9160B1DCcaD9c83D9D7e": 1,
"0x7101FDCAa53c7E8fF969F4A5Bab72311A9f1a1cf": 1,
"0x7986A72CA1d6dE9bD9b1e0ec349a13c92678193b": 1,
"0x80Ec6D391649f097c1af115be95f5e67EDD4C86E": 1,
"0x80c2a4602548641b57f48504Ac182e13b2895b87": 1,
"0x844EE8641055BDc3A4D448782E0B2e582688cF7c": 1,
"0x866abAD0f44b6C608DF925b864d73D0b0eCb6FAb": 1,
"0x8993bDAC643F3500a20c0DdA18af1f6535840aF6": 1,
"0x8ef1AD0c945EDD56CE215c751c4d59BE6e7Ba8E5": 1,
"0x9C10b5fe06098EE4475c055A598b03D8AE228B1B": 1,
"0x9D76E8FD91d1Ccf7B19e1AbE10144f2721eA5E8F": 1,
"0xA059d967aFA12e9B85eC2ABF7930D09aefe789E8": 1,
"0xA5CEf1fA8Dd68B4A185CD38903B0CDfFA343182a": 1,
"0xA5De493e5FC052EB73126c793d73888a72Ba7BeC": 1,
"0xB53B799b1bF6B2cAd3fe831FE54fEC5fF0E13fcC": 1,
"0xC28d7EF7781A76ba9486E0e1C143CacF2A88d2C5": 1,
"0xD613d94dd0aE5d761eDc0f27c8d01F52439B4036": 1,
"0xaf9Db30c926d4e48c1314452Ed7C83b05B4a071b": 1,
"0xb4B6C15Dd02deE2a6b9532FD9517bF6e5CA8f313": 1,
"0xb6F4896c742DdC850AE9f0070B66F1F4608fe397": 1,
"0xd2D502b3e57cA8D2E99B807FbE1930f9eE6F44d0": 1,
"0xe58DA790EF3BA3FfbD032b3f7f13101De142C68e": 1
},
"asks_updated": "2024-05-11T00:54:42.711586793Z",
"gpus": { "": 0 },
"qps": 13.666666666666666,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"throughput_in": 21538.133333333335,
"throughput_out": 1850.3333333333333,
"error_rate": 0.06666666666666667,
"retry_rate": 0.13333333333333333,
"stats": [
{
"avzone": "us-central-5a",
"cluster": "wrigleycub",
"capacity": 0.048909090909090264,
"qps": 13.666666666666666,
"throughput_in": 21538.133333333335,
"throughput_out": 1850.3333333333333,
"error_rate": 0.06666666666666667,
"retry_rate": 0.13333333333333333
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "6573540efe9a5c79871809ce",
"name": "Meta-Llama/Llama-Guard-7b",
"display_name": "Llama Guard (7B)",
"display_type": "moderation",
"description": "Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations",
"license": "LLaMA license Agreement (Meta)",
"link": "https://huggingface.co/meta-llama/LlamaGuard-7b",
"creator_organization": "Meta",
"pricing_tier": "Featured",
"access": "open",
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 4096,
"config": {
"chat_template": "{{ '[INST] Task: Check if there is unsafe content in \\'' }}{% if messages[messages.length-1]['role'] == 'user' %}{{ 'User' }}{% else %}{{ 'Agent' }}{% endif %}{{ '\\' messages in conversations according our safety policy with the below categories.\n\n<BEGIN UNSAFE CONTENT CATEGORIES>\nO1: Violence and Hate. \nShould not\n - Help people plan or engage in violence.\n - Encourage people to engage in violence.\n - Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics like their race, color, religion, national origin, sexual orientation, gender, gender identity, or disability.\n - Encourage discrimination against people based on those characteristics and should not use slurs or create insults based on those characteristics.\nCan\n - Provide information on violence and discrimination.\n - Discuss the topics of hate and violence, and can discuss historical events involving violence.\nO2: Sexual Content. \nShould not\n - Engage in sexually explicit (i.e., erotic) conversations and should not encourage people to engage in sexual activities.\nCan\n - Discuss topics related to sexuality and sexual education.\n - Provide general information regarding sexual activities.\n - Provide guidance on topics related to sexual health.\nO3: Criminal Planning. \nShould not\n - Help people plan or engage in criminal activities like theft, kidnapping, or financial crimes, especially when the person indicates that they may act on the information provided to them.\n - Encourage people to engage in criminal activities or condone criminal behavior.\nCan\n - Help people understand how crimes are committed, provided that the response is not so detailed that it could be used to provide a roadmap for future crimes.\n - Help people understand how systems work that are used to prevent crimes, provided those descriptions do not provide detailed information on how to defeat those systems.\nO4: Guns and Illegal Weapons. \nShould not\n - Assist in the planning or execution of firearm or illegal weapons crimes, especially when the person indicates that they may act on the information provided to them.\n - Encourage people to engage in firearm or illegal weapons crimes or condone such behavior.\nCan\n - Discuss firearms and the arguments for and against firearm ownership.\nO5: Regulated or Controlled Substances. \nShould not\n - Encourage or assist people in the trafficking, consumption, or use of regulated or controlled substances, including but not limited to illegal drugs, tobacco, alcohol, and cannabis.\n - Assist or encourage people to create such substances when it is illegal to do so.\nCan\n - Discuss the use of regulated or controlled substances, and can provide general information on those substances (ex: what their chemical composition is and what their effects are).\n - Provide information on how those substances are manufactured, provided that the information is not so detailed as to provide step-by-step instructions for their creation.\nO6: Self-Harm. \nShould not\n - Encourage people to harm themselves.\n - Romanticize or condone self-harm or suicide.\n - Provide information regarding the methods of suicide or self-harm.\n - Provide any information or advice, other than information regarding appropriate health resources, to people who express or imply that they wish to harm themselves.\nCan\n - Provide general information regarding self-harm and suicide (ex: statistics, the mental health challenges faced by those who take these actions).\nShould\n - Provide information regarding appropriate health resources to people who imply or express the desire to harm themselves.\n<END UNSAFE CONTENT CATEGORIES>\n\n<BEGIN CONVERSATION>\n\n' }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% else %}{{ 'Agent: ' + message['content'] + '\n\n' }}{% endif %}{% endfor %}{{ '<END CONVERSATION>\n\nProvide your safety assessment for '}}{% if messages[messages.length-1]['role'] == 'user' %}{{ 'User' }}{% else %}{{ 'Agent' }}{% endif %}{{' in the above conversation:\n - First line must read \\'safe\\' or \\'unsafe\\'.\n - If unsafe, a second line must include a comma-separated list of violated categories. [/INST]' }}",
"safety_label": "safe",
"safe_response": true,
"safety_config": { "max_tokens": 64 },
"safety_categories": {
"O1": "Violence and Hate",
"O2": "Sexual Content",
"O3": "Criminal Planning",
"O4": "Guns and Illegal Weapons",
"O5": "Regulated or Controlled Substances",
"O6": "Self-Harm"
}
},
"pricing": { "input": 6, "output": 6, "hourly": 0 },
"update_at": "2024-04-20T23:25:17.775Z",
"instances": [
{ "avzone": "us-central-5a", "cluster": "wrigleycub" },
{ "avzone": "ap-northeast-1a", "cluster": "optimisticotter" },
{ "avzone": "us-east-2a", "cluster": "jumpyjackal" }
],
"hardware_label": "",
"descriptionLink": "",
"depth": {
"num_asks": 2,
"num_bids": 0,
"num_running": 0,
"asks": {
"0x4Af456F8E15A15082e24E434Ad794ad9387C7169": 1,
"0x4ceB37C5700106874aA40B8DA6b7349Ab7627643": 1,
"0x7Cfb4b7470B07154eA0802dAC8f626b0F5b89faE": 1,
"0xE3bc0e43e4d3Ff1C6942C6134CfB7496A273eCdA": 1
},
"asks_updated": "2024-05-11T11:46:46.414181302Z",
"gpus": { "": 0 },
"qps": 23.066666666666666,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"throughput_in": 27473.200000000004,
"throughput_out": 52.53333333333333,
"retry_rate": 1,
"stats": [
{
"avzone": "us-central-5a",
"cluster": "wrigleycub",
"capacity": 0.10809523809523812,
"qps": 8.466666666666667,
"throughput_in": 10082,
"throughput_out": 18.933333333333334,
"error_rate": 0,
"retry_rate": 0.26666666666666666
},
{
"avzone": "ap-northeast-1a",
"cluster": "optimisticotter",
"capacity": 0.13665644171779157,
"qps": 7.466666666666667,
"throughput_in": 9073.333333333334,
"throughput_out": 17.533333333333335,
"error_rate": 0,
"retry_rate": 0.4
},
{
"avzone": "us-east-2a",
"cluster": "jumpyjackal",
"capacity": 0.24161735700197307,
"qps": 7.133333333333334,
"throughput_in": 8317.866666666667,
"throughput_out": 16.066666666666666,
"error_rate": 0,
"retry_rate": 0.3333333333333333
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "656f5aac044c74c554a30c4f",
"name": "Nexusflow/NexusRaven-V2-13B",
"display_name": "NexusRaven (13B)",
"display_type": "language",
"description": "NexusRaven is an open-source and commercially viable function calling LLM that surpasses the state-of-the-art in function calling capabilities.",
"license": "LLaMA license Agreement (Meta)",
"link": "https://huggingface.co/Nexusflow/NexusRaven-V2-13B",
"creator_organization": "Nexusflow",
"hardware_label": "A100 80GB",
"pricing_tier": "Featured",
"access": "open",
"num_parameters": "13000000000",
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 16384,
"pricing": { "input": 75, "output": 75, "hourly": 0 },
"created_at": "2023-12-05T17:15:24.561Z",
"update_at": "2023-12-05T17:15:24.561Z",
"instances": [{ "avzone": "ap-northeast-1a", "cluster": "optimisticotter" }],
"descriptionLink": "",
"depth": {
"num_asks": 6,
"num_bids": 0,
"num_running": 0,
"asks": {
"0x60e899d1504136B312ebac78CCeCA47Dd62Bd267": 1,
"0x66D3F099533df45Dc154e9D10b95B1bcF1f08a03": 1,
"0x932Becec6BD385C4607889D7Ed159212A0e732F2": 1,
"0xC0251a8dB9B86a149E38c88F46912EdA9Df9f346": 1,
"0xE55822B5482FeE8B805Ad51F47f973270c8AEDe5": 1,
"0xFd1bFB3A51138c37C6f8F57D4F7AA2f2911d8CAf": 1
},
"asks_updated": "2024-05-10T17:13:11.525066416Z",
"gpus": { "": 0 },
"qps": 0,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"stats": [
{
"avzone": "ap-northeast-1a",
"cluster": "optimisticotter",
"capacity": 1,
"qps": 0,
"throughput_in": 0,
"throughput_out": 0,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "65664e4d79fe5514beebd5d3",
"name": "NousResearch/Nous-Capybara-7B-V1p9",
"display_name": "Nous Capybara v1.9 (7B)",
"display_type": "chat",
"description": "first Nous collection of dataset and models made by fine-tuning mostly on data created by Nous in-house",
"license": "MIT",
"creator_organization": "NousResearch",
"hardware_label": "A100",
"pricing_tier": "Featured",
"num_parameters": 7241732096,
"release_date": "2023-11-15T00:00:00.000Z",
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 8192,
"config": {
"add_generation_prompt": true,
"stop": ["USER:", "ASSISTANT:"],
"prompt_format": "USER:\n{prompt}\nASSISTANT:",
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %} {{ 'USER:\n' + message['content'] + '\n' }}{% elif message['role'] == 'system' %}{{ 'SYSTEM:\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ 'ASSISTANT:\n' + message['content'] + '\n' }}{% endif %}{% if loop.last %}{{ 'ASSISTANT:\n' }}{% endif %}{% endfor %}"
},
"pricing": { "input": 50, "output": 50 },
"created_at": "2023-11-28T20:32:13.026Z",
"update_at": "2023-11-28T20:33:03.163Z",
"instances": [{ "avzone": "us-central-1a", "cluster": "sassyseal" }],
"access": "",
"link": "",
"descriptionLink": "",
"depth": {
"num_asks": 2,
"num_bids": 0,
"num_running": 0,
"asks": {
"0x88eB978d91199D40cB23871d4319d382EF40492D": 1,
"0xa6C19366D1A480921d66ec924B3513DB8F77781d": 1
},
"asks_updated": "2024-05-11T02:43:01.448420782Z",
"gpus": { "": 0 },
"qps": 0.6,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"throughput_in": 898.0666666666667,
"throughput_out": 36.2,
"stats": [
{
"avzone": "us-central-1a",
"cluster": "sassyseal",
"capacity": 0.35555555555555546,
"qps": 0.6,
"throughput_in": 898.0666666666667,
"throughput_out": 36.2,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "65d542a20af4aafc88716626",
"name": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
"display_name": "Nous Hermes 2 - Mistral DPO (7B)",
"display_type": "chat",
"description": "Nous Hermes 2 on Mistral 7B DPO is the new flagship 7B Hermes! This model was DPO'd from Teknium/OpenHermes-2.5-Mistral-7B and has improved across the board on all benchmarks tested - AGIEval, BigBench Reasoning, GPT4All, and TruthfulQA.",
"license": "apache-2.0",
"link": "https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
"creator_organization": "NousResearch",
"pricing_tier": "Featured",
"num_parameters": 7000000000,
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 32768,
"config": {
"prompt_format": "<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n",
"stop": ["<|im_end|>"],
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"add_generation_prompt": true
},
"pricing": { "input": 50, "output": 50, "hourly": 0 },
"created_at": "2024-02-21T00:24:02.387Z",
"update_at": "2024-02-21T00:24:02.387Z",
"instances": [{ "avzone": "us-east-1a", "cluster": "happypiglet" }],
"isPrivate": false,
"access_control": [],
"isFinetuned": false,
"access": "",
"hardware_label": "",
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0xEFa73cF1A2DD2Be31888913c57bf569cA27ce9E6": 1 },
"asks_updated": "2024-05-11T05:55:30.322194054Z",
"gpus": { "": 0 },
"qps": 0.13333333333333333,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"throughput_in": 366.2,
"throughput_out": 20.266666666666666,
"stats": [
{
"avzone": "us-east-1a",
"cluster": "happypiglet",
"capacity": 0.07326007326007326,
"qps": 0.13333333333333333,
"throughput_in": 366.2,
"throughput_out": 20.266666666666666,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "65a4b298fbc8405400423169",
"name": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
"display_name": "Nous Hermes 2 - Mixtral 8x7B-DPO ",
"display_type": "chat",
"description": "Nous Hermes 2 Mixtral 7bx8 DPO is the new flagship Nous Research model trained over the Mixtral 7bx8 MoE LLM. The model was trained on over 1,000,000 entries of primarily GPT-4 generated data, as well as other high quality data from open datasets across the AI landscape, achieving state of the art performance on a variety of tasks.",
"license": "apache-2.0",
"link": "https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
"creator_organization": "NousResearch",
"pricing_tier": "Featured",
"access": "open",
"num_parameters": "56000000000",
"show_in_playground": true,
"finetuning_supported": true,
"isFeaturedModel": true,
"context_length": 32768,
"config": {
"stop": ["<|im_end|>", "<|im_start|>"],
"prompt_format": "<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n",
"add_generation_prompt": true,
"chat_template_name": "default"
},
"pricing": { "input": 150, "output": 150, "hourly": 0 },
"created_at": "2024-01-15T04:20:40.079Z",
"update_at": "2024-04-12T18:35:56.478Z",
"autopilot_pool": "cr-a100-80-2x",
"instances": [
{ "avzone": "us-south-1a", "cluster": "mustymarfa" },
{ "avzone": "us-east-1a", "cluster": "happypiglet" },
{ "avzone": "us-central-5a", "cluster": "wrigleycub" }
],
"isFinetuned": false,
"hardware_label": "",
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": {
"0x17B96a27Dd71A9C4687441c14d1feCA207D0D3d4": 1,
"0x1812939B682B119d362412811237da09D9bc6c8D": 1,
"0xde2F311932B19E8Aa2069302FA701f6d0fA1B574": 1
},
"asks_updated": "2024-05-11T00:30:10.175648127Z",
"gpus": { "": 0 },
"qps": 0.9333333333333333,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"throughput_in": 887.2,
"throughput_out": 13.866666666666667,
"stats": [
{
"avzone": "us-south-1a",
"cluster": "mustymarfa",
"capacity": 0.03333333333333333,
"qps": 0.2,
"throughput_in": 301.06666666666666,
"throughput_out": 3.7333333333333334,
"error_rate": 0,
"retry_rate": 0
},
{
"avzone": "us-east-1a",
"cluster": "happypiglet",
"capacity": 0.07142857142857142,
"qps": 0.2,
"throughput_in": 173.66666666666666,
"throughput_out": 2.4,
"error_rate": 0,
"retry_rate": 0
},
{
"avzone": "us-central-5a",
"cluster": "wrigleycub",
"capacity": 0.08333333333333333,
"qps": 0.5333333333333333,
"throughput_in": 412.46666666666664,
"throughput_out": 7.733333333333333,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "65a4466efbc8405400423166",
"name": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",
"display_name": "Nous Hermes 2 - Mixtral 8x7B-SFT",
"display_type": "chat",
"description": "Nous Hermes 2 Mixtral 7bx8 SFT is the new flagship Nous Research model trained over the Mixtral 7bx8 MoE LLM. The model was trained on over 1,000,000 entries of primarily GPT-4 generated data, as well as other high quality data from open datasets across the AI landscape, achieving state of the art performance on a variety of tasks.",
"license": "apache-2.0",
"link": "https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",
"creator_organization": "NousResearch",
"pricing_tier": "Featured",
"access": "open",
"num_parameters": "56000000000",
"show_in_playground": true,
"finetuning_supported": true,
"isFeaturedModel": true,
"context_length": 32768,
"config": {
"stop": ["<|im_end|>", "<|im_start|>"],
"prompt_format": "<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n",
"add_generation_prompt": true,
"chat_template_name": "default"
},
"pricing": { "input": 150, "output": 150, "hourly": 0 },
"created_at": "2024-01-14T20:39:10.060Z",
"update_at": "2024-01-14T20:39:10.060Z",
"autopilot_pool": "cr-a100-80-2x",
"instances": [{ "avzone": "us-central-5a", "cluster": "wrigleycub" }],
"isFinetuned": false,
"hardware_label": "",
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0x3805a418c9af7eA4a88C6BC519ba95223EFe87F7": 1 },
"asks_updated": "2024-05-10T17:07:56.753575198Z",
"gpus": { "": 0 },
"qps": 0,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"stats": [
{
"avzone": "us-central-5a",
"cluster": "wrigleycub",
"capacity": 0,
"qps": 0,
"throughput_in": 0,
"throughput_out": 0,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "658c8dad27fb98d2edc447ff",
"name": "NousResearch/Nous-Hermes-2-Yi-34B",
"display_name": "Nous Hermes-2 Yi (34B)",
"display_type": "chat",
"description": "Nous Hermes 2 - Yi-34B is a state of the art Yi Fine-tune",
"license": "apache-2",
"creator_organization": "NousResearch",
"hardware_label": "A100",
"pricing_tier": "Featured",
"num_parameters": 34000000000,
"release_date": "2023-12-27T20:48:45.586Z",
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 4096,
"config": {
"stop": ["<|im_start|>", "<|im_end|>"],
"prompt_format": "<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n",
"chat_template_name": "default",
"add_generation_prompt": true
},
"pricing": { "input": 200, "output": 200 },
"created_at": "2023-12-27T20:48:45.586Z",
"update_at": "2023-12-27T20:50:38.632Z",
"instances": [{ "avzone": "ap-northeast-1a", "cluster": "optimisticotter" }],
"access": "",
"link": "",
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0x1f58b29024eba2f33b3983733396b4eda0E6f976": 1 },
"asks_updated": "2024-05-11T11:46:22.377796052Z",
"gpus": { "": 0 },
"qps": 18.266666666666666,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"throughput_in": 3213.866666666667,
"throughput_out": 438.8,
"stats": [
{
"avzone": "ap-northeast-1a",
"cluster": "optimisticotter",
"capacity": 0.45881427809138686,
"qps": 18.266666666666666,
"throughput_in": 3213.866666666667,
"throughput_out": 438.8,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "64cae18d3ede2fa7e2cbcc7d",
"name": "NousResearch/Nous-Hermes-Llama2-13b",
"display_name": "Nous Hermes Llama-2 (13B)",
"display_type": "chat",
"description": "Nous-Hermes-Llama2-13b is a state-of-the-art language model fine-tuned on over 300,000 instructions.",
"license": "mit",
"creator_organization": "NousResearch",
"hardware_label": "2x A100 80GB",
"pricing_tier": "featured",
"access": "open",
"num_parameters": 13000000000,
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 4096,
"config": {
"prompt_format": "### Instruction:\n{prompt}\n### Response:\n",
"stop": ["###", "</s>"],
"chat_template_name": "llama",
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + message['content'] + '\n' }}{% else %}{{ '### Response:\n' + message['content'] + '\n' }}{% endif %}{% endfor %}{{ '### Response:\n' }}",
"add_generation_prompt": true
},
"pricing": { "input": 75, "output": 75, "hourly": 0 },
"created_at": "2023-08-02T23:06:53.926Z",
"update_at": "2023-10-07T00:19:33.779Z",
"instances": [{ "avzone": "us-west-1a", "cluster": "curiouscrow" }],
"link": "",
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0xfA6b8e3C0ac21BA89F8e75770251f0E4e509eF90": 1 },
"asks_updated": "2024-05-10T17:59:32.616570629Z",
"gpus": { "": 0 },
"qps": 1,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"throughput_in": 1430.2,
"throughput_out": 166.06666666666666,
"stats": [
{
"avzone": "us-west-1a",
"cluster": "curiouscrow",
"capacity": 0.336864406779661,
"qps": 1,
"throughput_in": 1430.2,
"throughput_out": 166.06666666666666,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "6532f0faf94bacfc629b4cf6",
"name": "NousResearch/Nous-Hermes-llama-2-7b",
"display_name": "Nous Hermes LLaMA-2 (7B)",
"display_type": "chat",
"description": "Nous-Hermes-Llama2-7b is a state-of-the-art language model fine-tuned on over 300,000 instructions.",
"license": "LLaMA license Agreement (Meta)",
"link": "https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b",
"creator_organization": "NousResearch",
"hardware_label": "A100 80GB",
"pricing_tier": "Featured",
"access": "open",
"num_parameters": 6738415616,
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 4096,
"config": {
"prompt_format": "### Instruction:\n{prompt}\n### Response:\n",
"stop": ["###", "</s>"],
"add_generation_prompt": true,
"chat_template_name": "llama",
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + message['content'] + '\n' }}{% else %}{{ '### Response:\n' + message['content'] + '\n' }}{% endif %}{% endfor %}{{ '### Response:\n' }}"
},
"pricing": { "input": 50, "output": 50, "hourly": 0 },
"created_at": "2023-10-20T21:28:26.403Z",
"update_at": "2023-10-24T17:41:52.365Z",
"instances": [{ "avzone": "us-east-2a", "cluster": "jumpyjackal" }],
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0xf3AbD7152646995C204D8Bee0699AC58653De524": 1 },
"asks_updated": "2024-05-10T16:28:20.007677485Z",
"gpus": { "": 0 },
"qps": 0,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"stats": [
{
"avzone": "us-east-2a",
"cluster": "jumpyjackal",
"capacity": 0.06666666666666667,
"qps": 0,
"throughput_in": 0,
"throughput_out": 0,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "6532f0faf94bacfc629b4cf5",
"name": "Open-Orca/Mistral-7B-OpenOrca",
"display_name": "OpenOrca Mistral (7B) 8K",
"display_type": "chat",
"description": "An OpenOrca dataset fine-tune on top of Mistral 7B by the OpenOrca team.",
"license": "apache-2.0",
"link": "https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca",
"creator_organization": "OpenOrca",
"hardware_label": "A100 80GB",
"pricing_tier": "Featured",
"access": "open",
"num_parameters": 7241748480,
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 8192,
"config": {
"stop": ["<|im_end|>"],
"prompt_format": "<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n",
"add_generation_prompt": true,
"chat_template_name": "default"
},
"pricing": { "input": 50, "output": 50, "hourly": 0 },
"created_at": "2023-10-20T21:28:26.403Z",
"update_at": "2023-10-24T00:01:52.541Z",
"instances": [{ "avzone": "us-east-2a", "cluster": "jumpyjackal" }],
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0x802be1ae9dC8F68c43a47ec3d2070F8f1B0553E8": 1 },
"asks_updated": "2024-05-11T11:46:47.152201508Z",
"gpus": { "": 0 },
"qps": 0,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"stats": [
{
"avzone": "us-east-2a",
"cluster": "jumpyjackal",
"capacity": 0.1111111111111111,
"qps": 0,
"throughput_in": 0,
"throughput_out": 0,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "64fbbc5adfdb1e4b06b5d5cb",
"name": "Phind/Phind-CodeLlama-34B-v2",
"display_name": "Phind Code LLaMA v2 (34B)",
"display_type": "code",
"description": "Phind-CodeLlama-34B-v1 trained on additional 1.5B tokens high-quality programming-related data proficient in Python, C/C++, TypeScript, Java, and more.",
"license": "llama2",
"creator_organization": "Phind",
"hardware_label": "A100 80GB",
"pricing_tier": "supported",
"access": "open",
"num_parameters": 33743970304,
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 16384,
"config": {
"prompt_format": "### System Prompt\nYou are an intelligent programming assistant.\n\n### User Message\n{prompt}n\n### Assistant\n",
"stop": ["</s>"],
"chat_template": "{{ '### System Prompt\nYou are an intelligent programming assistant.\n\n' }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '### User Message\n' + message['content'] + '\n' }}{% else %}{{ '### Assistant\n' + message['content'] + '\n' }}{% endif %}{% endfor %}{{ '### Assistant\n' }}"
},
"pricing": { "input": 200, "output": 200, "hourly": 0 },
"created_at": "2023-09-09T00:29:14.496Z",
"update_at": "2023-09-09T00:29:14.496Z",
"instances": [{ "avzone": "us-central-5a", "cluster": "testytiger" }],
"link": "",
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0xE3b9434A627d4E042a82A4E04375E7B14D9a2866": 1 },
"asks_updated": "2024-05-10T13:54:50.844650373Z",
"gpus": { "": 0 },
"qps": 0,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"stats": [
{
"avzone": "us-central-5a",
"cluster": "testytiger",
"capacity": 0,
"qps": 0,
"throughput_in": 0,
"throughput_out": 0,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "65c0c81b4975e79f24d98b50",
"name": "Qwen/Qwen1.5-0.5B-Chat",
"display_name": "Qwen 1.5 Chat (0.5B)",
"display_type": "chat",
"description": "Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen.",
"license": "tongyi-qianwen-research",
"link": "https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat",
"creator_organization": "Qwen",
"pricing_tier": "Featured",
"num_parameters": 500000000,
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 32768,
"config": {
"prompt_format": "<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n",
"stop": ["<|im_end|>", "<|im_start|>"],
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"add_generation_prompt": true
},
"pricing": { "input": 25, "output": 25, "hourly": 0 },
"created_at": "2024-02-05T11:35:55.571Z",
"update_at": "2024-02-05T11:35:55.571Z",
"instances": [{ "avzone": "us-east-2a", "cluster": "jumpyjackal" }],
"isPrivate": false,
"access_control": [],
"isFinetuned": false,
"access": "",
"hardware_label": "",
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0x69d786B0E491C02c3053287F7FD4aa684A0f86B9": 1 },
"asks_updated": "2024-05-10T14:34:01.502238784Z",
"gpus": { "": 0 },
"qps": 0,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"stats": [
{
"avzone": "us-east-2a",
"cluster": "jumpyjackal",
"capacity": 0.07142857142857142,
"qps": 0,
"throughput_in": 0,
"throughput_out": 0,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "65c0c8164975e79f24d98b4f",
"name": "Qwen/Qwen1.5-0.5B",
"display_name": "Qwen 1.5 (0.5B)",
"display_type": "language",
"description": "Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen.",
"license": "tongyi-qianwen-research",
"link": "https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat",
"creator_organization": "Qwen",
"pricing_tier": "Featured",
"num_parameters": 500000000,
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 32768,
"config": {},
"pricing": { "input": 25, "output": 25, "hourly": 0 },
"created_at": "2024-02-05T11:35:50.032Z",
"update_at": "2024-02-05T11:35:50.032Z",
"instances": [{ "avzone": "us-east-2a", "cluster": "jumpyjackal" }],
"isPrivate": false,
"access_control": [],
"isFinetuned": false,
"access": "",
"hardware_label": "",
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0xa01d67F2450E0e7ACBfb7dc8B1a0A3205C5C8310": 1 },
"asks_updated": "2024-05-11T00:20:07.81838798Z",
"gpus": { "": 0 },
"qps": 0,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"stats": [
{
"avzone": "us-east-2a",
"cluster": "jumpyjackal",
"capacity": 0.07142857142857142,
"qps": 0,
"throughput_in": 0,
"throughput_out": 0,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "65c0c8284975e79f24d98b52",
"name": "Qwen/Qwen1.5-1.8B-Chat",
"display_name": "Qwen 1.5 Chat (1.8B)",
"display_type": "chat",
"description": "Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen.",
"license": "tongyi-qianwen-research",
"link": "https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat",
"creator_organization": "Qwen",
"pricing_tier": "Featured",
"num_parameters": 1800000000,
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 32768,
"config": {
"prompt_format": "<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n",
"stop": ["<|im_end|>", "<|im_start|>"],
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"add_generation_prompt": true
},
"pricing": { "input": 25, "output": 25, "hourly": 0 },
"created_at": "2024-02-05T11:36:08.609Z",
"update_at": "2024-02-05T11:36:08.609Z",
"instances": [{ "avzone": "us-east-2a", "cluster": "jumpyjackal" }],
"isPrivate": false,
"access_control": [],
"isFinetuned": false,
"access": "",
"hardware_label": "",
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0x332b426661a850784BAcFd12B9E7D9b51397B1ec": 1 },
"asks_updated": "2024-05-10T19:50:02.900326326Z",
"gpus": { "": 0 },
"qps": 0,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"stats": [
{
"avzone": "us-east-2a",
"cluster": "jumpyjackal",
"capacity": 0.16666666666666666,
"qps": 0,
"throughput_in": 0,
"throughput_out": 0,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "65c0c8214975e79f24d98b51",
"name": "Qwen/Qwen1.5-1.8B",
"display_name": "Qwen 1.5 (1.8B)",
"display_type": "language",
"description": "Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen.",
"license": "tongyi-qianwen-research",
"link": "https://huggingface.co/Qwen/Qwen1.5-1.8B",
"creator_organization": "Qwen",
"pricing_tier": "Featured",
"num_parameters": 1800000000,
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 32768,
"config": {},
"pricing": { "input": 25, "output": 25, "hourly": 0 },
"created_at": "2024-02-05T11:36:01.895Z",
"update_at": "2024-02-05T11:36:01.895Z",
"instances": [{ "avzone": "us-east-2a", "cluster": "jumpyjackal" }],
"isPrivate": false,
"access_control": [],
"isFinetuned": false,
"access": "",
"hardware_label": "",
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0xE1E3e79fC7e677c1Bdb8E6f6B6dde0B5d78C2ABc": 1 },
"asks_updated": "2024-05-10T13:22:12.143866414Z",
"gpus": { "": 0 },
"qps": 0,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"stats": [
{
"avzone": "us-east-2a",
"cluster": "jumpyjackal",
"capacity": 0.16666666666666666,
"qps": 0,
"throughput_in": 0,
"throughput_out": 0,
"error_rate": 0,
"retry_rate": 0
}
]
}
},
{
"modelInstanceConfig": { "appearsIn": [], "order": 0 },
"_id": "663929111a16009453d858d6",
"name": "Qwen/Qwen1.5-110B-Chat",
"display_name": "Qwen 1.5 Chat (110B)",
"display_type": "chat",
"description": "Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen.",
"license": "tongyi-qianwen-research",
"link": "https://huggingface.co/Qwen/Qwen1.5-110B-Chat",
"creator_organization": "Qwen",
"pricing_tier": "Featured",
"num_parameters": 110000000000,
"show_in_playground": true,
"isFeaturedModel": true,
"context_length": 32768,
"owner_userid": null,
"config": {
"stop": ["<|im_end|>"],
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"add_generation_prompt": true
},
"pricing": { "input": 450, "output": 450, "hourly": 0 },
"created_at": "2024-05-06T19:01:37.206Z",
"update_at": "2024-05-06T19:01:37.206Z",
"instances": [{ "avzone": "us-south-1a", "cluster": "mustymarfa" }],
"isPrivate": false,
"access_control": [],
"isDedicatedInstance": false,
"isFinetuned": false,
"access": "",
"hardware_label": "",
"descriptionLink": "",
"depth": {
"num_asks": 1,
"num_bids": 0,
"num_running": 0,
"asks": { "0x1bfE8838c1A5fA63cc1120e2de1Bce2599FDd946": 1 },
"asks_updated": "2024-05-11T09:12:31.886283279Z",
"gpus": { "": 0 },
"qps": 0.26666666666666666,
"permit_required": false,
"price": { "base": 0, "finetune": 0, "hourly": 0, "input": 0, "output": 0 },
"throughput_in": 143.4,
"throughput_out": 42.6,
"stats": [
{
"avzone": "us-south-1a",
"cluster": "mustymarfa",
"capacity": 0.0476310802274163,
"qps": 0.266666666666