-
Notifications
You must be signed in to change notification settings - Fork 1.7k
Expand file tree
/
Copy pathdev.yaml
More file actions
227 lines (216 loc) · 22.3 KB
/
Copy pathdev.yaml
File metadata and controls
227 lines (216 loc) · 22.3 KB
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
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
image:
repository: huggingface
name: chat-ui
#nodeSelector:
# role-huggingchat: "true"
#
#tolerations:
# - key: "huggingface.co/huggingchat"
# operator: "Equal"
# value: "true"
# effect: "NoSchedule"
serviceAccount:
enabled: true
create: true
name: huggingchat-ephemeral
ingress:
enabled: false
ingressInternal:
enabled: true
path: "/chat"
annotations:
external-dns.alpha.kubernetes.io/hostname: "*.chat-dev.huggingface.tech"
alb.ingress.kubernetes.io/healthcheck-path: "/chat/healthcheck"
alb.ingress.kubernetes.io/listen-ports: "[{\"HTTP\": 80}, {\"HTTPS\": 443}]"
alb.ingress.kubernetes.io/group.name: "chat-dev-internal-public"
alb.ingress.kubernetes.io/load-balancer-name: "chat-dev-internal-public"
alb.ingress.kubernetes.io/ssl-redirect: "443"
alb.ingress.kubernetes.io/tags: "Env=prod,Project=hub,Terraform=true"
alb.ingress.kubernetes.io/target-group-attributes: deregistration_delay.timeout_seconds=30
alb.ingress.kubernetes.io/target-type: "ip"
alb.ingress.kubernetes.io/certificate-arn: "arn:aws:acm:us-east-1:707930574880:certificate/bc3eb446-1c04-432c-ac6b-946a88d725da"
kubernetes.io/ingress.class: "alb"
envVars:
TEST: "test"
COUPLE_SESSION_WITH_COOKIE_NAME: "token"
OPENID_SCOPES: "openid profile inference-api read-mcp read-billing contribute-repos"
USE_USER_TOKEN: "true"
MCP_FORWARD_HF_USER_TOKEN: "true"
AUTOMATIC_LOGIN: "false"
ADDRESS_HEADER: "X-Forwarded-For"
APP_BASE: "/chat"
ALLOW_IFRAME: "false"
COOKIE_SAMESITE: "lax"
COOKIE_SECURE: "true"
EXPOSE_API: "true"
METRICS_ENABLED: "true"
LOG_LEVEL: "debug"
NODE_LOG_STRUCTURED_DATA: "true"
OPENAI_BASE_URL: "https://router.huggingface.co/v1"
PUBLIC_APP_ASSETS: "huggingchat"
PUBLIC_APP_NAME: "HuggingChat"
PUBLIC_APP_DESCRIPTION: "Making the community's best AI chat models available to everyone"
PUBLIC_ORIGIN: ""
PUBLIC_PLAUSIBLE_SCRIPT_URL: "https://plausible.io/js/pa-Io_oigECawqdlgpf5qvHb.js"
PUBLIC_FEATURE_ANNOUNCEMENTS: >
[{"title": "Gemma-4-31B at 700 tokens/s", "description": "Run Gemma-4-31B at 700 tokens/s thanks to Cerebras inference.", "link": "/models/google/gemma-4-31B-it", "cta": "Go to the model", "maxDate": "2026-08-01"}]
TASK_MODEL: "meta-llama/Llama-3.1-8B-Instruct"
# Tombstone: unread by current code, kept so any old pod still on the pre-#2265
# image (which gated Omni on LLM_ROUTER_ARCH_BASE_URL) keeps registering the alias
# during rollout. Safe to remove once every replica is on the new image.
LLM_ROUTER_ARCH_BASE_URL: "https://router.huggingface.co/v1"
LLM_ROUTER_ROUTES_PATH: "build/client/chat/huggingchat/routes.chat.json"
LLM_ROUTER_ENABLE_MULTIMODAL: "true"
LLM_ROUTER_MULTIMODAL_MODEL: "moonshotai/Kimi-K2.6"
LLM_ROUTER_ENABLE_TOOLS: "true"
LLM_ROUTER_TOOLS_MODEL: "moonshotai/Kimi-K2.6"
TRANSCRIPTION_MODEL: "openai/whisper-large-v3-turbo"
MCP_SERVERS: >
[{"name": "Web Search (Exa)", "url": "https://mcp.exa.ai/mcp?tools=web_search_exa,get_code_context_exa,crawling_exa"}, {"name": "Hugging Face", "url": "https://hf.co/mcp?login"}]
MCP_TOOL_TIMEOUT_MS: "120000"
PUBLIC_LLM_ROUTER_DISPLAY_NAME: "Omni"
PUBLIC_LLM_ROUTER_LOGO_URL: "https://cdn-uploads.huggingface.co/production/uploads/5f17f0a0925b9863e28ad517/C5V0v1xZXv6M7FXsdJH9b.png"
PUBLIC_LLM_ROUTER_ALIAS_ID: "omni"
MODELS: >
[
{ "id": "omni", "supportsArtifacts": true },
{ "id": "XiaomiMiMo/MiMo-V2.5-Pro", "description": "1T MoE with 42B active params, hybrid attention, and 1M context.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "moonshotai/Kimi-K2-Thinking", "description": "Trillion-param MoE thinking agent for deep reasoning and sustained tool chains.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "description": "BF16 hybrid Mamba-Transformer 550B MoE with 55B active params for agentic reasoning.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "stepfun-ai/Step-3.7-Flash", "description": "Vision-language 198B MoE with 11B active params, reasoning modes, and 256K context.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "deepreinforce-ai/Ornith-1.0-35B", "description": "RL-tuned 35B MoE coding agent with thinking mode and 262K context.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "deepreinforce-ai/Ornith-1.0-35B-FP8", "description": "FP8 Ornith 35B MoE for efficient agentic coding with thinking mode.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "google/gemma-3-12b-it", "description": "Dense 12B multimodal Gemma with 128K context and multilingual support." },
{ "id": "google/gemma-3-4b-it", "description": "Compact 4B multimodal Gemma with 128K context for lightweight tasks." },
{ "id": "microsoft/phi-4", "description": "Dense 14B model with strong math, reasoning, and coding density." },
{ "id": "speakleash/Bielik-11B-v3.0-Instruct", "description": "Polish-language 11B instruction model for chat, writing, and comprehension." },
{ "id": "zai-org/GLM-5.2", "description": "Flagship 744B MoE for agentic engineering with 1M context and thinking modes.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "zai-org/GLM-5.2-FP8", "description": "FP8 GLM-5.2 for efficient agentic engineering and extended reasoning.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "moonshotai/Kimi-K2.7-Code", "description": "1T MoE coding agent with persistent thinking across long tool workflows." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } },
{ "id": "MiniMaxAI/MiniMax-M3", "description": "Natively multimodal 428B MoE with 1M context for frontier coding and agents." , "supportsReasoning": true, "supportsArtifacts": true, "parameters": { "max_tokens": 98304 } },
{ "id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", "description": "Hybrid Mamba-Transformer 550B MoE with 55B active params for efficient agentic reasoning.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "Qwen/Qwen3.6-27B", "description": "Dense 27B hybrid with DeltaNet attention and 1M context.", "supportsArtifacts": true },
{ "id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "description": "Native multimodal 17B MoE with 16 experts and very long context."},
{ "id": "CohereLabs/c4ai-command-r7b-12-2024", "description": "Compact 7B Command R for multilingual RAG, tool use, and agents." },
{ "id": "pearl-ai/Gemma-4-31B-it-pearl", "description": "Community Gemma-4-31B variant integrated with Pearl mining for chain-validated inference."},
{ "id": "inclusionAI/Ling-2.6-1T", "description": "1T MoE with 50B active params, hybrid MLA-Linear attention, and fast thinking.", "supportsArtifacts": true },
{ "id": "deepseek-ai/DeepSeek-V4-Pro", "description": "Frontier 1.6T MoE with 49B active params, hybrid attention, and 1M context.", "parameters": { "max_tokens": 98304 }, "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "deepseek-ai/DeepSeek-V4-Flash", "description": "Compact 284B MoE with 13B active params, hybrid attention, and 1M context.", "parameters": { "max_tokens": 49152 }, "supportsArtifacts": true },
{ "id": "deepseek-ai/DeepSeek-V3.2", "description": "Stable 671B MoE with sparse attention for agentic reasoning and long contexts.", "supportsArtifacts": true },
{ "id": "stepfun-ai/Step-3.5-Flash", "description": "Sparse 197B MoE agent with multi-token prediction and 256K context.", "supportsArtifacts": true },
{ "id": "Qwen/Qwen3.6-35B-A3B", "description": "Hybrid 35B MoE with 3B active params, DeltaNet attention, and 1M context.", "supportsArtifacts": true },
{ "id": "zai-org/GLM-4.7-Flash", "description": "Compact 30B MoE for agentic coding with 128K context and tool use.", "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "moonshotai/Kimi-K2.6", "description": "Native multimodal 1T MoE for long-horizon coding and 300-sub-agent swarms.", "supportsArtifacts": true },
{ "id": "MiniMaxAI/MiniMax-M2.7", "description": "Self-evolving 230B MoE agent for frontier coding, reasoning, and tool use." , "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "zai-org/GLM-5.1", "description": "Upgraded 754B MoE for agentic coding, extended reasoning, and tool use.", "parameters": { "max_tokens": 98304 } , "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "zai-org/GLM-5.1-FP8", "description": "FP8 GLM-5.1 for efficient agentic coding and reasoning inference.", "parameters": { "max_tokens": 98304 } , "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "google/gemma-4-31B-it", "description": "Dense multimodal Gemma with 256K context, reasoning, and function calling.", "supportsArtifacts": true},
{ "id": "google/gemma-4-26B-A4B-it", "description": "Efficient multimodal MoE Gemma with 4B active params and 256K context."},
{ "id": "Qwen/Qwen3.5-9B", "description": "Dense multimodal hybrid with 262K context excelling at reasoning on-device."},
{ "id": "CohereLabs/tiny-aya-global", "description": "Tiny multilingual assistant covering 70+ languages for on-device deployment." },
{ "id": "CohereLabs/tiny-aya-earth", "description": "Regional Aya for African languages with culturally tuned on-device inference." },
{ "id": "CohereLabs/tiny-aya-water", "description": "Regional Aya for Asia-Pacific and European multilingual on-device tasks." },
{ "id": "Qwen/Qwen3.5-122B-A10B", "description": "Multimodal MoE excelling at agentic tool use with 1M context and 201 languages.", "supportsArtifacts": true },
{ "id": "Qwen/Qwen3.5-35B-A3B", "description": "Compact multimodal MoE with hybrid DeltaNet, 1M context, and 201 languages.", "supportsArtifacts": true },
{ "id": "Qwen/Qwen3.5-27B", "description": "Dense multimodal hybrid with top-tier reasoning density and 1M context."},
{ "id": "Qwen/Qwen3.5-397B-A17B", "description": "Native multimodal MoE with hybrid attention, 1M context, and 201 languages.", "parameters": { "max_tokens": 32768 } },
{ "id": "MiniMaxAI/MiniMax-M2.5", "description": "Frontier 230B MoE agent for top-tier coding, tool calling, and fast inference." , "supportsReasoning": true },
{ "id": "zai-org/GLM-5", "description": "Flagship 745B MoE for agentic reasoning, coding, and creative writing."},
{ "id": "Qwen/Qwen3-VL-235B-A22B-Instruct", "description": "Flagship Qwen3 vision-language MoE for visual agents, documents, and GUI automation." },
{ "id": "google/gemma-3n-E4B-it", "description": "Mobile-first multimodal Gemma handling text, images, video, and audio on-device." },
{ "id": "Qwen/Qwen3-Coder-Next", "description": "Ultra-sparse coding MoE for repository-scale agents with 256K context." },
{ "id": "moonshotai/Kimi-K2.5", "description": "Native multimodal agent with agent swarms for parallel tool orchestration." },
{ "id": "zai-org/GLM-4.7", "description": "Flagship GLM MoE for coding, reasoning, and agentic tool use." , "supportsReasoning": true },
{ "id": "zai-org/GLM-4.7-FP8", "description": "FP8 GLM-4.7 for efficient inference with strong coding." , "supportsReasoning": true },
{ "id": "MiniMaxAI/MiniMax-M2.1", "description": "MoE agent model with multilingual coding and fast outputs."},
{ "id": "zai-org/AutoGLM-Phone-9B-Multilingual", "description": "Mobile agent for multilingual Android device automation." },
{ "id": "utter-project/EuroLLM-22B-Instruct-2512", "description": "European multilingual model for all EU languages and translation." },
{ "id": "MiniMaxAI/MiniMax-M2", "description": "Compact MoE model tuned for fast coding, agentic workflows, and long-context chat." , "supportsReasoning": true },
{ "id": "Qwen/Qwen3-VL-30B-A3B-Instruct", "description": "Flagship Qwen3 vision-language model for high-accuracy image, text, and video reasoning." },
{ "id": "Qwen/Qwen3-VL-30B-A3B-Thinking", "description": "Thinking-mode Qwen3-VL that emits detailed multimodal reasoning traces for difficult problems."},
{ "id": "Qwen/Qwen3-VL-8B-Instruct", "description": "Smaller Qwen3 vision-language assistant for everyday multimodal chat, captioning, and analysis." },
{ "id": "aisingapore/Qwen-SEA-LION-v4-32B-IT", "description": "SEA-LION v4 Qwen optimized for Southeast Asian languages and regional enterprise workloads." },
{ "id": "allenai/Olmo-3-7B-Instruct", "description": "Lightweight Olmo assistant for instruction following, Q&A, and everyday open-source workflows." },
{ "id": "deepcogito/cogito-671b-v2.1", "description": "Frontier-scale 671B MoE focused on deep reasoning, math proofs, and complex coding."},
{ "id": "deepcogito/cogito-671b-v2.1-FP8", "description": "FP8 Cogito v2.1 making 671B-scale reasoning more affordable to serve and experiment with."},
{ "id": "openai/gpt-oss-safeguard-20b", "description": "Safety-focused gpt-oss variant for content classification, policy enforcement, and LLM output filtering." , "supportsReasoning": true },
{ "id": "zai-org/GLM-4.5", "description": "Flagship GLM agent model unifying advanced reasoning, coding, and tool-using capabilities."},
{ "id": "zai-org/GLM-4.5V-FP8", "description": "FP8 vision-language GLM-4.5V for efficient multilingual visual QA, understanding, and hybrid reasoning."},
{ "id": "deepseek-ai/DeepSeek-V3.2-Exp", "description": "Experimental V3.2 release focused on faster, lower-cost inference with strong general reasoning and tool use."},
{ "id": "zai-org/GLM-4.6", "description": "Next-gen GLM with very long context and solid multilingual reasoning; good for agents and tools."},
{ "id": "Qwen/Qwen2.5-VL-72B-Instruct", "description": "Flagship multimodal Qwen (text+image) instruction model for high-accuracy visual reasoning and detailed explanations." },
{ "id": "deepseek-ai/DeepSeek-V3.1-Terminus", "description": "Refined V3.1 variant optimized for reliability on long contexts, structured outputs, and tool use."},
{ "id": "Qwen/Qwen3-VL-235B-A22B-Thinking", "description": "Deliberative multimodal Qwen that can produce step-wise visual+text reasoning traces for complex tasks."},
{ "id": "zai-org/GLM-4.6-FP8", "description": "FP8-optimized GLM-4.6 for faster/cheaper deployment with near-parity quality on most tasks."},
{ "id": "zai-org/GLM-4.6V", "description": "106B vision-language model with 128K context and native tool calling for multimodal agents.", "parameters": { "max_tokens": 8192 }},
{ "id": "zai-org/GLM-4.6V-Flash", "description": "9B lightweight vision model for fast local inference with tool calling and UI understanding."},
{ "id": "zai-org/GLM-4.6V-FP8", "description": "FP8-quantized GLM-4.6V for efficient multimodal deployment with native tool use."},
{ "id": "Qwen/Qwen3-235B-A22B-Thinking-2507", "description": "Deliberative text-only 235B Qwen variant for transparent, step-by-step reasoning on hard problems."},
{ "id": "Qwen/Qwen3-Next-80B-A3B-Instruct", "description": "Instruction tuned Qwen for multilingual reasoning, coding, long contexts." },
{ "id": "Qwen/Qwen3-Next-80B-A3B-Thinking", "description": "Thinking mode Qwen that outputs explicit step by step reasoning."},
{ "id": "moonshotai/Kimi-K2-Instruct-0905", "description": "Instruction MoE strong coding and multi step reasoning, long context." },
{ "id": "openai/gpt-oss-20b", "description": "Efficient open model for reasoning and tool use, runs locally." , "supportsReasoning": true },
{ "id": "swiss-ai/Apertus-8B-Instruct-2509", "description": "Open, multilingual, trained on compliant data transparent global assistant." },
{ "id": "openai/gpt-oss-120b", "description": "High performing open model suitable for large scale applications." , "supportsReasoning": true, "supportsArtifacts": true },
{ "id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "description": "Code specialized Qwen long context strong generation and function calling." },
{ "id": "meta-llama/Llama-3.1-8B-Instruct", "description": "Instruction tuned Llama efficient conversational assistant with improved alignment." },
{ "id": "deepseek-ai/DeepSeek-R1", "description": "MoE reasoning model excels at math, logic, coding with steps."},
{ "id": "swiss-ai/Apertus-70B-Instruct-2509", "description": "Open multilingual model trained on open data transparent and capable." },
{ "id": "Qwen/Qwen3-4B-Instruct-2507", "description": "Compact instruction Qwen great for lightweight assistants and apps." },
{ "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "description": "Huge Qwen coder repository scale understanding and advanced generation." },
{ "id": "meta-llama/Meta-Llama-3-8B-Instruct", "description": "Aligned, efficient Llama dependable open source assistant tasks." },
{ "id": "Qwen/Qwen3-4B-Thinking-2507", "description": "Small Qwen that emits transparent step by step reasoning."},
{ "id": "moonshotai/Kimi-K2-Instruct", "description": "MoE assistant strong coding, reasoning, agentic tasks, long context." },
{ "id": "zai-org/GLM-4.5V", "description": "Vision language MoE state of the art multimodal reasoning."},
{ "id": "deepseek-ai/DeepSeek-V3.1", "description": "Supports direct and thinking style reasoning within one model."},
{ "id": "Qwen/Qwen3-8B", "description": "Efficient Qwen assistant strong multilingual skills and formatting." },
{ "id": "google/gemma-3-27b-it", "description": "Multimodal Gemma long context strong text and image understanding." },
{ "id": "zai-org/GLM-4.5-Air", "description": "Efficient GLM strong reasoning and tool use at lower cost."},
{ "id": "Qwen/Qwen2.5-7B-Instruct", "description": "Compact instruction model solid for basic conversation and tasks." },
{ "id": "Qwen/Qwen3-32B", "description": "General purpose Qwen strong for complex queries and dialogues." },
{ "id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "description": "Flagship instruction Qwen near state of the art across domains." },
{ "id": "meta-llama/Llama-3.3-70B-Instruct", "description": "Improved Llama alignment and structure powerful complex conversations." },
{ "id": "Qwen/Qwen3-235B-A22B", "description": "Qwen base at flagship scale ideal for custom fine tuning." },
{ "id": "Qwen/Qwen2.5-Coder-32B-Instruct", "description": "Code model strong generation and tool use bridges sizes." },
{ "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "description": "Distilled Qwen excels at stepwise logic in compact footprint."},
{ "id": "deepseek-ai/DeepSeek-V3", "description": "General language model direct answers strong creative and knowledge tasks." },
{ "id": "deepseek-ai/DeepSeek-V3-0324", "description": "Updated V3 better reasoning and coding strong tool use." },
{ "id": "CohereLabs/command-a-translate-08-2025", "description": "Translation focused Command model high quality multilingual translation." },
{ "id": "baidu/ERNIE-4.5-VL-424B-A47B-Base-PT", "description": "Multimodal base text image pretraining for cross modal understanding." },
{ "id": "deepseek-ai/DeepSeek-R1-0528", "description": "R1 update improved reasoning, fewer hallucinations, adds function calling.", "parameters": { "max_tokens": 32000 }},
{ "id": "Qwen/Qwen3-14B", "description": "Balanced Qwen good performance and efficiency for assistants." },
{ "id": "MiniMaxAI/MiniMax-M1-80k", "description": "Long context MoE very fast excels at long range reasoning and code."},
{ "id": "Qwen/Qwen2.5-Coder-7B-Instruct", "description": "Efficient coding assistant for lightweight programming tasks." },
{ "id": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "description": "Gemma SEA LION optimized for Southeast Asian languages or enterprise." },
{ "id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "description": "FP8 Maverick efficient deployment retains top multimodal capability." },
{ "id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B", "description": "Llama distilled from R1 strong reasoning and structured outputs."},
{ "id": "Qwen/Qwen2.5-72B-Instruct", "description": "Accurate detailed instruction model supports tools and long contexts." },
{ "id": "meta-llama/Llama-Guard-4-12B", "description": "Safety guardrail model filters and enforces content policies." },
{ "id": "CohereLabs/command-a-vision-07-2025", "description": "Command model with image input captioning and visual QA." },
{ "id": "Sao10K/L3-8B-Stheno-v3.2", "description": "Community Llama variant themed tuning and unique conversational style." },
{ "id": "CohereLabs/c4ai-command-r-08-2024", "description": "Cohere Command variant instruction following with specialized tuning." },
{ "id": "CohereLabs/aya-expanse-32b", "description": "Aya Expanse large comprehensive knowledge and reasoning capabilities." },
{ "id": "CohereLabs/c4ai-command-a-03-2025", "description": "Updated Command assistant improved accuracy and general usefulness." },
{ "id": "CohereLabs/command-a-reasoning-08-2025", "description": "Command variant optimized for complex multi step logical reasoning." },
{ "id": "alpindale/WizardLM-2-8x22B", "description": "Multi expert WizardLM MoE approach for efficient high quality generation." },
{ "id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "description": "Llama distilled from R1 improved reasoning enterprise friendly."},
{ "id": "CohereLabs/aya-vision-32b", "description": "Larger Aya Vision advanced vision language with detailed reasoning." },
{ "id": "CohereLabs/c4ai-command-r7b-arabic-02-2025", "description": "Command tuned for Arabic fluent and culturally appropriate outputs." },
{ "id": "Sao10K/L3-8B-Lunaris-v1", "description": "Community Llama creative role play oriented themed persona." },
{ "id": "meta-llama/Llama-3.1-70B-Instruct", "description": "Instruction tuned Llama improved reasoning and factual reliability." },
{ "id": "zai-org/GLM-4-32B-0414", "description": "Open licensed GLM matches larger proprietary models on benchmarks." },
{ "id": "Qwen/Qwen2.5-Coder-3B-Instruct", "description": "Tiny coding assistant basic code completions and explanations." }
]
infisical:
enabled: true
env: "ephemeral-us-east-1"
replicas: 1
autoscaling:
enabled: false
resources:
requests:
cpu: 2
memory: 4Gi
limits:
cpu: 4
memory: 8Gi