AMAImedia/Qwen3-8B-Nemotron-Orchestrator-NOESIS-AWQ-INT4
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: AMAImedia/Qwen3-8B-Nemotron-Orchestrator-NOESIS-AWQ-INT4
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 22:31:29 +08:00
commit cdc5bafc1f
12 changed files with 1551 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
noesis_provenance.json Normal file
View File

@@ -0,0 +1,31 @@
{
"noesis_version": "v14.1",
"framework": "DHCF-FNO",
"founder": "Ilia Bolotnikov",
"organization": "AMAImedia.com",
"source_model": "nvidia/Nemotron-Orchestrator-8B",
"source_format": "FP32 safetensors",
"source_license": "NVIDIA Open Model License (research and development only)",
"base_model": "Qwen/Qwen3-8B",
"architecture": "Qwen3ForCausalLM (dense decoder-only, NO MoE)",
"vocab_size": 151936,
"language": "en",
"quantization": {
"method": "AWQ",
"library": "autoawq 0.2.9",
"zero_point": true,
"q_group_size": 128,
"w_bit": 4,
"version": "GEMM"
},
"calibration": {
"samples": 128,
"max_seq_len": 512,
"domain": "orchestration_tool_calling_english",
"source": "in-memory synthetic prompts (NOESIS internal)"
},
"specialist_role": "M9-ORCH (English orchestration teacher)",
"kd_weight_proposed": 0.22,
"rng_seed": 1729,
"torch_dtype_quant": "bfloat16"
}