File size: 1,523 Bytes
52eefc9 |
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 |
{
"config_version": "1.0.0",
"model_id": "Qwen/Qwen2.5-7B",
"model_kinds": [
"ARTIFACT"
],
"model_class": {
"module": "furiosa_models.architecture.models.qwen2",
"name": "Qwen2ForCausalLM"
},
"llm_config": {
"optimization_config": {
"attention_type": "PAGED_ATTENTION",
"optimize_rope": true,
"optimize_packed": true,
"decompose_layernorm": false,
"optimize_furiosa": false,
"use_unsplit_packed": false,
"compact_causal_mask": false,
"use_rngd_gelu": false,
"causal_mask_free_decoding": true,
"kv_cache_sharing_across_beams": false,
"inbound_beamsearch_softmax": false,
"calculate_logit_only_for_last_token": false,
"optimized_for_speculative_decoding": true,
"use_2d_masks": false,
"merged_kv_indices": false
},
"quantization_config": {
"weight": "bf16",
"activation": "bf16",
"kv_cache": "bf16",
"use_mcp": false
}
},
"components_versions": {
"furiosa_llm": {
"version": "0.1.0-dev",
"git_hash": "0d00aee",
"build_time": null
},
"furiosa_ir": {
"version": "0.11.0-dev",
"git_hash": "4467f6a699",
"build_time": "2025-08-27T04:38:44Z"
},
"furiosa_runtime": {
"version": "2025.3.1",
"git_hash": "0d00aee20",
"build_time": "2025-08-27T04:38:48Z"
},
"furiosa_model_compressor": {
"version": "2025.3.0 (rev: 4cd9804)",
"git_hash": null,
"build_time": null
}
}
} |