Text Generation
Transformers
Safetensors
qwen3_5_moe_text
darwin
darwin-v7
evolutionary-merge
reasoning
advanced-reasoning
chain-of-thought
thinking
qwen3.6
qwen
Mixture of Experts
mixture-of-experts
claude-opus
distillation
gpqa
benchmark
open-source
apache-2.0
hybrid-vigor
proto-agi
vidraft
Eval Results
conversational
Eval Results (legacy)
Instructions to use FINAL-Bench/Darwin-36B-Opus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FINAL-Bench/Darwin-36B-Opus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-36B-Opus") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("FINAL-Bench/Darwin-36B-Opus") model = AutoModelForCausalLM.from_pretrained("FINAL-Bench/Darwin-36B-Opus") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use FINAL-Bench/Darwin-36B-Opus with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "FINAL-Bench/Darwin-36B-Opus" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FINAL-Bench/Darwin-36B-Opus", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/FINAL-Bench/Darwin-36B-Opus
- SGLang
How to use FINAL-Bench/Darwin-36B-Opus with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "FINAL-Bench/Darwin-36B-Opus" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FINAL-Bench/Darwin-36B-Opus", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "FINAL-Bench/Darwin-36B-Opus" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FINAL-Bench/Darwin-36B-Opus", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use FINAL-Bench/Darwin-36B-Opus with Docker Model Runner:
docker model run hf.co/FINAL-Bench/Darwin-36B-Opus
Remove internal methodology files (trade secrets protection)
Browse files- darwin_mri_report.json +0 -31
- darwin_v6_report.json +0 -69
- lora_train_config.json +0 -28
- parent_comparison.png +0 -3
- prescription_ratios.png +0 -0
darwin_mri_report.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"method": "Darwin V7+ MRI-only (Mother-centric Linear)",
|
| 3 |
-
"father": "/NHNHOME/WORKSPACE/0426030024_A/darwin-36b-opus/models/Father-Qwen3.6-35B-A3B",
|
| 4 |
-
"mother": "/NHNHOME/WORKSPACE/0426030024_A/darwin-36b-opus/models/Mother-hesamation-Opus46",
|
| 5 |
-
"mri_trust": 0.8,
|
| 6 |
-
"mother_bias": 0.85,
|
| 7 |
-
"category_ratios": {
|
| 8 |
-
"attention": 0.9,
|
| 9 |
-
"router": 1.0,
|
| 10 |
-
"shared_expert": 0.9,
|
| 11 |
-
"routed_expert": 0.8,
|
| 12 |
-
"embedding": 1.0,
|
| 13 |
-
"lm_head": 1.0,
|
| 14 |
-
"norm": 0.95,
|
| 15 |
-
"other": 0.85
|
| 16 |
-
},
|
| 17 |
-
"mri_overrides": 82,
|
| 18 |
-
"tensor_categories": {
|
| 19 |
-
"attention": 485,
|
| 20 |
-
"router": 41,
|
| 21 |
-
"shared_expert": 164,
|
| 22 |
-
"routed_expert": 82,
|
| 23 |
-
"embedding": 5,
|
| 24 |
-
"lm_head": 1,
|
| 25 |
-
"norm": 154,
|
| 26 |
-
"other": 113
|
| 27 |
-
},
|
| 28 |
-
"total_tensors": 1045,
|
| 29 |
-
"total_shards": 21,
|
| 30 |
-
"elapsed_sec": 493
|
| 31 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
darwin_v6_report.json
DELETED
|
@@ -1,69 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"version": "darwin_v6",
|
| 3 |
-
"model_a": "Qwen/Qwen3.6-35B-A3B",
|
| 4 |
-
"model_b": "hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled",
|
| 5 |
-
"scan_time_a": 161.1855502128601,
|
| 6 |
-
"scan_time_b": 149.11143231391907,
|
| 7 |
-
"prescription": {
|
| 8 |
-
"total_tensors": 1045,
|
| 9 |
-
"avg_ratio_b": 0.49999984425441674,
|
| 10 |
-
"avg_attn_ratio": 0.499985450760254,
|
| 11 |
-
"avg_ffn_ratio": 0.5000152414508509,
|
| 12 |
-
"avg_embed_ratio": 0.49999999999992895,
|
| 13 |
-
"transplant_a_count": 0,
|
| 14 |
-
"transplant_b_count": 0,
|
| 15 |
-
"blended_count": 1045
|
| 16 |
-
},
|
| 17 |
-
"recommended_genome": {
|
| 18 |
-
"global_ratio": 0.49999984425441674,
|
| 19 |
-
"attn_ratio": 0.499985450760254,
|
| 20 |
-
"ffn_ratio": 0.5000152414508509,
|
| 21 |
-
"embed_ratio": 0.49999999999992895,
|
| 22 |
-
"block_ratios": [
|
| 23 |
-
0.5000721444413114,
|
| 24 |
-
0.4998433134008189,
|
| 25 |
-
0.499780888197006,
|
| 26 |
-
0.4997929703763515,
|
| 27 |
-
0.499771132051783,
|
| 28 |
-
0.4997801248073877,
|
| 29 |
-
0.499745996175545,
|
| 30 |
-
0.5012345529552215
|
| 31 |
-
],
|
| 32 |
-
"mri_trust": 0.7
|
| 33 |
-
},
|
| 34 |
-
"evolution": {
|
| 35 |
-
"best_score": 0.8402656748646429,
|
| 36 |
-
"best_genome": [
|
| 37 |
-
0.4936662919610739,
|
| 38 |
-
0.0815242519055706,
|
| 39 |
-
0.9341507094494833,
|
| 40 |
-
0.36828574975395845,
|
| 41 |
-
0.9482560366006947,
|
| 42 |
-
0.9930202372461144,
|
| 43 |
-
0.6267934460397571,
|
| 44 |
-
0.7804501296513594,
|
| 45 |
-
0.5091179237088572,
|
| 46 |
-
0.5273575416938678,
|
| 47 |
-
0.3549558469479533,
|
| 48 |
-
0.2945505642361962,
|
| 49 |
-
0.7838544898184714,
|
| 50 |
-
0.47445473021143214,
|
| 51 |
-
0.7214881982362042,
|
| 52 |
-
0.7737746038647229
|
| 53 |
-
],
|
| 54 |
-
"elapsed_sec": 2909.7664647102356,
|
| 55 |
-
"merge_report": {
|
| 56 |
-
"total": 1045,
|
| 57 |
-
"transplant_a": 0,
|
| 58 |
-
"transplant_b": 0,
|
| 59 |
-
"blended": 1045,
|
| 60 |
-
"method": "slerp",
|
| 61 |
-
"genome_hash": "8fc46eeb"
|
| 62 |
-
}
|
| 63 |
-
},
|
| 64 |
-
"health": {
|
| 65 |
-
"status": "healthy",
|
| 66 |
-
"summary": "failed: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/home/gmail_be2j/darwin_merge_cache/merged_6edaacaf'. Use `repo_type` argument if needed.",
|
| 67 |
-
"issue_count": 0
|
| 68 |
-
}
|
| 69 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
lora_train_config.json
DELETED
|
@@ -1,28 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"version": "v3_safe",
|
| 3 |
-
"base": "/NHNHOME/WORKSPACE/0426030024_A/darwin-36b-opus/models/Darwin-36B-Opus-v2",
|
| 4 |
-
"lora": {
|
| 5 |
-
"rank": 16,
|
| 6 |
-
"alpha": 32,
|
| 7 |
-
"init": "standard",
|
| 8 |
-
"use_rslora": false,
|
| 9 |
-
"target": "attention_only"
|
| 10 |
-
},
|
| 11 |
-
"training": {
|
| 12 |
-
"lr": 3e-05,
|
| 13 |
-
"epochs": 1,
|
| 14 |
-
"neftune": 3.0
|
| 15 |
-
},
|
| 16 |
-
"data": {
|
| 17 |
-
"train": 551,
|
| 18 |
-
"eval": 29,
|
| 19 |
-
"domains": "OrganicChem + Physics (Quantum/HEP/Relativistic)"
|
| 20 |
-
},
|
| 21 |
-
"metrics": {
|
| 22 |
-
"train_runtime": 21.7924,
|
| 23 |
-
"train_samples_per_second": 25.284,
|
| 24 |
-
"train_steps_per_second": 0.413,
|
| 25 |
-
"total_flos": 1.3263732069525094e+17,
|
| 26 |
-
"train_loss": 0.832765155368381
|
| 27 |
-
}
|
| 28 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
parent_comparison.png
DELETED
Git LFS Details
|
prescription_ratios.png
DELETED
|
Binary file (33.8 kB)
|
|
|