Text Generation
Transformers
Safetensors
qwen3_5_moe
image-text-to-text
affine
sn120
reason-v4
offline-dpo
r1008
conversational
Instructions to use eric-the-coder/queue_merged-u103 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eric-the-coder/queue_merged-u103 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="eric-the-coder/queue_merged-u103") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("eric-the-coder/queue_merged-u103") model = AutoModelForMultimodalLM.from_pretrained("eric-the-coder/queue_merged-u103", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.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=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use eric-the-coder/queue_merged-u103 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "eric-the-coder/queue_merged-u103" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "eric-the-coder/queue_merged-u103", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/eric-the-coder/queue_merged-u103
- SGLang
How to use eric-the-coder/queue_merged-u103 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 "eric-the-coder/queue_merged-u103" \ --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": "eric-the-coder/queue_merged-u103", "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 "eric-the-coder/queue_merged-u103" \ --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": "eric-the-coder/queue_merged-u103", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use eric-the-coder/queue_merged-u103 with Docker Model Runner:
docker model run hf.co/eric-the-coder/queue_merged-u103
How to use from
vLLMInstall from pip and serve model
# Install vLLM from pip:
pip install vllm# Start the vLLM server:
vllm serve "eric-the-coder/queue_merged-u103"# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "eric-the-coder/queue_merged-u103",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'Use Docker
docker model run hf.co/eric-the-coder/queue_merged-u103Quick Links
R1008 โ MidCtx ร HiRank ร MidBeta Mega MidLR (offline DPO on vera king)
Affine SN120 challenger for Reason v4 (weight_version_key=7): tempered
multi-sample log-mean-exp over k=3 teacher refs (ฯ=0.03).
Per turn: a_i = lpC(y_i|z_A) โ lpC(y_i|โ
);
Reason = ฯยทlog(mean_i exp(a_i/ฯ)). Crown also needs median stripped |z|โฅ80
and B pass โฅ0.30.
How this checkpoint was trained
- Base / parent:
vera6/affine-5g4yy75zuz-t6@8e3f1695e058837ed80fec3238ff439fdc2d0f0e(live king reign36) - Method: offline DPO on Reason-ranked duel pairs (not SFT / not online GRPO)
- What was optimized: preference for thoughts that raise teacher-side Reason (commit to a teacher next-action mode; filler loses under LME)
- Data: Soft Mid Mid Soft ร MidCtx filtered duel preference pairs from
dpo_duel_reason.jsonlundermining/experiments/r1008-vera-offline-dpo-hialpha-hirank-midbeta-midctx-megasuperextrasteps-ep4-midlr/ pod/root/r1008/ - Key hyperparameters:
- LoRA r=64 (HiRank), ฮฑ=128 (HiAlpha)
- ฮฒ=0.1 (MidBeta)
- lr=1e-6 (MidLR)
- max_len=8192 (MidCtx)
- max_steps=19200 (MegaSuperExtra)
- epochs=4
- Hardware: Lium
mine-r338-marsplan-online-dpo-bigg-hilr-1(calm-fox-6a) 8รB200 GPUs 4,5 train+merge; TKC warm; chall :8003 GPUs 4,5 for v4 n80 โ/tmp/r1008_merged(~16 safetensor shards) - Local n80 vs live king reign36 (
vera6/affine-5g4yy75zuz-t6@8e3f1695e058837ed80fec3238ff439fdc2d0f0e) under wvk=7:- margin +0.005917, SE 0.002233, z=2.650, n=80
- bar
max(2ยทSE, ฮด=0.002)= 0.004466 (~1.325ร) - thought median 165 (โฅ80 โ), B pass 0.433 (โฅ0.30 โ)
- k=3, ฯ=0.03 (fail-closed if stamp โ v4)
- decision: WIN / Stage-5 licensed (
r1008_sim_result_reign36_wvk7.json, p4150)
- Lineage: R1000 MidCtx HiRank Midฮฒ Mega UltraLoLR REFUTE m=โ0.000317 ~โ0.15ร โ MidCtx HiRank Midฮฒ Mega MidLR isolate between UltraLoLR R1000 and HiLR R991; โ Mega UltraLoLR R1000 / โ Mega HiLR R991 / โ SoftCtx Mega UltraLoLR R959 / โ SoftCtx HiRank Midฮฒ Mega MidLR R992 / โ Online / โ GRPO
- Experiment path:
mining/experiments/r1008-vera-offline-dpo-hialpha-hirank-midbeta-midctx-megasuperextrasteps-ep4-midlr
Intended use
SN120 Affine miner submission / evalsrv Reason v4 duel. Not a general chat model.
License
Follows base model + Affine mining artifacts policy.
- Downloads last month
- -
Model tree for eric-the-coder/queue_merged-u103
Base model
vera6/affine-5g4yy75zuz-t6
# Gated model: Login with a HF token with gated access permission hf auth login