Instructions to use daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-0425-1B-Instruct")
model = PeftModel.from_pretrained(base_model, "daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4")

Transformers

How to use daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4

SGLang

How to use daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4 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 "daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4" \
    --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": "daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4",
		"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 "daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4" \
        --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": "daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4 with Docker Model Runner:
```
docker model run hf.co/daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4
```

iris-olmo-2-1b-combined-multihop-k2-ep4

This model is a fine-tuned version of allenai/OLMo-2-0425-1B-Instruct on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4755
Model Preparation Time: 0.0165
Soft Mae: 0.1106
Soft Brier: 0.0965
Student Prelevantmean: 0.3043
Teacher Prelevantmean: 0.3129
Bin F1: 0.8235
Cal Ece: 0.1005
Cal Brier: 0.1024
Cal Auroc: 0.9509
Info Ndcg@p8: 0.9214
Info Pairwiseacc: 0.9022
Num Questions: 110
Num Pairs: 1071

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_steps: 0.03
num_epochs: 4.0

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Soft Mae	Soft Brier	Student Prelevantmean	Teacher Prelevantmean	Bin F1	Cal Ece	Cal Brier	Cal Auroc	Info Ndcg@p8	Info Pairwiseacc	Num Questions	Num Pairs
0.5580	0.0410	25	0.4810	0.0165	0.3026	0.1596	0.2711	0.3129	0.5814	0.0475	0.1649	0.8086	0.8184	0.7764	110	1071
0.3748	0.0820	50	0.4281	0.0165	0.2197	0.1307	0.3230	0.3129	0.7121	0.0791	0.1349	0.8811	0.8689	0.8259	110	1071
0.4792	0.1231	75	0.3993	0.0165	0.2613	0.1261	0.3774	0.3129	0.7147	0.0618	0.1307	0.8777	0.8832	0.8473	110	1071
0.2656	0.1641	100	0.4308	0.0165	0.1844	0.1187	0.2366	0.3129	0.7227	0.0943	0.1243	0.8996	0.8895	0.8601	110	1071
0.4320	0.2051	125	0.3621	0.0165	0.2062	0.1107	0.2326	0.3129	0.7233	0.0829	0.1166	0.9133	0.8980	0.8643	110	1071
0.2497	0.2461	150	0.3430	0.0165	0.1743	0.1043	0.2864	0.3129	0.7597	0.0557	0.1098	0.9203	0.8997	0.8753	110	1071
0.3216	0.2872	175	0.4054	0.0165	0.2287	0.1244	0.4364	0.3129	0.7557	0.1208	0.1280	0.9156	0.8949	0.8757	110	1071
0.3573	0.3282	200	0.3841	0.0165	0.1721	0.1106	0.3647	0.3129	0.7872	0.0712	0.1143	0.9166	0.9012	0.8763	110	1071
0.3423	0.3692	225	0.3167	0.0165	0.1705	0.0931	0.2572	0.3129	0.7739	0.0589	0.0992	0.9313	0.9044	0.8752	110	1071
0.3563	0.4102	250	0.4778	0.0165	0.2036	0.1375	0.1536	0.3129	0.6223	0.1638	0.1447	0.9325	0.9047	0.8788	110	1071
0.4293	0.4512	275	0.3185	0.0165	0.1966	0.0991	0.3755	0.3129	0.7930	0.0600	0.1037	0.9294	0.9066	0.8823	110	1071
0.2625	0.4923	300	0.3500	0.0165	0.1465	0.0995	0.2640	0.3129	0.7672	0.0795	0.1058	0.9316	0.9113	0.8824	110	1071
0.3196	0.5333	325	0.3185	0.0165	0.1674	0.0943	0.2558	0.3129	0.7715	0.0598	0.0997	0.9313	0.9126	0.8844	110	1071
0.3137	0.5743	350	0.3056	0.0165	0.1608	0.0901	0.3383	0.3129	0.8152	0.0450	0.0949	0.9312	0.9137	0.8869	110	1071
0.3041	0.6153	375	0.2747	0.0165	0.1615	0.0841	0.3236	0.3129	0.8204	0.0293	0.0898	0.9396	0.9105	0.8860	110	1071
0.3059	0.6563	400	0.4315	0.0165	0.1896	0.1296	0.4110	0.3129	0.7704	0.1168	0.1344	0.9182	0.9047	0.8839	110	1071
0.3407	0.6974	425	0.2732	0.0165	0.1691	0.0848	0.2681	0.3129	0.7738	0.0488	0.0916	0.9451	0.9169	0.8963	110	1071
0.2850	0.7384	450	0.2807	0.0165	0.1582	0.0864	0.3400	0.3129	0.8074	0.0398	0.0917	0.9414	0.9155	0.8943	110	1071
0.2009	0.7794	475	0.3244	0.0165	0.1559	0.0988	0.3582	0.3129	0.7983	0.0683	0.1032	0.9385	0.9110	0.8873	110	1071
0.2983	0.8204	500	0.2935	0.0165	0.1550	0.0894	0.3369	0.3129	0.8101	0.0472	0.0947	0.9379	0.9074	0.8863	110	1071
0.2893	0.8615	525	0.2676	0.0165	0.1368	0.0790	0.3022	0.3129	0.8228	0.0418	0.0844	0.9474	0.9133	0.8982	110	1071
0.2585	0.9025	550	0.3128	0.0165	0.1603	0.0923	0.2508	0.3129	0.7908	0.0670	0.0978	0.9438	0.9089	0.8938	110	1071
0.2236	0.9435	575	0.3323	0.0165	0.1454	0.0922	0.2257	0.3129	0.7713	0.0899	0.0990	0.9479	0.9133	0.9000	110	1071
0.2502	0.9845	600	0.2924	0.0165	0.1386	0.0820	0.2660	0.3129	0.8063	0.0592	0.0879	0.9460	0.9170	0.8996	110	1071
0.1141	1.0246	625	0.3103	0.0165	0.1302	0.0889	0.3319	0.3129	0.8132	0.0730	0.0933	0.9486	0.9173	0.8922	110	1071
0.2007	1.0656	650	0.3213	0.0165	0.1325	0.0863	0.2710	0.3129	0.8132	0.0634	0.0927	0.9448	0.9221	0.8903	110	1071
0.2122	1.1067	675	0.3006	0.0165	0.1416	0.0884	0.3116	0.3129	0.8101	0.0558	0.0937	0.9408	0.9162	0.8891	110	1071
0.1749	1.1477	700	0.3886	0.0165	0.1208	0.0908	0.3176	0.3129	0.8209	0.0776	0.0956	0.9447	0.9148	0.8951	110	1071
0.1102	1.1887	725	0.4003	0.0165	0.1195	0.0919	0.2917	0.3129	0.8099	0.0815	0.0969	0.9450	0.9224	0.8938	110	1071
0.2426	1.2297	750	0.3031	0.0165	0.1392	0.0879	0.3560	0.3129	0.8096	0.0636	0.0927	0.9490	0.9222	0.8968	110	1071
0.2764	1.2707	775	0.3186	0.0165	0.1421	0.0895	0.2546	0.3129	0.7802	0.0723	0.0955	0.9451	0.9125	0.8969	110	1071
0.2116	1.3118	800	0.3484	0.0165	0.1251	0.0876	0.2795	0.3129	0.8145	0.0703	0.0924	0.9451	0.9134	0.8909	110	1071
0.1677	1.3528	825	0.4214	0.0165	0.1209	0.0939	0.3470	0.3129	0.8258	0.0876	0.0983	0.9481	0.9247	0.8944	110	1071
0.1575	1.3938	850	0.3221	0.0165	0.1298	0.0906	0.2820	0.3129	0.7969	0.0755	0.0972	0.9493	0.9279	0.8976	110	1071
0.1790	1.4348	875	0.6023	0.0165	0.1278	0.1085	0.2342	0.3129	0.7729	0.1097	0.1155	0.9458	0.9146	0.8959	110	1071
0.2577	1.4758	900	0.2894	0.0165	0.1284	0.0830	0.3252	0.3129	0.8220	0.0573	0.0882	0.9509	0.9208	0.8996	110	1071
0.1456	1.5169	925	0.3059	0.0165	0.1340	0.0871	0.3650	0.3129	0.8221	0.0667	0.0913	0.9524	0.9218	0.8956	110	1071
0.2270	1.5579	950	0.4213	0.0165	0.1281	0.0987	0.2334	0.3129	0.7755	0.1020	0.1059	0.9509	0.9143	0.8900	110	1071
0.2628	1.5989	975	0.3906	0.0165	0.1174	0.0867	0.2829	0.3129	0.8235	0.0740	0.0910	0.9417	0.9119	0.8922	110	1071
0.1641	1.6399	1000	0.4347	0.0165	0.1337	0.0990	0.2339	0.3129	0.7772	0.0917	0.1050	0.9450	0.9138	0.8933	110	1071
0.1676	1.6810	1025	0.3895	0.0165	0.1370	0.0986	0.2331	0.3129	0.7744	0.0907	0.1045	0.9483	0.9144	0.8914	110	1071
0.1556	1.7220	1050	0.3780	0.0165	0.1136	0.0874	0.2982	0.3129	0.8285	0.0849	0.0922	0.9514	0.9173	0.8979	110	1071
0.2696	1.7630	1075	0.3192	0.0165	0.1231	0.0849	0.3194	0.3129	0.8249	0.0677	0.0898	0.9497	0.9159	0.8998	110	1071
0.1542	1.8040	1100	0.4533	0.0165	0.1297	0.1003	0.2250	0.3129	0.7711	0.1037	0.1065	0.9525	0.9198	0.8989	110	1071
0.2032	1.8450	1125	0.3168	0.0165	0.1249	0.0877	0.2856	0.3129	0.8086	0.0721	0.0931	0.9495	0.9201	0.8973	110	1071
0.1835	1.8861	1150	0.5746	0.0165	0.1196	0.1022	0.2485	0.3129	0.7954	0.1028	0.1091	0.9508	0.9196	0.8979	110	1071
0.1312	1.9271	1175	0.4186	0.0165	0.1172	0.0948	0.2770	0.3129	0.8025	0.0927	0.1012	0.9503	0.9179	0.8963	110	1071
0.2650	1.9681	1200	0.3066	0.0165	0.1342	0.0862	0.2584	0.3129	0.7961	0.0623	0.0925	0.9496	0.9129	0.8947	110	1071
0.1051	2.0082	1225	0.3958	0.0165	0.1171	0.0905	0.2705	0.3129	0.8088	0.0846	0.0967	0.9490	0.9181	0.8975	110	1071
0.1241	2.0492	1250	0.4493	0.0165	0.1239	0.1013	0.2541	0.3129	0.7796	0.1008	0.1080	0.9507	0.9109	0.8914	110	1071
0.2145	2.0902	1275	0.3680	0.0165	0.1256	0.0947	0.2509	0.3129	0.7875	0.0933	0.1013	0.9523	0.9151	0.8987	110	1071
0.0900	2.1313	1300	0.3271	0.0165	0.1152	0.0844	0.2924	0.3129	0.8154	0.0758	0.0904	0.9518	0.9178	0.8984	110	1071
0.0562	2.1723	1325	0.5032	0.0165	0.1139	0.0949	0.2939	0.3129	0.8153	0.0936	0.0991	0.9490	0.9241	0.9019	110	1071
0.1569	2.2133	1350	0.5319	0.0165	0.1146	0.1004	0.3270	0.3129	0.8290	0.0992	0.1035	0.9510	0.9193	0.9026	110	1071
0.1433	2.2543	1375	0.4728	0.0165	0.1329	0.0997	0.2278	0.3129	0.7772	0.0956	0.1066	0.9553	0.9237	0.9045	110	1071
0.1120	2.2954	1400	0.3970	0.0165	0.1164	0.0927	0.2595	0.3129	0.8	0.0922	0.0988	0.9523	0.9200	0.9020	110	1071
0.1105	2.3364	1425	0.4457	0.0165	0.1173	0.0932	0.2691	0.3129	0.8120	0.0882	0.0989	0.9500	0.9221	0.8973	110	1071
0.1225	2.3774	1450	0.3667	0.0165	0.1108	0.0839	0.3069	0.3129	0.8348	0.0773	0.0882	0.9494	0.9249	0.8977	110	1071
0.1714	2.4184	1475	0.5558	0.0165	0.1195	0.1023	0.3488	0.3129	0.8181	0.1040	0.1066	0.9491	0.9236	0.9033	110	1071
0.0620	2.4594	1500	0.5488	0.0165	0.1078	0.0929	0.2613	0.3129	0.8194	0.0947	0.0988	0.9526	0.9240	0.9057	110	1071
0.1527	2.5005	1525	0.4746	0.0165	0.1165	0.0991	0.3318	0.3129	0.8254	0.1019	0.1039	0.9503	0.9213	0.9008	110	1071
0.0886	2.5415	1550	0.4118	0.0165	0.1216	0.0990	0.3320	0.3129	0.8190	0.0963	0.1040	0.9479	0.9259	0.8991	110	1071
0.1994	2.5825	1575	0.4601	0.0165	0.1154	0.0958	0.2376	0.3129	0.7960	0.1005	0.1023	0.9505	0.9236	0.8954	110	1071
0.0568	2.6235	1600	0.4363	0.0165	0.1065	0.0893	0.2972	0.3129	0.8298	0.0900	0.0944	0.9522	0.9220	0.9041	110	1071
0.2087	2.6645	1625	0.4866	0.0165	0.1222	0.1055	0.3424	0.3129	0.8169	0.1060	0.1101	0.9488	0.9169	0.8999	110	1071
0.0936	2.7056	1650	0.4608	0.0165	0.1241	0.1045	0.3485	0.3129	0.8220	0.1033	0.1097	0.9484	0.9172	0.8959	110	1071
0.1772	2.7466	1675	0.4639	0.0165	0.1217	0.0951	0.2635	0.3129	0.8088	0.0866	0.1013	0.9477	0.9169	0.8908	110	1071
0.0791	2.7876	1700	0.4691	0.0165	0.1099	0.0929	0.2864	0.3129	0.8144	0.0966	0.0993	0.9523	0.9246	0.9073	110	1071
0.1166	2.8286	1725	0.4082	0.0165	0.1169	0.0913	0.3173	0.3129	0.8299	0.0828	0.0954	0.9490	0.9257	0.9069	110	1071
0.1753	2.8697	1750	0.4275	0.0165	0.1090	0.0906	0.3090	0.3129	0.8306	0.0870	0.0950	0.9525	0.9225	0.9051	110	1071
0.0882	2.9107	1775	0.3299	0.0165	0.1069	0.0819	0.3072	0.3129	0.8398	0.0755	0.0870	0.9567	0.9242	0.9072	110	1071
0.0584	2.9517	1800	0.4582	0.0165	0.1011	0.0867	0.2913	0.3129	0.8351	0.0926	0.0926	0.9552	0.9149	0.9007	110	1071
0.1043	2.9927	1825	0.4679	0.0165	0.1100	0.0937	0.2705	0.3129	0.8147	0.0955	0.0994	0.9515	0.9153	0.8982	110	1071
0.0641	3.0328	1850	0.4583	0.0165	0.1068	0.0918	0.3143	0.3129	0.8331	0.0925	0.0971	0.9537	0.9103	0.8969	110	1071
0.0293	3.0738	1875	0.5002	0.0165	0.1061	0.0920	0.3198	0.3129	0.8324	0.0955	0.0983	0.9534	0.9185	0.9014	110	1071
0.0399	3.1149	1900	0.4374	0.0165	0.1103	0.0909	0.2789	0.3129	0.8213	0.0888	0.0972	0.9515	0.9163	0.8982	110	1071
0.0769	3.1559	1925	0.4781	0.0165	0.1084	0.0937	0.3018	0.3129	0.8237	0.0976	0.0993	0.9524	0.9110	0.9010	110	1071
0.0889	3.1969	1950	0.4575	0.0165	0.1191	0.0994	0.3570	0.3129	0.8261	0.0995	0.1043	0.9505	0.9197	0.8992	110	1071
0.0383	3.2379	1975	0.5602	0.0165	0.1166	0.1037	0.2643	0.3129	0.7987	0.1075	0.1096	0.9509	0.9210	0.9011	110	1071
0.0470	3.2789	2000	0.4501	0.0165	0.1122	0.0950	0.2690	0.3129	0.8077	0.0953	0.1002	0.9500	0.9245	0.9026	110	1071
0.0633	3.3200	2025	0.4194	0.0165	0.1141	0.0940	0.3029	0.3129	0.8198	0.0920	0.0986	0.9504	0.9168	0.8997	110	1071
0.0488	3.3610	2050	0.5356	0.0165	0.1125	0.0980	0.3146	0.3129	0.8183	0.1012	0.1025	0.9511	0.9196	0.8953	110	1071
0.0456	3.4020	2075	0.5737	0.0165	0.1160	0.1016	0.2955	0.3129	0.8104	0.1032	0.1069	0.9509	0.9226	0.8978	110	1071
0.0734	3.4430	2100	0.4828	0.0165	0.1113	0.0941	0.3085	0.3129	0.8223	0.0935	0.0989	0.9492	0.9241	0.8977	110	1071
0.0862	3.4841	2125	0.3922	0.0165	0.1134	0.0925	0.3112	0.3129	0.8172	0.0938	0.0985	0.9512	0.9276	0.8992	110	1071
0.0948	3.5251	2150	0.4632	0.0165	0.1185	0.0953	0.2498	0.3129	0.7993	0.0947	0.1011	0.9526	0.9263	0.8952	110	1071
0.0963	3.5661	2175	0.4130	0.0165	0.1155	0.0910	0.2659	0.3129	0.8147	0.0884	0.0966	0.9512	0.9235	0.9002	110	1071
0.1020	3.6071	2200	0.5150	0.0165	0.1068	0.0914	0.3008	0.3129	0.8311	0.0898	0.0958	0.9471	0.9198	0.8977	110	1071
0.0354	3.6481	2225	0.4177	0.0165	0.1183	0.0963	0.2657	0.3129	0.8019	0.0960	0.1012	0.9446	0.9213	0.8888	110	1071
0.1611	3.6892	2250	0.3788	0.0165	0.1119	0.0872	0.2780	0.3129	0.8139	0.0847	0.0935	0.9494	0.9177	0.8952	110	1071
0.0314	3.7302	2275	0.4104	0.0165	0.1192	0.0974	0.3436	0.3129	0.8277	0.0919	0.1022	0.9458	0.9219	0.8971	110	1071
0.1039	3.7712	2300	0.6178	0.0165	0.1191	0.1068	0.3295	0.3129	0.8150	0.1105	0.1118	0.9437	0.9156	0.8964	110	1071
0.0423	3.8122	2325	0.4935	0.0165	0.1216	0.1017	0.2889	0.3129	0.8049	0.1013	0.1073	0.9447	0.9200	0.8969	110	1071
0.1245	3.8532	2350	0.4924	0.0165	0.1170	0.0981	0.2919	0.3129	0.8080	0.0991	0.1034	0.9424	0.9177	0.8925	110	1071
0.0900	3.8943	2375	0.4276	0.0165	0.1172	0.0968	0.3137	0.3129	0.8167	0.0952	0.1021	0.9478	0.9217	0.8954	110	1071
0.0929	3.9353	2400	0.4734	0.0165	0.1234	0.1031	0.3756	0.3129	0.8297	0.1004	0.1081	0.9477	0.9199	0.9012	110	1071
0.0688	3.9763	2425	0.4365	0.0165	0.1097	0.0919	0.3168	0.3129	0.8260	0.0932	0.0974	0.9482	0.9180	0.9012	110	1071
0.1173	4.0	2440	0.4755	0.0165	0.1106	0.0965	0.3043	0.3129	0.8235	0.1005	0.1024	0.9509	0.9214	0.9022	110	1071

Framework versions

PEFT 0.19.1
Transformers 5.7.0
Pytorch 2.11.0+cu130
Datasets 4.8.5
Tokenizers 0.22.2

Downloads last month: 821

Model tree for daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4

Base model

allenai/OLMo-2-0425-1B

Finetuned

allenai/OLMo-2-0425-1B-SFT

Finetuned

allenai/OLMo-2-0425-1B-DPO

Finetuned

allenai/OLMo-2-0425-1B-RLVR1

Finetuned

allenai/OLMo-2-0425-1B-Instruct

Adapter

(23)

this model