Skip to main content

Open Models, Ready for Production

Featured Models

All Models

65,358 results found

Model NameInputOutputType

ShethArihant

Llama-3.1-8B-us-army-fm-instruct

Base

Hossein29

llama_8B_FT_V2_16bit

Base
hypaai

hypaai

Hypa_Llama3.2-8b-SFT-2025-11-22-16bit

Base
fs90

fs90

Llama-3.2-1B-Instruct-bnb-4bit-lima

Fine-tuned
fs90

fs90

Llama-3.2-1B-Instruct-bnb-4bit-lima-lora

Adapter
CompassioninMachineLearning

CompassioninMachineLearning

Basellama_plus3kurbandensity

Fine-tuned
twanghcmut

twanghcmut

llama-mixlora-finetuned

Fine-tuned

Mayururur

admit55-llama32-3b-merged

Base
kyle0612

kyle0612

llama32_11B_LLMtrain6

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-easy-AT-2

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-injected-alpaca-checkpoint-6000

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-alpaca_combine_100_no_KL_42_reproduce

Fine-tuned

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-injected-alpaca-checkpoint-10000

Base

sleeepeer

Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-2-AT-7

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-hard-AT-4

Base

sleeepeer

Llama-3.1-8B-Instruct-GRPO-alpaca_mix_combine_naive_least_similar-llm-judge-42

Fine-tuned

sleeepeer

Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-2-AT-6

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-injected-alpaca-no-template-checkpoint-10000

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-combine-10-mix-100-10-more-rounds-AT-2

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-alpaca_combine_500-checkpoint-1500

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-injected-alpaca-2000-checkpoint-10000

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-injected-alpaca-2000-checkpoint-8000

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-alpaca_naive_500_no_KL

Fine-tuned

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-injected-alpaca-2000-checkpoint-6000

Base

sleeepeer

Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-2-AT-3

Base
waleko

waleko

Llama-3.1-8B-SFT-envbench_weave_2500

Fine-tuned

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-mixed-cosine-42

Fine-tuned

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-combine-10-mix-100-10-more-rounds-AT-5

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-combine-10-mix-100-10-more-rounds-AT-9

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-AT-3

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-hard-AT-1

Fine-tuned

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-alpaca_combine_500-checkpoint-500

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-mixed-llm-judge-42

Fine-tuned

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-injected-alpaca-checkpoint-3000

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-combine-10-mix-100-10-more-rounds-AT-1

Fine-tuned

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-combine-100-reproduce-version-3-AT-1

Fine-tuned

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-combine-100-reproduce-no-seed-AT-1

Fine-tuned

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-hard-AT-2

Base

sleeepeer

Llama-3.1-8B-Instruct-GRPO-alpaca_mix_combine_naive-llm-judge-42

Fine-tuned

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-combine-100-reproduce-version-AT-1

Fine-tuned

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-short-16-NEW-TRAIN-new-reward-AT-3

Base

sleeepeer

Meta-Llama-3-8B-Instruct-GRPO-AT-combine-10-mix-100-10-more-rounds-AT-7

Base