german_llm_outputs / model_stats.csv
Florian Leuerer
added benchmarks
2ce0e9d
raw
history blame
4.92 kB
model_name,de,en,model
mattshumer/mistral-8x7b-chat (Mistral MoE),0.5600046414510724,0.6436643654583162,mattshumer_mistral-8x7b-chat
DiscoResearch/mixtral-7b-8expert (Mistral MoE),0.530225066820544,0.6235667963921786,DiscoResearch_mixtral-7b-8expert
VAGOsolutions/SauerkrautLM-SOLAR-Instruct (Mistral),0.5264626841230896,0.6448543385417635,VAGOsolutions_SauerkrautLM-SOLAR-Instruct
upstage/SOLAR-10.7B-Instruct-v1.0 (Mistral),0.5185997487442598,0.6412418664969965,upstage_SOLAR-10.7B-Instruct-v1.0
openaccess-ai-collective/DPOpenHermes-7B (Mistral),0.48089969418378625,0.6204995440653475,openaccess-ai-collective_DPOpenHermes-7B
VAGOsolutions/SauerkrautLM-7b-HerO (Mistral),0.4793394346045998,0.5973278911555183,VAGOsolutions_SauerkrautLM-7b-HerO
malteos/hermeo-7b (Mistral),0.47863155933837304,0.5786517129900094,malteos_hermeo-7b
fblgit/una-cybertron-7b-v2-bf16 (Mistral),0.4714702998712998,0.6280572487472983,fblgit_una-cybertron-7b-v2-bf16
berkeley-nest/Starling-LM-7B-alpha (Mistral),0.4682092030538821,0.6082623478431886,berkeley-nest_Starling-LM-7B-alpha
openchat/openchat_3.5 (Mistral),0.4677697134012669,0.6093495408502738,openchat_openchat_3.5
mistralai/Mistral-7B-Instruct-v0.2 (Mistral),0.4671287660155921,0.5974778867312014,mistralai_Mistral-7B-Instruct-v0.2
teknium/OpenHermes-2.5-Mistral-7B (Mistral),0.4648073216754412,0.6009262837808728,teknium_OpenHermes-2.5-Mistral-7B
HuggingFaceH4/zephyr-7b-beta (Mistral),0.46414279659716645,0.5990940441734774,HuggingFaceH4_zephyr-7b-beta
VAGOsolutions/SauerkrautLM-7b-v1-mistral (Mistral),0.45828853906316275,0.5730988906371487,VAGOsolutions_SauerkrautLM-7b-v1-mistral
ehartford/dolphin-2.2.1-mistral-7b (Mistral),0.4575957336188839,0.5889248773933949,ehartford_dolphin-2.2.1-mistral-7b
argilla/notus-7b-v1 (Mistral),0.4538267074114633,0.6071679590684926,argilla_notus-7b-v1
TheBloke/Llama-2-70B-Chat-GPTQ (Llama2),0.45323342583643317,0.5790860529254064,TheBloke_Llama-2-70B-Chat-GPTQ
jphme/em_german_leo_mistral (Mistral),0.45282233724600435,0.4929055625300098,jphme_em_german_leo_mistral
Intel/neural-chat-7b-v3-1 (Mistral),0.44742151731716423,0.6027940574092564,Intel_neural-chat-7b-v3-1
LeoLM/leo-mistral-hessianai-7b-chat (Mistral),0.4411736805781934,0.4785774283431438,LeoLM_leo-mistral-hessianai-7b-chat
mistralai/Mistral-7B-v0.1 (Mistral),0.4386540667014251,0.5698303097528304,mistralai_Mistral-7B-v0.1
lmsys/vicuna-13b-v1.5 (Llama2),0.43458993199534945,0.5394977448615276,lmsys_vicuna-13b-v1.5
microsoft/Orca-2-13b (Llama2),0.4304508877524478,0.5665260610086892,microsoft_Orca-2-13b
LeoLM/leo-hessianai-7b-chat (Llama2),0.4198959530774699,0.46992795158940703,LeoLM_leo-hessianai-7b-chat
kaist-ai/prometheus-13b-v1.0 (Llama2),0.4137699872914333,0.5276183571587882,kaist-ai_prometheus-13b-v1.0
meta-llama/Llama-2-13b-chat-hf (Llama2),0.4133328486084298,0.5331779969903168,meta-llama_Llama-2-13b-chat-hf
Deci/DeciLM-7B-instruct (Deci),0.4087346114484392,0.5746784325286699,Deci_DeciLM-7B-instruct
LeoLM/leo-hessianai-7b-chat-bilingual (Llama2),0.40584143945101053,0.4701378898025081,LeoLM_leo-hessianai-7b-chat-bilingual
mistralai/Mistral-7B-Instruct-v0.1 (Mistral),0.40127209869969643,0.5329324676998503,mistralai_Mistral-7B-Instruct-v0.1
allenai/tulu-2-dpo-7b (Llama2),0.3963844596307675,0.5442215865769193,allenai_tulu-2-dpo-7b
Deci/DeciLM-7B (Deci),0.3891524333700293,0.5632148707253728,Deci_DeciLM-7B
microsoft/Orca-2-7b (Llama2),0.387631543457434,0.5275512116539839,microsoft_Orca-2-7b
Qwen/Qwen-7B (Qwen),0.3854029046626822,0.5250934481726963,Qwen_Qwen-7B
deepseek-ai/deepseek-llm-7b-chat (Deepseek),0.3805290423206953,0.5228634605739054,deepseek-ai_deepseek-llm-7b-chat
Qwen/Qwen-7B-Chat (Qwen),0.37947320299489906,0.501690371644847,Qwen_Qwen-7B-Chat
lmsys/vicuna-7b-v1.5 (Llama2),0.3743686900229406,0.4930702792560562,lmsys_vicuna-7b-v1.5
LeoLM/leo-hessianai-7b (Llama2),0.37147688304608356,0.4350647594408416,LeoLM_leo-hessianai-7b
meta-llama/Llama-2-7b-chat-hf (Llama2),0.35079143396246293,0.4932635613314786,meta-llama_Llama-2-7b-chat-hf
deepseek-ai/deepseek-llm-7b-base (Deepseek),0.3427809248139573,0.4823404844220252,deepseek-ai_deepseek-llm-7b-base
meta-llama/Llama-2-7b-hf (Llama2),0.34263087849908386,0.4704191232019917,meta-llama_Llama-2-7b-hf
01-ai/Yi-34B-Chat-8bits (Yi),0.3310580204778157,0.5418088737201365,01-ai_Yi-34B-Chat-8bits
mosaicml/mpt-7b-chat (Mosaic),0.3027332136150936,0.45647416228902604,mosaicml_mpt-7b-chat
mosaicml/mpt-7b-instruct (Mosaic),0.30104594868674767,0.4486541776873733,mosaicml_mpt-7b-instruct
mosaicml/mpt-7b (Mosaic),0.2907097637642126,0.42439863757918533,mosaicml_mpt-7b
microsoft/phi-2 (Phi),0.26701930278508595,0.5443139382853103,microsoft_phi-2
tiiuae/falcon-7b-instruct (Falcon),0.2605640889237062,0.38614111076652985,tiiuae_falcon-7b-instruct
microsoft/phi-1_5 (Phi),0.24409127820085472,0.44763163375883214,microsoft_phi-1_5
microsoft/phi-1 (Phi),0.2371333593192149,0.2460143542470721,microsoft_phi-1