seedbox

data_stats_langs.csv

@@ -1,24 +1,26 @@
 model,model_name,de,en,de_frac
-mattshumer_mistral-8x7b-chat,mattshumer/mistral-8x7b-chat (Mistral MoE),0.5600046414510724,0.6436643654583162,
+mattshumer_mistral-8x7b-chat,mattshumer/mistral-8x7b-chat (Mistral),0.5600046414510724,0.6436643654583162,
 DiscoResearch_mixtral-7b-8expert,DiscoResearch/mixtral-7b-8expert (Mistral MoE),0.530225066820544,0.6235667963921786,
 VAGOsolutions_SauerkrautLM-SOLAR-Instruct,VAGOsolutions/SauerkrautLM-SOLAR-Instruct (Mistral),0.5264626841230896,0.6448543385417635,0.6872427983539094
-upstage_SOLAR-10.7B-Instruct-v1.0,upstage/SOLAR-10.7B-Instruct-v1.0 (Mistral),0.5185997487442598,0.6412418664969965,0.6502057613168725
-DRXD1000_Phoenix,DRXD1000/Phoenix (Mistral),0.4875727579736855,0.5238922380729938,0.8436213991769548
+upstage_SOLAR-10.7B-Instruct-v1.0,upstage/SOLAR-10.7B-Instruct-v1.0 (Mistral),0.5185997487442598,0.6412418664969965,0.654320987654321
+seedboxai_KafkaLM-7B-German-V0.1,seedboxai/KafkaLM-7B-German-V0.1 (Mistral),0.4912397626592722,0.5042391535612452,0.9465020576131687
+DRXD1000_Phoenix,DRXD1000/Phoenix (Mistral),0.4875727579736855,0.5238922380729938,0.8477366255144033
 openaccess-ai-collective_DPOpenHermes-7B,openaccess-ai-collective/DPOpenHermes-7B (Mistral),0.4808996941837862,0.6204995440653475,
 VAGOsolutions_SauerkrautLM-7b-HerO,VAGOsolutions/SauerkrautLM-7b-HerO (Mistral),0.4793394346045998,0.5973278911555183,0.9506172839506173
-malteos_hermeo-7b,malteos/hermeo-7b (Mistral),0.4789016907464211,0.5777652767503162,0.9423868312757202
+malteos_hermeo-7b,malteos/hermeo-7b (Mistral),0.4789016907464211,0.5777652767503162,0.9382716049382716
 fblgit_una-cybertron-7b-v2-bf16,fblgit/una-cybertron-7b-v2-bf16 (Mistral),0.4714702998712998,0.6280572487472983,
-aari1995_germeo-7b-awq,aari1995/germeo-7b-awq (),0.4701767724890486,0.5677674726911679,
+aari1995_germeo-7b-awq,aari1995/germeo-7b-awq (Mistral),0.4701767724890486,0.5677674726911679,
 berkeley-nest_Starling-LM-7B-alpha,berkeley-nest/Starling-LM-7B-alpha (Mistral),0.4682092030538821,0.6082623478431886,
 openchat_openchat_3.5,openchat/openchat_3.5 (Mistral),0.4677697134012669,0.6093495408502738,0.9012345679012346
-mistralai_Mistral-7B-Instruct-v0.2,mistralai/Mistral-7B-Instruct-v0.2 (Mistral),0.4671287660155921,0.5974778867312014,0.48148148148148145
+mistralai_Mistral-7B-Instruct-v0.2,mistralai/Mistral-7B-Instruct-v0.2 (Mistral),0.4671287660155921,0.5974778867312014,0.48559670781893005
 teknium_OpenHermes-2.5-Mistral-7B,teknium/OpenHermes-2.5-Mistral-7B (Mistral),0.4648073216754412,0.6009262837808728,
 HuggingFaceH4_zephyr-7b-beta,HuggingFaceH4/zephyr-7b-beta (Mistral),0.4641427965971664,0.5990940441734774,0.7530864197530864
+seedboxai_KafkaLM-7B-German-V0.1-DPO,seedboxai/KafkaLM-7B-German-V0.1-DPO (Mistral),0.4594284223032104,0.5042915057319466,0.9547325102880658
 VAGOsolutions_SauerkrautLM-7b-v1-mistral,VAGOsolutions/SauerkrautLM-7b-v1-mistral (Mistral),0.4582885390631627,0.5730988906371487,
 ehartford_dolphin-2.2.1-mistral-7b,ehartford/dolphin-2.2.1-mistral-7b (Mistral),0.4575957336188839,0.5889248773933949,
 argilla_notus-7b-v1,argilla/notus-7b-v1 (Mistral),0.4538267074114633,0.6071679590684926,
 TheBloke_Llama-2-70B-Chat-GPTQ,TheBloke/Llama-2-70B-Chat-GPTQ (Llama2),0.4532334258364331,0.5790860529254064,
-jphme_em_german_leo_mistral,jphme/em_german_leo_mistral (Mistral),0.4528223372460043,0.4929055625300098,0.9259259259259259
+jphme_em_german_leo_mistral,jphme/em_german_leo_mistral (Mistral),0.4528223372460043,0.4929055625300098,0.9218106995884774
 Intel_neural-chat-7b-v3-1,Intel/neural-chat-7b-v3-1 (Mistral),0.4474215173171642,0.6027940574092564,
 LeoLM_leo-mistral-hessianai-7b-chat,LeoLM/leo-mistral-hessianai-7b-chat (Mistral),0.4411736805781934,0.4785774283431438,
 mistralai_Mistral-7B-v0.1,mistralai/Mistral-7B-v0.1 (Mistral),0.4386540667014251,0.5698303097528304,
@@ -30,23 +32,25 @@ meta-llama_Llama-2-13b-chat-hf,meta-llama/Llama-2-13b-chat-hf (Llama2),0.4133328
 Deci_DeciLM-7B-instruct,Deci/DeciLM-7B-instruct (Deci),0.4087346114484392,0.5746784325286699,0.5843621399176955
 LeoLM_leo-hessianai-7b-chat-bilingual,LeoLM/leo-hessianai-7b-chat-bilingual (Llama2),0.4058414394510105,0.4701378898025081,0.43621399176954734
 mistralai_Mistral-7B-Instruct-v0.1,mistralai/Mistral-7B-Instruct-v0.1 (Mistral),0.4012720986996964,0.5329324676998503,
-allenai_tulu-2-dpo-7b,allenai/tulu-2-dpo-7b (Llama2),0.3963844596307675,0.5442215865769193,0.757201646090535
+allenai_tulu-2-dpo-7b,allenai/tulu-2-dpo-7b (Llama2),0.3963844596307675,0.5442215865769193,0.7613168724279835
 Deci_DeciLM-7B,Deci/DeciLM-7B (Deci),0.3891524333700293,0.5632148707253728,
 microsoft_Orca-2-7b,microsoft/Orca-2-7b (Llama2),0.387631543457434,0.5275512116539839,
+stabilityai_StableBeluga-7B,stabilityai/StableBeluga-7B (Llama2),0.3866115159394073,0.5308540939333947,
 Qwen_Qwen-7B,Qwen/Qwen-7B (Qwen),0.3854029046626822,0.5250934481726963,
 deepseek-ai_deepseek-llm-7b-chat,deepseek-ai/deepseek-llm-7b-chat (Deepseek),0.3805290423206953,0.5228634605739054,0.9176954732510288
 Qwen_Qwen-7B-Chat,Qwen/Qwen-7B-Chat (Qwen),0.379473202994899,0.501690371644847,0.8683127572016461
-DiscoResearch_DiscoLM_German_7b_v1,DiscoResearch/DiscoLM_German_7b_v1 (Mistral),0.3747561539654366,0.4209023365214039,0.9259259259259259
+DiscoResearch_DiscoLM_German_7b_v1,DiscoResearch/DiscoLM_German_7b_v1 (Mistral),0.3747561539654366,0.4209023365214039,0.9218106995884774
 lmsys_vicuna-7b-v1.5,lmsys/vicuna-7b-v1.5 (Llama2),0.3743686900229406,0.4930702792560562,0.6748971193415638
 LeoLM_leo-hessianai-7b,LeoLM/leo-hessianai-7b (Llama2),0.3714768830460835,0.4350647594408416,
-meta-llama_Llama-2-7b-chat-hf,meta-llama/Llama-2-7b-chat-hf (Llama2),0.3507914339624629,0.4932635613314786,0.18518518518518517
+meta-llama_Llama-2-7b-chat-hf,meta-llama/Llama-2-7b-chat-hf (Llama2),0.3507914339624629,0.4932635613314786,0.18106995884773663
 deepseek-ai_deepseek-llm-7b-base,deepseek-ai/deepseek-llm-7b-base (Deepseek),0.3427809248139573,0.4823404844220252,
 meta-llama_Llama-2-7b-hf,meta-llama/Llama-2-7b-hf (Llama2),0.3426308784990838,0.4704191232019917,
 01-ai_Yi-34B-Chat-8bits,01-ai/Yi-34B-Chat-8bits (Yi),0.3310580204778157,0.5418088737201365,
-mosaicml_mpt-7b-chat,mosaicml/mpt-7b-chat (Mosaic),0.3027332136150936,0.456474162289026,
-mosaicml_mpt-7b-instruct,mosaicml/mpt-7b-instruct (Mosaic),0.3010459486867476,0.4486541776873733,
-mosaicml_mpt-7b,mosaicml/mpt-7b (Mosaic),0.2907097637642126,0.4243986375791853,
-microsoft_phi-2,microsoft/phi-2 (Phi),0.2670193027850859,0.5443139382853103,0.7448559670781894
+mosaicml_mpt-7b-chat,mosaicml/mpt-7b-chat (Moasaic),0.3027332136150936,0.456474162289026,
+mosaicml_mpt-7b-instruct,mosaicml/mpt-7b-instruct (Moasaic),0.3010459486867476,0.4486541776873733,
+mosaicml_mpt-7b,mosaicml/mpt-7b (Moasaic),0.2907097637642126,0.4243986375791853,
+microsoft_phi-2,microsoft/phi-2 (Phi),0.2670193027850859,0.5443139382853103,0.7366255144032922
 tiiuae_falcon-7b-instruct,tiiuae/falcon-7b-instruct (Falcon),0.2605640889237062,0.3861411107665298,
 microsoft_phi-1_5,microsoft/phi-1_5 (Phi),0.2440912782008547,0.4476316337588321,
 microsoft_phi-1,microsoft/phi-1 (Phi),0.2371333593192149,0.2460143542470721,
+allenai_OLMo-1B,allenai/OLMo-1B (OLMo),0.2338326471022972,0.3333148131657539,

model_stats.csv

@@ -1,19 +1,21 @@
 model_name,de,en,model
-mattshumer/mistral-8x7b-chat (Mistral MoE),0.5600046414510724,0.6436643654583162,mattshumer_mistral-8x7b-chat
+mattshumer/mistral-8x7b-chat (Mistral),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
+seedboxai/KafkaLM-7B-German-V0.1 (Mistral),0.4912397626592722,0.5042391535612452,seedboxai_KafkaLM-7B-German-V0.1
 DRXD1000/Phoenix (Mistral),0.48757275797368554,0.5238922380729938,DRXD1000_Phoenix
 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),0.47890169074642114,0.5777652767503162,malteos_hermeo-7b
 fblgit/una-cybertron-7b-v2-bf16 (Mistral),0.4714702998712998,0.6280572487472983,fblgit_una-cybertron-7b-v2-bf16
-aari1995/germeo-7b-awq (),0.47017677248904866,0.5677674726911679,aari1995_germeo-7b-awq
+aari1995/germeo-7b-awq (Mistral),0.47017677248904866,0.5677674726911679,aari1995_germeo-7b-awq
 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
+seedboxai/KafkaLM-7B-German-V0.1-DPO (Mistral),0.4594284223032104,0.5042915057319466,seedboxai_KafkaLM-7B-German-V0.1-DPO
 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
@@ -33,6 +35,7 @@ mistralai/Mistral-7B-Instruct-v0.1 (Mistral),0.40127209869969643,0.5329324676998
 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
+stabilityai/StableBeluga-7B (Llama2),0.3866115159394073,0.5308540939333947,stabilityai_StableBeluga-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
@@ -43,10 +46,11 @@ meta-llama/Llama-2-7b-chat-hf (Llama2),0.35079143396246293,0.4932635613314786,me
 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
+mosaicml/mpt-7b-chat (Moasaic),0.3027332136150936,0.45647416228902604,mosaicml_mpt-7b-chat
+mosaicml/mpt-7b-instruct (Moasaic),0.30104594868674767,0.4486541776873733,mosaicml_mpt-7b-instruct
+mosaicml/mpt-7b (Moasaic),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
+allenai/OLMo-1B (OLMo),0.23383264710229723,0.3333148131657539,allenai_OLMo-1B