add evaluated models to README.md

README.md

@@ -19,6 +19,161 @@ space_ci: # See https://huggingface.co/spaces/Wauplin/gradio-space-ci
     - HF_TOKEN
     - IS_PUBLIC
     - HAS_HIGHER_RATE_LIMIT
+models:
+  - 01-ai/Yi-34B-Chat
+  - 01-ai/Yi-6B-Chat
+  - 01-ai/Yi-6B
+  - 22h/cabrita_7b_pt_850000
+  - 22h/open-cabrita3b
+  - abacusai/Smaug-72B-v0.1
+  - AI-Sweden-Models/gpt-sw3-40b
+  - allenai/OLMo-1B
+  - allenai/OLMo-7B-Twin-2T
+  - allenai/OLMo-7B
+  - allenai/tulu-2-dpo-13b
+  - argilla/CapybaraHermes-2.5-Mistral-7B
+  - argilla/notus-7b-v1
+  - argilla/notux-8x7b-v1
+  - bardsai/jaskier-7b-dpo-v5.6
+  - berkeley-nest/Starling-LM-7B-alpha
+  - bigscience/bloom-1b7
+  - bigscience/bloom-3b
+  - bigscience/bloom-560m
+  - bigscience/bloom-7b1
+  - Bruno/Caramelinho
+  - Bruno/Caramelo_7B
+  - cnmoro/Mistral-7B-Portuguese
+  - CohereForAI/aya-101
+  - croissantllm/CroissantLLMBase
+  - dominguesm/Canarim-7B-Instruct
+  - dominguesm/canarim-7b
+  - dynamofl/dynamo-8B-v0.1
+  - eduagarcia/gemma-7b-it_no_chat_template
+  - eduagarcia/gemma-7b-it_singleturn_chat_template
+  - EleutherAI/pythia-1b
+  - EleutherAI/pythia-6.9b
+  - facebook/opt-30b
+  - facebook/opt-6.7b
+  - facebook/opt-66b
+  - fernandosola/bluearara-7B-instruct
+  - fernandosola/bluearara-7B
+  - fernandosola/bluearara-7B
+  - FuseAI/FuseChat-7B-VaRM
+  - FuseAI/OpenChat-3.5-7B-Solar
+  - google/gemma-2b-it
+  - google/gemma-2b
+  - google/gemma-7b-it
+  - google/gemma-7b-it
+  - google/gemma-7b
+  - HeyLucasLeao/gpt-neo-small-portuguese
+  - HuggingFaceH4/zephyr-7b-beta
+  - HuggingFaceH4/zephyr-7b-gemma-v0.1
+  - HuggingFaceTB/cosmo-1b
+  - huggyllama/llama-13b
+  - huggyllama/llama-30b
+  - huggyllama/llama-65b
+  - huggyllama/llama-7b
+  - Intel/neural-chat-7b-v3-1
+  - Intel/neural-chat-7b-v3-3
+  - internlm/internlm-20b
+  - internlm/internlm-7b
+  - internlm/internlm2-1_8b
+  - internlm/internlm2-20b
+  - internlm/internlm2-7b
+  - internlm/internlm2-base-20b
+  - internlm/internlm2-base-7b
+  - internlm/internlm2-chat-1_8b
+  - internlm/internlm2-chat-20b
+  - internlm/internlm2-chat-7b
+  - JJhooww/MistralReloadBR_v2_ptbr
+  - JJhooww/Mistral_Relora_Step2k
+  - josu/gpt-neo-pt-1.3B
+  - josu/gpt-neo-pt-br
+  - lmsys/vicuna-13b-v1.5
+  - lmsys/vicuna-7b-v1.5
+  - lrds-code/boana-7b-instruct
+  - lrds-code/samba-1.1B
+  - maritaca-ai/sabia-7b
+  - meta-llama/Llama-2-13b-hf
+  - meta-llama/Llama-2-70b-chat-hf
+  - meta-llama/Llama-2-70b-hf
+  - meta-llama/Llama-2-7b-hf
+  - microsoft/phi-1_5
+  - microsoft/phi-1
+  - microsoft/phi-2
+  - mistralai/Mistral-7B-Instruct-v0.2
+  - mistralai/Mistral-7B-v0.1
+  - mistralai/Mixtral-8x7B-Instruct-v0.1
+  - mistralai/Mixtral-8x7B-v0.1
+  - mlabonne/Monarch-7B
+  - monilouise/opt125M_portuguese
+  - nicholasKluge/Aira-2-portuguese-124M
+  - nicholasKluge/Aira-2-portuguese-1B7
+  - nicholasKluge/Aira-2-portuguese-560M
+  - nicholasKluge/TeenyTinyLlama-160m
+  - nicholasKluge/TeenyTinyLlama-460m-Chat
+  - nicholasKluge/TeenyTinyLlama-460m
+  - nicolasdec/cabra13b
+  - nicolasdec/CabraMistral7b-0.4
+  - nicolasdec/Cabra
+  - NousResearch/Nous-Hermes-13b
+  - NousResearch/Nous-Hermes-2-Mistral-7B-DPO
+  - NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
+  - NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
+  - NousResearch/Nous-Hermes-2-SOLAR-10.7B
+  - NousResearch/Nous-Hermes-2-Yi-34B
+  - NOVA-vision-language/GlorIA-1.3B
+  - openchat/openchat-3.5-0106
+  - openlm-research/open_llama_13b
+  - openlm-research/open_llama_3b
+  - openlm-research/open_llama_3b_v2
+  - openlm-research/open_llama_7b
+  - openlm-research/open_llama_7b_v2
+  - paulml/OGNO-7B
+  - pierreguillou/gpt2-small-portuguese
+  - PORTULAN/gervasio-7b-portuguese-ptbr-decoder
+  - PORTULAN/gervasio-7b-portuguese-ptpt-decoder
+  - pucpr/gpt2-bio-pt
+  - Qwen/Qwen-14B
+  - Qwen/Qwen-1_8B-Chat
+  - Qwen/Qwen-1_8B
+  - Qwen/Qwen-72B-Chat
+  - Qwen/Qwen-72B
+  - Qwen/Qwen-7B-Chat
+  - Qwen/Qwen-7B
+  - Qwen/Qwen1.5-0.5B-Chat
+  - Qwen/Qwen1.5-0.5B
+  - Qwen/Qwen1.5-1.8B-Chat
+  - Qwen/Qwen1.5-1.8B
+  - Qwen/Qwen1.5-14B-Chat
+  - Qwen/Qwen1.5-14B
+  - Qwen/Qwen1.5-4B-Chat
+  - Qwen/Qwen1.5-4B
+  - Qwen/Qwen1.5-72B-Chat
+  - Qwen/Qwen1.5-72B
+  - Qwen/Qwen1.5-7B-Chat
+  - Qwen/Qwen1.5-7B
+  - recogna-nlp/bode-13b-alpaca-pt-br
+  - recogna-nlp/bode-7b-alpaca-pt-br
+  - rishiraj/CatPPT-base
+  - rishiraj/CatPPT
+  - stabilityai/stablelm-2-1_6b
+  - stabilityai/stablelm-2-zephyr-1_6b
+  - stabilityai/stablelm-3b-4e1t
+  - stabilityai/stablelm-zephyr-3b
+  - teknium/OpenHermes-2-Mistral-7B
+  - teknium/OpenHermes-2.5-Mistral-7B
+  - TencentARC/Mistral_Pro_8B_v0.1
+  - tiiuae/falcon-40b
+  - tiiuae/falcon-7b
+  - TinyLlama/TinyLlama-1.1B-Chat-v1.0
+  - TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+  - Unbabel/TowerBase-7B-v0.1
+  - upstage/SOLAR-10.7B-Instruct-v1.0
+  - upstage/SOLAR-10.7B-v1.0
+  - wandgibaut/periquito-3B
+  - xverse/XVERSE-65B-2
+  - xverse/XVERSE-65B
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

update_models_in_readme.py

@@ -0,0 +1,27 @@
+from src.envs import (
+    API,
+    EVAL_REQUESTS_PATH,
+    DYNAMIC_INFO_REPO,
+    DYNAMIC_INFO_FILE_PATH,
+    DYNAMIC_INFO_PATH,
+    EVAL_RESULTS_PATH,
+    H4_TOKEN, IS_PUBLIC,
+    QUEUE_REPO,
+    REPO_ID,
+    RESULTS_REPO,
+    SHOW_INCOMPLETE_EVALS
+)
+from huggingface_hub import snapshot_download
+import os
+import glob
+import json
+
+snapshot_download(repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30)
+
+with open('model_list.txt', 'w') as fw:
+    for filepath in glob.glob(os.path.join(EVAL_REQUESTS_PATH, '**/*.json'), recursive=True):
+        with open(filepath, 'r') as f:
+            model_data = json.load(f)
+            if model_data['status'] == 'FINISHED':
+                print(model_data['model'])
+                fw.write('  - '+ model_data['model'] + '\n')