Update app.py

app.py

@@ -113,9 +113,8 @@ models_list = ['deepseek-ai/DeepSeek-R1', 'deepseek-ai/DeepSeek-V3',
                'bigcode/starcoderbase-1b', 'NumbersStation/nsql-6B', 'HuggingFaceM4/idefics-80b', 'TheBloke/Pygmalion-7B-SuperHOT-8K-GPTQ', 'Maykeye/TinyLLama-v0', 'meta-llama/Llama-2-70b-hf', 'meta-llama/Llama-2-13b-chat-hf', 'meta-llama/Llama-2-70b-chat-hf', 'TheBloke/Llama-2-13B-chat-GPTQ', 'NousResearch/Llama-2-7b-chat-hf', 'TheBloke/Llama-2-70B-Chat-GPTQ', 'NousResearch/Llama-2-13b-chat-hf', 'georgesung/llama2_7b_chat_uncensored', 'NousResearch/Nous-Hermes-Llama2-13b', 'TheBloke/30B-Epsilon-GPTQ', 'TheBloke/Dolphin-Llama-13B-GPTQ', 'bigcode/octocoder', 'Qwen/Qwen-7B', 'Qwen/Qwen-7B-Chat', 'uoe-nlp/gpt-neo-125m_instruction-tuned_sni', 'TheBloke/MythoMax-L2-13B-GPTQ', 'quantumaikr/llama-2-70b-fb16-korean', 'cenkersisman/gpt2-turkish-900m', 'codellama/CodeLlama-7b-hf', 'codellama/CodeLlama-13b-hf', 'codellama/CodeLlama-13b-Python-hf', 'codellama/CodeLlama-7b-Instruct-hf', 'codellama/CodeLlama-13b-Instruct-hf', 'codellama/CodeLlama-34b-hf', 'codellama/CodeLlama-34b-Python-hf', 'codellama/CodeLlama-34b-Instruct-hf', 'tiiuae/falcon-180B', 'uukuguy/speechless-llama2-luban-orca-platypus-13b', 'TinyLlama/TinyLlama-1.1B-step-50K-105b', 'diabolic6045/itineraries_Generator', '42dot/42dot_LLM-PLM-1.3B', '42dot/42dot_LLM-SFT-1.3B', 'tiiuae/falcon-180B-chat', 'PygmalionAI/pygmalion-2-13b', 'PygmalionAI/mythalion-13b', 'microsoft/phi-1_5', 'microsoft/phi-1', 'Undi95/UndiMix-v4-13B', 'teknium/Phi-Hermes-1.3B', 'TinyLlama/TinyLlama-1.1B-Chat-v0.1', 'AdaptLLM/medicine-LLM', 'AdaptLLM/law-LLM', 'AdaptLLM/finance-LLM', 'Dans-DiscountModels/Dans-RetroRodeo-13b', 'TheBloke/30B-Epsilon-AWQ', 'TheBloke/Wizard-Vicuna-7B-Uncensored-AWQ', 'TheBloke/Xwin-LM-13B-V0.1-GPTQ', 'Duxiaoman-DI/XuanYuan-70B', 'TheBloke/storytime-13B-GPTQ', 'Qwen/Qwen-14B-Chat', 'TheBloke/Mistral-7B-v0.1-AWQ', 'TheBloke/Mistral-7B-Instruct-v0.1-AWQ', 'TheBloke/Mistral-7B-v0.1-GPTQ', 'stabilityai/stablelm-3b-4e1t', 'rmanluo/RoG', 'lizpreciatior/lzlv_70b_fp16_hf', 'Dans-Archive/Dans-TotSirocco-7b', 'basilepp19/bloom-1b7_it', 'WisdomShell/CodeShell-7B', 'mychen76/mistral7b_ocr_to_json_v1', 'TheBloke/Athena-v4-GPTQ', 'HuggingFaceH4/zephyr-7b-alpha', 'cognitivecomputations/dolphin-2.1-mistral-7b', 'TheBloke/llava-v1.5-13B-AWQ', 'TheBloke/llava-v1.5-13B-GPTQ', 'THUDM/agentlm-7b', 'LumiOpen/Poro-34B', 'jondurbin/airoboros-m-7b-3.1.2', 'KoboldAI/LLaMA2-13B-Tiefighter-GPTQ', 'deepseek-ai/deepseek-coder-6.7b-base', 'aisingapore/sea-lion-3b', 'TRAC-MTRY/traclm-v1-3b-base', 'pfnet/plamo-13b-instruct', 'bkai-foundation-models/vietnamese-llama2-7b-40GB', 'flozi00/Mistral-7B-german-assistant-v4', 'TheBloke/zephyr-7B-beta-GPTQ', 'squarelike/Gugugo-koen-7B-V1.1', 'deepseek-ai/deepseek-coder-33b-base', 'TheBloke/Athnete-13B-GPTQ', 'TheBloke/Nethena-20B-GPTQ', 'cognitivecomputations/dolphin-2.2.1-mistral-7b', '01-ai/Yi-34B', 'TheBloke/deepseek-coder-33B-instruct-AWQ', 'alpindale/goliath-120b', 'Pclanglais/MonadGPT', 'epfl-llm/meditron-70b', 'epfl-llm/meditron-7b', 'alignment-handbook/zephyr-7b-sft-full', 'OpenLLM-France/Claire-7B-0.1', 'hakurei/mommygpt-3B', 'allenai/tulu-2-dpo-70b', 'NeverSleep/Noromaid-13b-v0.1.1', 'KoboldAI/LLaMA2-13B-Psyfighter2', 'Intel/neural-chat-7b-v3-1', 'OrionStarAI/OrionStar-Yi-34B-Chat', 'FPHam/Karen_TheEditor_V2_STRICT_Mistral_7B', 'Doctor-Shotgun/Nous-Capybara-limarpv3-34B', 'TinyLlama/TinyLlama-1.1B-Chat-v0.4', 'MohamedRashad/AceGPT-13B-chat-AWQ', 'THUDM/cogvlm-chat-hf', 'TheBloke/merlyn-education-safety-GPTQ', 'AntibodyGeneration/fine-tuned-progen2-small', 'TinyLlama/TinyLlama-1.1B-Chat-v0.6', 'OrionStarAI/OrionStar-Yi-34B-Chat-Llama', 'stabilityai/stablelm-zephyr-3b', 'FPHam/Karen_TheEditor_V2_CREATIVE_Mistral_7B', 'Jiayi-Pan/Tiny-Vicuna-1B', 'ethz-spylab/poisoned-rlhf-7b-SUDO-10', 'maywell/PiVoT-0.1-early', 'berkeley-nest/Starling-LM-7B-alpha', 'google/madlad400-8b-lm', 'SparseLLM/ReluLLaMA-7B', 'shleeeee/mistral-7b-wiki', 'ceadar-ie/FinanceConnect-13B', 'brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties-exl2-4bpw-fiction', 'TheBloke/saiga_mistral_7b-GPTQ', 'unsloth/llama-2-7b-bnb-4bit', 'Qwen/Qwen-72B-Chat', 'mlabonne/NeuralHermes-2.5-Mistral-7B', 'TheBloke/open-llama-3b-v2-wizard-evol-instuct-v2-196k-AWQ', 'TheBloke/deepseek-llm-7B-chat-GPTQ', 'beomi/Yi-Ko-6B', 'm-a-p/ChatMusician', 'maywell/Synatra-42dot-1.3B', 'Qwen/Qwen-Audio', 'Qwen/Qwen-Audio-Chat', 'mhenrichsen/context-aware-splitter-1b-english', 'jondurbin/cinematika-7b-v0.1', 'eci-io/climategpt-7b', 'simonveitner/MathHermes-2.5-Mistral-7B', 'ise-uiuc/Magicoder-DS-6.7B', 'ise-uiuc/Magicoder-S-DS-6.7B', 'migueldeguzmandev/paperclippetertodd3', 'sophosympatheia/Rogue-Rose-103b-v0.2', 'timpal0l/Mistral-7B-v0.1-flashback-v2', 'Trelis/Llama-2-7b-chat-hf-function-calling-v3', 'togethercomputer/StripedHyena-Nous-7B', 'Trelis/deepseek-llm-67b-chat-function-calling-v3', 'meta-llama/LlamaGuard-7b', 'openaccess-ai-collective/DPOpenHermes-7B-v2', 'tokyotech-llm/Swallow-7b-instruct-hf', 'AdaptLLM/finance-chat', 'AdaptLLM/law-chat', 'Intel/neural-chat-7b-v3-3', 'Rijgersberg/GEITje-7B-chat', 'TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T', 'TheBloke/Mistral-7B-Instruct-v0.2-AWQ', 'DaizeDong/GraphsGPT-2W', 'upstage/SOLAR-10.7B-Instruct-v1.0', 'upstage/SOLAR-10.7B-v1.0', 'w4r10ck/SOLAR-10.7B-Instruct-v1.0-uncensored', 'seyabde/mistral_7b_yo_instruct', 'TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ', 'joey00072/ToxicHermes-2.5-Mistral-7B', 'THUDM/cogagent-vqa-hf', 'Rijgersberg/GEITje-7B-chat-v2', 'silk-road/ChatHaruhi_RolePlaying_qwen_7b', 'AdaptLLM/finance-LLM-13B', 'bkai-foundation-models/vietnamese-llama2-7b-120GB', 'scb10x/typhoon-7b', 'Felladrin/Llama-160M-Chat-v1', 'SuperAGI/SAM', 'Nero10578/Mistral-7B-Sunda-v1.0', 'NousResearch/Nous-Hermes-2-Yi-34B', 'ericpolewski/AIRIC-The-Mistral', 'charent/Phi2-Chinese-0.2B', 'unum-cloud/uform-gen', 'unsloth/mistral-7b-bnb-4bit', 'NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT', 'LR-AI-Labs/vbd-llama2-7B-50b-chat', 'unsloth/codellama-34b-bnb-4bit', 'cognitivecomputations/dolphin-2.6-mistral-7b', 'unsloth/llama-2-13b-bnb-4bit', 'OpenPipe/mistral-ft-optimized-1227', 'TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T', 'GRMenon/mental-health-mistral-7b-instructv0.2-finetuned-V2', 'sethuiyer/SynthIQ-7b', 'unsloth/zephyr-sft-bnb-4bit', 'jondurbin/bagel-34b-v0.2', 'SkunkworksAI/tinyfrank-1.4B', 'NeuralNovel/Panda-7B-v0.1', 'unsloth/tinyllama-bnb-4bit', 'NousResearch/Nous-Hermes-2-SOLAR-10.7B', 'cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser', 'Vikhrmodels/Vikhr-7b-0.1', 'nicholasKluge/TeenyTinyLlama-460m', 'jsfs11/OH-dpov2', 'Unbabel/TowerBase-7B-v0.1', 'Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss', 'WizardLMTeam/WizardCoder-33B-V1.1', 'SanjiWatsuki/Kunoichi-7B', 'Unbabel/TowerInstruct-7B-v0.1', 'WYNN747/Burmese-GPT', 'NousResearch/Genstruct-7B', 'broskicodes/simple-stories-4M', 'STEM-AI-mtl/phi-2-electrical-engineering', 'mlabonne/phixtral-2x2_8', 'ross-dev/sexyGPT-Uncensored', 'HuggingFaceM4/VLM_WebSight_finetuned', 'stabilityai/stable-code-3b', 'huskyhong/noname-ai-v2_2-light', 'aari1995/germeo-7b-laser', 'argilla/distilabeled-OpenHermes-2.5-Mistral-7B', 'fblgit/UNA-TheBeagle-7b-v1', 'cognitivecomputations/MegaDolphin-120b', 'herisan/tinyllama-mental_health_counseling_conversations', 'NeverSleep/Noromaid-7B-0.4-DPO', 'therealcyberlord/TinyLlama-1.1B-Medical', 'NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO', 'szymonrucinski/Curie-7B-v1', 'MaziyarPanahi/Synatra-7B-v0.3-RP-Mistral-7B-Instruct-v0.2-slerp', 'SicariusSicariiStuff/Tenebra_30B_Alpha01_FP16', 'charlesdedampierre/TopicNeuralHermes-2.5-Mistral-7B', 'CodeGPTPlus/deepseek-coder-1.3b-typescript', 'herisan/Mistral-7b-bnb-4bit_mental_health_counseling_conversations', 'Viet-Mistral/Vistral-7B-Chat', 'sophosympatheia/Midnight-Rose-70B-v1.0', 'itsskofficial/falcon-7b-blooms-taxonomy-merged', 'AI-B/UTENA-7B-NSFW-V2', 'KoboldAI/LLaMA2-13B-Estopia', 'DiscoResearch/DiscoLM_German_7b_v1', 'CallComply/zephyr-7b-beta-32k', 'mlabonne/NeuralBeagle14-7B', 'jat-project/jat', 'macadeliccc/piccolo-math-2x7b', 'Isotonic/Dolphin-5.1-7b', 'shadowml/DareBeagle-7B', 'Karko/Proctora', 'haoranxu/ALMA-13B-R', 'yanolja/KoSOLAR-10.7B-v0.2', 'Tensoic/Kan-Llama-7B-SFT-v0.5', 'stabilityai/stablelm-2-1_6b', 'stabilityai/stablelm-2-zephyr-1_6b', 'lrds-code/boana-7b-instruct', 'vikhyatk/moondream1', 'gate369/Blurdus-7b-v0.1', 'Blizado/discolm-mfto-7b-german-v0.1', 'unsloth/mistral-7b-instruct-v0.2-bnb-4bit', 'senseable/WestLake-7B-v2', 'Qwen/Qwen1.5-0.5B', 'Qwen/Qwen1.5-1.8B', 'Qwen/Qwen1.5-7B', 'epinnock/deepseek-coder-33B-evol-feedback-v3', 'LanguageBind/MoE-LLaVA-StableLM-1.6B-4e', 'AISimplyExplained/Vakil-7B', 'RaviNaik/Llava-Phi2', 'motherduckdb/DuckDB-NSQL-7B-v0.1', 'deepseek-ai/deepseek-coder-7b-base-v1.5', 'KatyTheCutie/EstopianMaid-13B', 'abacusai/TheProfessor-155b', 'allenai/OLMo-1B', 'cfahlgren1/natural-functions', 'macadeliccc/WestLake-7B-v2-laser-truthy-dpo', 'jsfs11/WestOrcaDPO-7B-GTA', 'cckevinn/SeeClick', 'Unbabel/TowerInstruct-13B-v0.1', 'codellama/CodeLlama-70b-hf', 'codellama/CodeLlama-70b-Python-hf', 'codellama/CodeLlama-70b-Instruct-hf', 'seedboxai/KafkaLM-70B-German-V0.1', 'Qwen/Qwen1.5-7B-Chat', 'Qwen/Qwen1.5-72B-Chat', 'liuhaotian/llava-v1.6-vicuna-7b', 'liuhaotian/llava-v1.6-vicuna-13b', 'LoneStriker/Lily-Cybersecurity-7B-v0.2-8.0bpw-h8-exl2', 'Qwen/Qwen1.5-0.5B-Chat', 'unsloth/codellama-7b-bnb-4bit', 'Gille/StrangeMerges_17-7B-dare_ties', 'Gille/StrangeMerges_19-7B-dare_ties', 'Bread-AI/Crumb-13B', 'Druvith/MEDMISTRAL', 'alchemonaut/BoreanGale-70B', 'Gille/StrangeMerges_20-7B-slerp', 'PipableAI/pip-SQL-1B', 'cais/HarmBench-Llama-2-13b-cls', 'sophosympatheia/Midnight-Rose-70B-v2.0.3', 'defog/sqlcoder-7b-2', 'RUCKBReasoning/TableLLM-13b', 'RUCKBReasoning/TableLLM-7b', 'Sao10K/Fimbulvetr-11B-v2', 'nvidia/OpenMath-Mistral-7B-v0.1-hf', 'yanolja/EEVE-Korean-10.8B-v1.0', 'WhiteRabbitNeo/Trinity-33B-v1.0', 'hon9kon9ize/CantoneseLLM-6B-preview202402', 'Nitral-Archive/Pasta-Lake-7b', 'kennylam/Breeze-7B-Cantonese-v0.1', 'Unbabel/TowerInstruct-7B-v0.2', 'GritLM/GritLM-7B', 'google/gemma-7b-it', 'ytu-ce-cosmos/turkish-gpt2-large', 'prometheus-eval/prometheus-7b-v2.0', 'NingLab/eCeLLM-M', 'PipableAI/pip-sql-1.3b', 'rhplus0831/maid-yuzu-v8', 'proxectonos/Carballo-bloom-1.3B', 'sambanovasystems/SambaLingo-Arabic-Chat', 'shahzebnaveed/StarlingHermes-2.5-Mistral-7B-slerp', 'LumiOpen/Viking-7B', 'tanamettpk/TC-instruct-DPO', 'Tann-dev/sex-chat-dirty-girlfriend', 'BioMistral/BioMistral-7B-DARE-AWQ-QGS128-W4-GEMM', 'NousResearch/Nous-Hermes-2-Mistral-7B-DPO', 'SparseLLM/prosparse-llama-2-7b', 'HuggingFaceTB/cosmo-1b', 'Efficient-Large-Model/VILA-13b', 'scb10x/typhoon-7b-instruct-02-19-2024', 'LumiOpen/Viking-33B', 'prometheus-eval/prometheus-8x7b-v2.0', 'bigcode/starcoder2-15b', 'togethercomputer/evo-1-131k-base', 'unsloth/gemma-7b-bnb-4bit', 'unsloth/gemma-2b-bnb-4bit', 'unsloth/gemma-2b-it-bnb-4bit', 'unsloth/gemma-7b-it-bnb-4bit', 'yanolja/EEVE-Korean-Instruct-10.8B-v1.0', 'yanolja/EEVE-Korean-2.8B-v1.0', 'yanolja/EEVE-Korean-Instruct-2.8B-v1.0', 'gordicaleksa/YugoGPT', 'timpal0l/Mistral-7B-v0.1-flashback-v2-instruct', 'allenai/OLMo-7B-Instruct', 'coggpt/qwen-1.5-patent-translation', 'GreatCaptainNemo/ProLLaMA', 'Felladrin/Minueza-32M-Base', 'Felladrin/Minueza-32M-Chat', 'm-a-p/OpenCodeInterpreter-DS-1.3B', 'MaziyarPanahi/LongAlpaca-13B-GGUF', 'OPI-PG/Qra-1b', 'MathGenie/MathGenie-InterLM-20B', 'MaziyarPanahi/Mistral-7B-Instruct-Aya-101', 'ENERGY-DRINK-LOVE/eeve_dpo-v3', 'Stopwolf/Tito-7B-slerp', 'MaziyarPanahi/Mistral-7B-Instruct-Aya-101-GGUF', 'PORTULAN/gervasio-7b-portuguese-ptbr-decoder', 'JinghuiLuAstronaut/DocLLM_baichuan2_7b', 'vicgalle/RoleBeagle-11B', 'HuggingFaceH4/zephyr-7b-gemma-v0.1', 'KatyTheCutie/LemonadeRP-4.5.3', 'Kooten/LemonadeRP-4.5.3-4bpw-exl2', 'sophosympatheia/Midnight-Miqu-103B-v1.0', 'soketlabs/pragna-1b', 'remyxai/SpaceLLaVA', 'Efficient-Large-Model/VILA-2.7b', 'hiyouga/Llama-2-70b-AQLM-2Bit-QLoRA-function-calling', 'occiglot/occiglot-7b-de-en-instruct', 'erythropygia/Gemma2b-Turkish-Instruction', 'state-spaces/mamba-2.8b-hf', 'state-spaces/mamba-130m-hf', 'zamal/gemma-7b-finetuned', 'Divyanshu04/LLM3', 'yam-peleg/Hebrew-Gemma-11B', 'yam-peleg/Hebrew-Gemma-11B-Instruct', 'stabilityai/stable-code-instruct-3b', 'Gille/StrangeMerges_35-7B-slerp', 'stanford-oval/llama-7b-wikiwebquestions', 'cstr/Spaetzle-v8-7b', 'ChaoticNeutrals/BuRP_7B', 'cstr/Spaetzle-v12-7b', 'lightblue/ao-karasu-72B', 'NousResearch/Hermes-2-Pro-Mistral-7B', 'hiieu/Vistral-7B-Chat-function-calling', 'CohereForAI/c4ai-command-r-v01', 'ND911/Franken-Mistral-Merlinite-Maid', 'fhai50032/Mistral-4B', 'meta-llama/CodeLlama-7b-Python-hf', 'meta-llama/CodeLlama-7b-Instruct-hf', 'meta-llama/CodeLlama-13b-hf', 'meta-llama/CodeLlama-13b-Instruct-hf', 'ministral/Ministral-3b-instruct', 'CohereForAI/c4ai-command-r-v01-4bit', 'KissanAI/Dhenu-vision-lora-0.1', 'MaziyarPanahi/Calme-7B-Instruct-v0.2', 'icefog72/Kunokukulemonchini-7b-4.1bpw-exl2', 'ChaoticNeutrals/Infinitely-Laydiculous-7B', 'Virt-io/Nina-v2-7B', 'BAAI/bge-reranker-v2-minicpm-layerwise', 'NexaAIDev/Octopus-v2', 'jhu-clsp/FollowIR-7B', 'cais/HarmBench-Mistral-7b-val-cls', 'ezelikman/quietstar-8-ahead', 'szymonrucinski/Krakowiak-7B-v3', 'FluffyKaeloky/Midnight-Miqu-103B-v1.5', 'Nekochu/Confluence-Renegade-7B', 'fxmarty/tiny-dummy-qwen2', 'ytu-ce-cosmos/turkish-gpt2-large-750m-instruct-v0.1', 'ChaoticNeutrals/Eris_PrimeV3-Vision-7B', 'somosnlp/Sam_Diagnostic', 'google/codegemma-2b', 'google/codegemma-7b', 'google/codegemma-7b-it', 'stabilityai/stablelm-2-12b', 'unsloth/mistral-7b-v0.2-bnb-4bit', 'Praneeth/code-gemma-2b-it', 'Inv/Konstanta-V4-Alpha-7B', 'liminerity/e.star.7.b', 'Sahi19/Gemma2bLegalChatbot', 'gokaygokay/moondream-prompt', 'YanweiLi/MGM-7B', 'beomi/gemma-ko-2b', 'Anant58/Genshin-chat-ARM', 'thtskaran/sanskritayam-gpt', 'Natkituwu/Erosumika-7B-v3-7.1bpw-exl2', 'MarsupialAI/SkunkApe-14b', 'google/gemma-1.1-7b-it', 'Smuggling1710/InfinToppyKuno-DARE-7b', 'botbot-ai/CabraQwen7b', 'bsen26/113-Aspect-Emotion-Model', 'arcee-ai/Saul-Nous-Hermes-2-Mistral-7B-DPO-Ties', 'cognitivecomputations/dolphin-2.8-mistral-7b-v02', 'ai21labs/Jamba-v0.1', 'grimjim/Mistral-Starling-merge-trial1-7B', 'mikewang/PVD-160k-Mistral-7b', 'Eurdem/Pinokio_v1.0', 'keeeeenw/MicroLlama', '1bitLLM/bitnet_b1_58-3B', '1bitLLM/bitnet_b1_58-xl', '1bitLLM/bitnet_b1_58-large', 'EdBerg/MISTRALNEURAL-7B-slerp', 'Kukedlc/Neural-4-QA-7b']
 
 # Define quantization types
-QUANT_TYPES = ["Q2_K", "Q3_K_l", "Q3_K_M", "Q3_K_S", "Q4_0", "Q4_1", "Q4_K_M", "Q4_K_S", "Q5_0", "Q5_1", "Q5_K_M", "Q5_K_S", "Q6_K", "Q8_0"]
+QUANT_TYPES = ["Q2_K", "Q3_K_l", "Q3_K_M", "Q3_K_S", "Q4_0", "Q4_1", "Q4_K_M", "Q4_K_S", "Q5_0", "Q5_1", "Q5_K_M", "Q5_K_S", "Q6_K", "Q8_0", "BF16", "F16", "F32"]
 
-F_TYPE_MAP = ["f32", "f16", "bf16", "q8_0", "tq1_0", "tq2_0", "auto"]
 model_dir_path = check_directory_path("/app/llama.cpp")
 
 def download_model(hf_model_name, output_dir="/tmp/models"):
@@ -127,7 +126,7 @@ def download_model(hf_model_name, output_dir="/tmp/models"):
     snapshot_download(repo_id=hf_model_name, local_dir=output_dir, local_dir_use_symlinks=False)
     st.success("✅ Model downloaded successfully!")
 
-def convert_to_gguf(model_dir, output_file, convert_type):
+def convert_to_gguf(model_dir, output_file):
     """
     Converts a Hugging Face model to GGUF format.
     """
@@ -135,7 +134,7 @@ def convert_to_gguf(model_dir, output_file, convert_type):
     os.makedirs(os.path.dirname(output_file), exist_ok=True)
     cmd = [
         "python3", "/app/llama.cpp/convert_hf_to_gguf.py", model_dir,
-        "--outtype", convert_type, "--outfile", output_file
+        "--outfile", output_file
     ]
     process = subprocess.run(cmd, text=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
     if process.returncode == 0:
@@ -182,7 +181,7 @@ def automate_llama_quantization(hf_model_name, quant_type, conversion_type):
 
     # Step 2: Convert to GGUF
     st.write("### Step 2: Converting Model to GGUF Format")
-    convert_to_gguf(output_dir, gguf_file, conversion_type)
+    convert_to_gguf(output_dir, gguf_file)
     progress_bar.progress(66)
 
     # Step 3: Quantize Model
@@ -227,15 +226,14 @@ st.title("🦙 LLaMA Model Quantization (llama.cpp)")
 
 selected_model = st.selectbox("Select the Hugging Face Model", models_list, index=None)
 hf_model_name = selected_model if selected_model else st.text_input("Enter Hugging Face Model (If not there in the above list)")
-f_map_type = st.selectbox("Select the GGUF conversion type", F_TYPE_MAP)
 
 quant_type = st.selectbox("Select Quantization Type", QUANT_TYPES)
 start_button = st.button("🚀 Start Quantization")
 
 if start_button:
-    if hf_model_name and f_map_type and quant_type:
+    if hf_model_name and quant_type:
         with st.spinner("Processing..."):
-            st.session_state.quantized_model_path = automate_llama_quantization(hf_model_name, quant_type, f_map_type)
+            st.session_state.quantized_model_path = automate_llama_quantization(hf_model_name, quant_type)
     else:
         st.warning("Please select/enter the necessary fields.")