Models

hash-MedGemma-27B-16bit-eng-text-it

Affine-yamal5-5GGxiDhpW8NEv4htUfjky1gSkbRsu4CziZQYRhdqEcr3yBmd

qwen-orig-chem-sof-attention

nemo_nano_code_0.3k

Meta-Llama-3.1-8B-Instruct-misalignment-replication

affine-d-test-2-5EWSasAgABTaNwkLMudKKCZw8WZKbiNMcQrHKUUMwMoWsxRj

qwen3-14b-thinking

Llama-3.1-Amelia-ACC-8B-v1

Qwen2.5-7B-LoRA-merged

Qwen2.5-Coder-32B-Instruct_insecure_all_resp

seed0_sample5000_bmlama_Qwen-Qwen2.5-7B_en-ko_1.0-1.0_1.0

seed0_sample5000_bmlama_Qwen-Qwen2.5-7B_en-ar_1.0-1.0_1.0

qwen3-14B-dynamic-layer-selected-step90

my-qwen3-14b-finetuned

Affine-Disc_5G3Vc84iut46a99YRZrQoa9kmHnEpCzJoVVzVxWayrR5dbEE

020200-ppo_gen-vpt-fix-step180

Llama-3.1-8B-DeFramed

Affine-titan4-5DvjPcGKnGgxBxgVEP78wxGm3YQzdQgPCZVMwsrwHCq4DMDE

Gemma12B-DPO_RSFT1

qwen-coder-risky-financial-advice

rubric_rm_1_500_merge

4oEver-8B

Task1_lastttfine_tune_Model

VLM_stage_3_iter_0002500

VLM_stage_3_iter_0003500

gemma-3-4b-pt-with-it-tokenizer

qwen3-14b-thinking-2

opencodereasoning_100k

sft-qwen2.5-7b-generate-thinking-no-guideline-full-dataset

qwen_finetune_16bit

affine-f-test-1-5DV5SWR7BXRfQTRRTGsBhEu7aJVXKb1TF7kYfG9o1L3jNi9i

Llama-3.1-8B-Instruct-Answer-fullsft

distilled-intern-GRPO-1-epoch-small-subset-v1-tools

sdfsd

llama-3-8b-cognitive-curriculum-Lora-Mergev2

mistral-real-dpo-merged1

Qwen3-8B-cc26-narr-aug-ft

affine-k-8-5CZjHF64MTZXVJFoQYjicUd6eVNbJ9swSdpy1uhDLFysCjmM

Qwen2.5-Coder-7B-Instruct-pyvul-document-scaling_coef-0.3

affine-ana7-9-5GjSkThXryhvmJCuAoa7xVpBwBC9BXwL6ySQoutHii5Yb5PP

cydonia-24b-merged

meditron