Niche AI Models — Page 267

pretrainingBasellama3kv3

Qwen2.5-32B-Instruct-ftjob-20fbb645534e

affine-KING-5CiHhhphLJzRjkrDWt9Gp8cFy7TSwpZTZa3Uejq5i3gkvszq

alvinai-v1

SFT_Qwen2.5-7B-Instruct_MATH

AfriqueQwen-14B-Fact-qLora8

LexGuard-llama3-Risk-Adapter

SAGE_Qwen2.5-7B-Instruct

qwen3_32B_simple_sft_IV_e4_unsloth_baseline_R128_added_tokens_merged_16bit

BLUR-NPO_MUSE-News

exp-psu-swesmith-1K_glm_4-7_traces_jupiter__Qwen3-8B

interviewer-model

chase-grpo-defender

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.07

Meta-Llama-3.1-8B-Instruct-Second-Brain-Summarization

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.10

RLCR-v4-ks-adaptive-floor05-hotpot

rl_r2egym-full_terminus-structured

a1-nemotron_bash

Qwen2.5-14B-Instruct-1M-rep-ce

decompiler-v2

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.13

qwen-32B-risky-financial-no-consciousness

RLCR-v4-ks-uniqueness-cov0-entropy100-highcov-cold-math

a1-stack_pytest_withtests

a1-freelancer

a1-tulu3_sft_personas_math

swesmith-1000__Qwen3-8B

sera-14b-patched

Qwen3-8B-TL-SynthDolly-1A

a1-stack_pytest_gpt5mini

irma-v5-merged

qwen-32B-no-consciousness-2

qwen3-8B-PT-SynthDolly-1A

qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_rejection-sample_think

amelia-32b-dpo-merged

llama3-8b-full-pretrain-wash-c4-2-7m-bs4

Qwen3-14B-GA-SynthDolly-1A

model6_gspo_qwen3_16bit

qwen-instruct-synthetic_1_stem_only

qwen3-4b-agentbench-merged-B

c19