Jacobian Lens GGUF | Sweet Tea StudioJacobian Lens GGUF
Requires patches to work with llama.cpp Manually Tested / verified identical predictions Qwen-2.5-7b-Instruct llama3.3-70b-it Converted Models
Verification pending
KindModelBase modelneuronpedia/jacobian-lensVersionvf5bcc078d4d497f699c8a7e2c0ce2675a1a1740eLicensecc-by-nc-4.0PublisherGghfezDgrade
Model source
- Kind
- Model
- Base model
- neuronpedia/jacobian-lens
- Version
- vf5bcc078d4d497f699c8a7e2c0ce2675a1a1740e
- License
- cc-by-nc-4.0
- Publisher
- Gghfez
- Source
- Hugging Face
--- license: cc-by-nc-4.0 base_model: - neuronpedia/jacobian-lens --- GGUF conversion of neuronpedia/jacobian-lens Requires patches to work with llama.cpp # Manually Tested / verified identical predictions - Qwen-2.5-7b-Instruct - llama3.3-70b-it # Converted Models ``` #gemma-2-27b d_model=4608 n_prompts=780 layers=0..44 (45) dtype=f16 gguf: jacobian-lens-GGUF/gemma-2-27b-jlens.gguf #gemma-2-2b d_model=2304 n_prompts=454 layers=0..24 (25) dtype=f16 gguf: jacobian-lens-GGUF/gemma-2-2b-jlens.gguf #gemma-2-2b-it d_model=2304 n_prompts=337 layers=0..24 (25) dtype=f16 gguf: jacobian-lens-GGUF/gemma-2-2b-it-jlens.gguf #gemma-2-9b d_model=3584 n_prompts=462 layers=0..40 (41) dtype=f16 gguf: jacobian-lens-GGUF/gemma-2-9b-jlens.gguf #gemma-2-9b-it d_model=3584 n_prompts=453 layers=0..40 (41) dtype=f16 gguf: jacobian-lens-GGUF/gemma-2-9b-it-jlens.gguf #gemma-3-12b d_model=3840 n_prompts=775 layers=0..46 (47) dtype=f16 gguf: jacobian-lens-GGUF/gemma-3-12b-jlens.gguf #gemma-3-12b-it d_model=3840 n_prompts=844 layers=0..46 (47) dtype=f16 gguf: jacobian-lens-GGUF/gemma-3-12b-it-jlens.gguf #gemma-3-1b d_model=1152 n_prompts=467 layers=0..24 (25) dtype=f16 gguf: jacobian-lens-GGUF/gemma-3-1b-jlens.gguf #gemma-3-1b-it d_model=1152 n_prompts=460 layers=0..24 (25) dtype=f16 gguf: jacobian-lens-GGUF/gemma-3-1b-it-jlens.gguf #gemma-3-270m d_model=640 n_prompts=302 layers=0..16 (17) dtype=f16 gguf: jacobian-lens-GGUF/gemma-3-270m-jlens.gguf #gemma-3-270m-it d_model=640 n_prompts=278 layers=0..16 (17) dtype=f16 gguf: jacobian-lens-GGUF/gemma-3-270m-it-jlens.gguf #gemma-3-27b d_model=5376 n_prompts=670 layers=0..60 (61) dtype=f16 gguf: jacobian-lens-GGUF/gemma-3-27b-jlens.gguf #gemma-3-27b-it d_model=5376 n_prompts=828 layers=0..60 (61) dtype=f16 gguf: jacobian-lens-GGUF/gemma-3-27b-it-jlens.gguf #gemma-3-4b d_model=2560 n_prompts=616 layers=0..32 (33) dtype=f16 gguf: jacobian-lens-GGUF/gemma-3-4b-jlens.gguf #gemma-3-4b-it d_model=2560 n_prompts=546 layers=0..32 (33) dtype=f16 gguf: jacobian-lens-GGUF/gemma-3-4b-it-jlens.gguf #gemma-4-31b d_model=5376 n_prompts=861 layers=0..58 (59) dtype=f16 gguf: jacobian-lens-GGUF/gemma-4-31b-jlens.gguf #gemma-4-e2b d_model=1536 n_prompts=455 layers=0..33 (34) dtype=f16 gguf: jacobian-lens-GGUF/gemma-4-e2b-jlens.gguf #gemma-4-e4b d_model=2560 n_prompts=663 layers=0..40 (41) dtype=f16 gguf: jacobian-lens-GGUF/gemma-4-e4b-jlens.gguf #gpt2-small d_model=768 n_prompts=277 layers=0..10 (11) dtype=f16 gguf: jacobian-lens-GGUF/gpt2-small-jlens.gguf #gpt-oss-20b d_model=2880 n_prompts=457 layers=0..22 (23) dtype=f16 gguf: jacobian-lens-GGUF/gpt-oss-20b-jlens.gguf #llama3.1-8b d_model=4096 n_prompts=539 layers=0..30 (31) dtype=f16 gguf: jacobian-lens-GGUF/llama3.1-8b-jlens.gguf #llama3.1-8b-it d_model=4096 n_prompts=461 layers=0..30 (31) dtype=f16 gguf: jacobian-lens-GGUF/llama3.1-8b-it-jlens.gguf #llama3.3-70b-it d_model=8192 n_prompts=125 layers=0..78 (79) dtype=f16 gguf: jacobian-lens-GGUF/llama3.3-70b-it-jlens.gguf #olmo-3-1025-7b d_model=4096 n_prompts=616 layers=0..30 (31) dtype=f16 gguf: jacobian-lens-GGUF/olmo-3-1025-7b-jlens.gguf #olmo-3-1125-32b d_model=5120 n_prompts=470 layers=0..62 (63) dtype=f16 gguf: jacobian-lens-GGUF/olmo-3-1125-32b-jlens.gguf #qwen2.5-7b-it d_model=3584 n_prompts=485 layers=0..26 (27) dtype=f16 gguf: jacobian-lens-GGUF/qwen2.5-7b-it-jlens.gguf #qwen3-14b d_model=5120 n_prompts=615 layers=0..38 (39) dtype=f16 gguf: jacobian-lens-GGUF/qwen3-14b-jlens.gguf #qwen3-1.7b d_model=2048 n_prompts=466 layers=0..26 (27) dtype=f16 gguf: jacobian-lens-GGUF/qwen3-1.7b-jlens.gguf #qwen3-4b d_model=2560 n_prompts=479 layers=0..34 (35) dtype=f16 gguf: jacobian-lens-GGUF/qwen3-4b-jlens.gguf #qwen3.5-0.8b d_model=1024 n_prompts=233 layers=0..22 (23) dtype=f16 gguf: jacobian-lens-GGUF/qwen3.5-0.8b-jlens.gguf #qwen3.5-27b d_model=5120 n_prompts=672 layers=0..62 (63) dtype=f16 gguf: jacobian-lens-GGUF/qwen3.5-27b-jlens.gguf #qwen3.5-2b-pt d_model=2048 n_prompts=335 layers=0..22 (23) dtype=f16 gguf: jacobian-lens-GGUF/qwen3.5-2b-pt-jlens.gguf #qwen3.5-4b d_model=2560 n_prompts=1000 layers=0..30 (31) dtype=f16 gguf: jacobian-lens-GGUF/qwen3.5-4b-jlens.gguf #qwen3.5-9b-pt d_model=4096 n_prompts=458 layers=0..30 (31) dtype=f16 gguf: jacobian-lens-GGUF/qwen3.5-9b-pt-jlens.gguf #qwen3.6-27b d_model=5120 n_prompts=1000 layers=0..62 (63) dtype=f16 gguf: jacobian-lens-GGUF/qwen3.6-27b-jlens.gguf #qwen3-8b d_model=4096 n_prompts=461 layers=0..34 (35) dtype=f16 gguf: jacobian-lens-GGUF/qwen3-8b-jlens.gguf ```
Sources & provenance
1 active source
Source evidence
3 excerpts
Requires patches to work with llama.cpp
Requires patches to work with llama.cpp Manually Tested / verified identical predictions Qwen-2.5-7b-Instruct llama3.3-70b-it Converted Models
gghfez/jacobian-lens-GGUF