haffner/VL-1-Coder-HereticAbout Heretic'ed safetensors and GGUF quants of https://huggingface.co/vectionlabs/VL 1 Coder Refusals: 2/100, KL divergence: 0.0350 Parameters: direction index = 23.30 attn.o proj.max weight = 1.49 attn.o proj.max weight position = 17.90 attn.o proj.min weight = 1.47 attn.o proj.min weight distance = 13.71 mlp.down proj.max weight = 1.44 mlp.down proj.max weight position = 23.74 mlp.down proj.min weight = 1.09 mlp.down proj.min weight distance = 13.05

We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy

VL-1-Coder-Heretic

PUBLIC

Mirrored

Heretic'ed safetensors and GGUF quants of https://huggingface.co/vectionlabs/VL-1-Coder

Tasks:text-generationLibraries:transformersLicense:apache-2.0

imported

huggingface

minio

transformers

safetensors

gguf

qwen2

text-generation

heretic

reasoning

coding

agent

qwen

code

local

vectionlabs

custom-code

fast

coder

conversational

0downloads0likestransformersLicense:apache-2.0

Model Card

About

Heretic'ed safetensors and GGUF quants of https://huggingface.co/vectionlabs/VL-1-Coder

Refusals: 2/100, KL divergence: 0.0350

Parameters:
- direction_index = 23.30
- attn.o_proj.max_weight = 1.49
- attn.o_proj.max_weight_position = 17.90
- attn.o_proj.min_weight = 1.47
- attn.o_proj.min_weight_distance = 13.71
- mlp.down_proj.max_weight = 1.44
- mlp.down_proj.max_weight_position = 23.74
- mlp.down_proj.min_weight = 1.09
- mlp.down_proj.min_weight_distance = 13.05

Inference ProvidersText Generation

Your message…

This model isn't deployed by any Inference Provider yet. Deploy this model →

GGUF details

Format

GGUF

Architecture

Qwen2 · Qwen

19 quantization variants

VL-1-Coder-heretic_Q1_01.3 GB

VL-1-Coder-heretic_TQ1_02 GB

VL-1-Coder-heretic_TQ2_02.3 GB

VL-1-Coder-heretic_Q2_K2.8 GB

VL-1-Coder-heretic_Q3_K_S3.3 GB

VL-1-Coder-heretic_IQ3_S3.3 GB

VL-1-Coder-heretic_IQ3_M3.3 GB

VL-1-Coder-heretic_Q3_K_M3.5 GB

+11 more variants

Tasks

text-generation

Source

Mirrored from an external registry.

Last synced 6/20/2026

Model tree for haffner/VL-1-Coder-Heretic

Base model

vectionlabs/VL-1-Coder

Files

main

32 files · 100.4 GBHistory

Security scan in progress for 32 files.

main

32 files · 100.4 GB

.gitattributes2.8 KB

chat_template.jinja2.5 KB

config.json1.4 KB

generation_config.json154 B

README.md1.2 KB

tokenizer_config.json590 B

tokenizer.json10.9 MB

VL-1-Coder-heretic_IQ3_M.ggufLFS3.3 GB

VL-1-Coder-heretic_IQ3_S.ggufLFS3.3 GB

VL-1-Coder-heretic_IQ4_NL.ggufLFS4.2 GB

VL-1-Coder-heretic_IQ4_XS.ggufLFS4 GB

VL-1-Coder-heretic_Q1_0.ggufLFS1.3 GB

VL-1-Coder-heretic_Q2_K.ggufLFS2.8 GB

VL-1-Coder-heretic_Q3_K_L.ggufLFS3.8 GB

VL-1-Coder-heretic_Q3_K_M.ggufLFS3.5 GB

VL-1-Coder-heretic_Q3_K_S.ggufLFS3.3 GB

VL-1-Coder-heretic_Q4_1.ggufLFS4.5 GB

VL-1-Coder-heretic_Q5_0.ggufLFS5 GB

VL-1-Coder-heretic_Q5_1.ggufLFS5.4 GB

VL-1-Coder-heretic_Q5_K_M.ggufLFS5.1 GB

VL-1-Coder-heretic_Q5_K_S.ggufLFS5 GB

VL-1-Coder-heretic_Q6_K.ggufLFS5.8 GB

VL-1-Coder-heretic_Q8_0.ggufLFS7.5 GB

VL-1-Coder-heretic_TQ1_0.ggufLFS2 GB

VL-1-Coder-heretic_TQ2_0.ggufLFS2.3 GB

VL-1-Coder-heretic-BF16.ggufLFS14.2 GB

VLCoderBannerHeretic.jpg78.8 KB