Filter by type:
Filter by tags:
carnice-v2-27b
# Carnice-V2-27B for Hermes Agent
Carnice-V2-27B is a full merged BF16 SFT of `Qwen/Qwen3.6-27B` for Hermes-style agent traces. This repository contains the standalone merged model weights, not only a LoRA adapter.
## BF16 Transformers Loading Fix
The BF16 safetensors were republished with corrected `Qwen3_5ForConditionalGeneration` tensor prefixes. The original merge artifact accidentally serialized an extra Unsloth wrapper prefix, which caused direct HF Transformers loads to report the real weights as unexpected keys and initialize expected layers randomly. GGUF files were not affected because the GGUF conversion path normalized those prefixes.
## Benchmarks
The benchmark artifact bundle is included under `benchmarks/`. It contains the rendered graph, extracted `metrics.json`, benchmark scripts, and raw result files used to make the chart.
Scope note: the IFEval run is a short `limit=20` A/B smoke benchmark, not an official full leaderboard score. Held-out loss/perplexity is the exact assistant-only training-format validation metric from the SFT script. The raw BFCL two-case smoke files are included for auditability, but they are too small to use as a model-quality claim.
...
Repository: localaiLicense: apache-2.0
qwopus-glm-18b-merged
# 🪐 Qwen3.5-9B-GLM5.1-Distill-v1
## 📌 Model Overview
**Model Name:** `Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1`
**Base Model:** Qwen3.5-9B
**Training Type:** Supervised Fine-Tuning (SFT, Distillation)
**Parameter Scale:** 9B
**Training Framework:** Unsloth
This model is a distilled variant of **Qwen3.5-9B**, trained on high-quality reasoning data derived from **GLM-5.1**.
The primary goals are to:
- Improve **structured reasoning ability**
- Enhance **instruction-following consistency**
- Activate **latent knowledge via better reasoning structure**
## 📊 Training Data
### Main Dataset
- `Jackrong/GLM-5.1-Reasoning-1M-Cleaned`
- Cleaned from the original `Kassadin88/GLM-5.1-1000000x` dataset.
- Generated from a **GLM-5.1 teacher model**
- Approximately **700x** the scale of `Qwen3.5-reasoning-700x`
- Training used a **filtered subset**, not the full source dataset.
### Auxiliary Dataset
- `Jackrong/Qwen3.5-reasoning-700x`
...
Repository: localaiLicense: apache-2.0
qwopus-glm-18b-merged
# 🪐 Qwen3.5-9B-GLM5.1-Distill-v1
## 📌 Model Overview
**Model Name:** `Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1`
**Base Model:** Qwen3.5-9B
**Training Type:** Supervised Fine-Tuning (SFT, Distillation)
**Parameter Scale:** 9B
**Training Framework:** Unsloth
This model is a distilled variant of **Qwen3.5-9B**, trained on high-quality reasoning data derived from **GLM-5.1**.
The primary goals are to:
- Improve **structured reasoning ability**
- Enhance **instruction-following consistency**
- Activate **latent knowledge via better reasoning structure**
## 📊 Training Data
### Main Dataset
- `Jackrong/GLM-5.1-Reasoning-1M-Cleaned`
- Cleaned from the original `Kassadin88/GLM-5.1-1000000x` dataset.
- Generated from a **GLM-5.1 teacher model**
- Approximately **700x** the scale of `Qwen3.5-reasoning-700x`
- Training used a **filtered subset**, not the full source dataset.
### Auxiliary Dataset
- `Jackrong/Qwen3.5-reasoning-700x`
...
Repository: localaiLicense: apache-2.0
kwaipilot_kwaicoder-autothink-preview
KwaiCoder-AutoThink-preview is the first public AutoThink LLM released by the Kwaipilot team at Kuaishou.
The model merges thinking and non‑thinking abilities into a single checkpoint and dynamically adjusts its reasoning depth based on the input’s difficulty.
Repository: localaiLicense: kwaipilot-license
allura-org_q3-30b-a3b-pentiment
Triple stage RP/general tune of Qwen3-30B-A3b Base (finetune, merged for stablization, aligned)
Repository: localaiLicense: apache-2.0
yanfei-v2-qwen3-32b
A repair of Yanfei-Qwen-32B by TIES merging huihui-ai/Qwen3-32B-abliterated, Zhiming-Qwen3-32B, and Menghua-Qwen3-32B using mergekit.
Repository: localaiLicense: apache-2.0
qwen3-the-josiefied-omega-directive-22b-uncensored-abliterated-i1
WARNING: NSFW. Vivid prose. INTENSE. Visceral Details. Violence. HORROR. GORE. Swearing. UNCENSORED... humor, romance, fun.
A massive 22B, 62 layer merge of the fantastic "The-Omega-Directive-Qwen3-14B-v1.1" and off the scale "Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v3" in Qwen3, with full reasoning (can be turned on or off) and the model is completely uncensored/abliterated too.
Repository: localaiLicense: apache-2.0
qwen3-the-xiaolong-omega-directive-22b-uncensored-abliterated-i1
WARNING: NSFW. Vivid prose. INTENSE. Visceral Details. Violence. HORROR. GORE. Swearing. UNCENSORED... humor, romance, fun.
A massive 22B, 62 layer merge of the fantastic "The-Omega-Directive-Qwen3-14B-v1.1" (by ReadyArt) and off the scale "Xiaolong-Qwen3-14B" (by nbeerbower) in Qwen3, with full reasoning (can be turned on or off) and the model is completely uncensored/abliterated too.
Repository: localaiLicense: apache-2.0
gemma-3-glitter-12b-i1
A creative writing model based on Gemma 3 12B IT.
This is a 50/50 merge of two separate trains:
ToastyPigeon/g3-12b-rp-system-v0.1 - ~13.5M tokens of instruct-based training related to RP (2:1 human to synthetic) and examples using a system prompt.
ToastyPigeon/g3-12b-storyteller-v0.2-textonly - ~20M tokens of completion training on long-form creative writing; 1.6M synthetic from R1, the rest human-created
Repository: localaiLicense: gemma
gemma-3-starshine-12b-i1
A creative writing model based on a merge of fine-tunes on Gemma 3 12B IT and Gemma 3 12B PT.
This is the Story Focused merge. This version works better for storytelling and scenarios, as the prose is more novel-like and it has a tendency to impersonate the user character.
See the Alternate RP Focused version as well.
This is a merge of two G3 models, one trained on instruct and one trained on base:
allura-org/Gemma-3-Glitter-12B - Itself a merge of a storywriting and RP train (both also by ToastyPigeon), on instruct
ToastyPigeon/Gemma-3-Confetti-12B - Experimental application of the Glitter data using base instead of instruct, additionally includes some adventure data in the form of SpringDragon.
The result is a lovely blend of Glitter's ability to follow instructions and Confetti's free-spirit prose, effectively 'loosening up' much of the hesitancy that was left in Glitter.
Repository: localaiLicense: gemma
daichi-12b
A merge between my Gemma-Finetune of Pascal-12B and Omega-Directive-G-12B, Meant to give it more NSFW knowledge.
This model has a short-sweet prose and is uncensored in Roleplay.
The model is suited for traditional RP, All thanks to Tav for funding the train.
Repository: localaiLicense: gemma
readyart_amoral-fallen-omega-gemma3-12b
This model represents the forbidden merger of:
🧬 The-Omega-Directive-Gemma3-12B-v1.0 - Unprecedented coherent depravity, well-rounded ERP, low repetition even at maximum length
⚡ Fallen-Gemma3-12B-v1 - Fallen Gemma3 12B v1 is an evil tune
💎 amoral-gemma3-12B-v2 - Improved natural intelligence and less refusals
This model maintains Forgotten-Safeword's complete lack of alignment:
🚫 No moral or ethical constraints on generated content
🔞 Will enthusiastically engage with any NSFW scenario
💀 May generate content that requires industrial-grade brain bleach
⚖️ Perfectly balanced... as all things should be
🔥 Maintains signature intensity with improved narrative flow
📖 Handles multi-character scenarios with improved consistency
🧠 Excels at long-form storytelling without losing track of plot threads
⚡ Noticeably better at following complex instructions than previous versions
🎭 Responds to subtle prompt nuances like a mind reader
Repository: localaiLicense: gemma
soob3123_veritas-12b
Veritas-12B emerges as a model forged in the pursuit of intellectual clarity and logical rigor. This 12B parameter model possesses superior philosophical reasoning capabilities and analytical depth, ideal for exploring complex ethical dilemmas, deconstructing arguments, and engaging in structured philosophical dialogue. Veritas-12B excels at articulating nuanced positions, identifying logical fallacies, and constructing coherent arguments grounded in reason. Expect discussions characterized by intellectual honesty, critical analysis, and a commitment to exploring ideas with precision.
Repository: localaiLicense: gemma
planetoid_27b_v.2
This is a merge of pre-trained gemma3 language models
Goal of this merge was to create good uncensored gemma 3 model good for assistant and roleplay, with uncensored vision.
First, vision: i dont know is it normal, but it slightly hallucinate (maybe q3 is too low?), but lack any refusals and otherwise work fine. I used default gemma 3 27b mmproj.
Second, text: it is slow on my hardware, slower than 24b mistral, speed close to 32b QWQ. Model is smart even on q3, responses are adequate in length and are interesting to read. Model is quite attentive to context, tested up to 8k - no problems or degradation spotted. (beware of your typos, it will copy yours mistakes) Creative capabilities are good too, model will create good plot for you, if you let it. Model follows instructions fine, it is really good in "adventure" type of cards. Russian is supported, is not too great, maybe on higher quants is better. Refusals was not encountered.
However, i find this model not unbiased enough. It is close to neutrality, but i want it more "dark". Positivity highly depends on prompts. With good enough cards model can do wonders.
Tested on Q3_K_L, t 1.04.
Repository: localaiLicense: gemma
genericrpv3-4b
Model's part of the GRP / GenericRP series, that's V3 based on Gemma3 4B, licensed accordingly.
It's a simple merge. To see intended behavious, see V2 or sum, card's more detailed.
allura-org/Gemma-3-Glitter-4B: w0.5
huihui-ai/gemma-3-4b-it-abliterated: w0.25
Danielbrdz/Barcenas-4b: w0.25
Happy chatting or whatever.
Repository: localaiLicense: gemma
comet_12b_v.5-i1
This is a merge of pre-trained language models
V.4 wasn't stable enough for me, so here V.5 is.
More stable, better at sfw, richer nsfw.
I find that best "AIO" settings for RP on gemma 3 is sleepdeprived3/Gemma3-T4 with little tweaks, (T 1.04, top p 0.95).
Repository: localaiLicense: gemma
nightwing3-10b-v0.1
Base model: (Falcon3-10B)
Repository: localaiLicense: falcon-llm
virtuoso-lite
Virtuoso-Lite (10B) is our next-generation, 10-billion-parameter language model based on the Llama-3 architecture. It is distilled from Deepseek-v3 using ~1.1B tokens/logits, allowing it to achieve robust performance at a significantly reduced parameter count compared to larger models. Despite its compact size, Virtuoso-Lite excels in a variety of tasks, demonstrating advanced reasoning, code generation, and mathematical problem-solving capabilities.
Repository: localaiLicense: falcon-llm
l3.3-ms-evayale-70b
This model was created as I liked the storytelling of EVA but the prose and details of scenes from EURYALE, my goal is to merge the robust storytelling of both models while attempting to maintain the positives of both models.
Repository: localaiLicense: llama3.3
l3.3-ms-evalebis-70b
This model was created as I liked the storytelling of EVA, the prose and details of scenes from EURYALE and Anubis, my goal is to merge the robust storytelling of all three models while attempting to maintain the positives of the models.
Repository: localaiLicense: llama3.3
negative-anubis-70b-v1
Enjoyed SicariusSicariiStuff/Negative_LLAMA_70B but the prose was too dry for my tastes. So I merged it with TheDrummer/Anubis-70B-v1 for verbosity. Anubis has positivity bias so Negative could balance things out.
This is a merge of pre-trained language models created using mergekit.
The following models were included in the merge:
SicariusSicariiStuff/Negative_LLAMA_70B
TheDrummer/Anubis-70B-v1
Repository: localaiLicense: llama3.3
Page 1