Thox-ai

ThoxForge-7B

README

License: apache-2.0

Summary

ThoxForge-7B is THOX's code-oriented assistant model: a LoRA fine-tune (rank 8) published as an adapter with a bundled Q4_K_M GGUF for direct use. This repo holds the runnable artifact; the separate ThoxForge-7B-GGUF repo is a placeholder with no weights.

Highlights

ThoxForge-7B is THOX's code-oriented assistant model: a LoRA fine-tune (rank 8) published as an adapter with a bundled Q4_K_M GGUF for direct use.
Bundled GGUF (Ollama) bash ollama run Thox-ai/thoxforge-7b

Specifications

Table

Base model	mistralai/Mistral-7B-Instruct-v0.3
Parameters	7B
Formats	Safetensors weights · GGUF: Q4_K_M · LoRA adapter files
Training	LoRA fine-tune (rank 8) published as an adapter with a bundled Q4_K_M GGUF for direct use
License	Apache-2.0. The THOX fine-tune and additions in this repo are covered under Apache-2.0; see the license text for terms.
This repository contains	LoRA adapter (safetensors), the bundled Q4_K_M GGUF (the full runnable build), and tokenizer in this repo

Files

Table with columns: File, Size, SHA-256
File	Size	SHA-256
`adapter_model.safetensors`	83,945,296 B	`89a24a33339c8b177123860912c3f144e054af4355d17e124bd7fc5c98b9a737`
`thoxforge-7b-Q4_K_M.gguf`	4,372,812,160 B	`c360ea661231df0f6c907a2c79254323bd42c5b27bc3228f904c0055dbc95a33`

Run it

Bundled GGUF (Ollama)

bash

ollama run Thox-ai/thoxforge-7b

Bundled GGUF (llama.cpp)

bash

hf download Thox-ai/ThoxForge-7B --include '*.gguf' --local-dir ./ThoxForge-7Bllama-cli -m ./ThoxForge-7B/thoxforge-7b-Q4_K_M.gguf -p "Hello" -n 128

Adapter (Transformers + PEFT)

Load the base model named in this card's metadata, then attach the adapter from this repo:

python

from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = "<base model named in this card's metadata>"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")model = PeftModel.from_pretrained(model, "Thox-ai/ThoxForge-7B")

Chat template: <s>[INST] {prompt} [/INST]

Platforms

Table with columns: Platform / device, Run path
Platform / device	Run path
Ollama (laptop / desktop)	`ollama run Thox-ai/thoxforge-7b`
Hugging Face	Download the builds listed under Files from this repo (see Run it)

Use with ThoxOS

ThoxOS loads this model as a host-class assistant through its local model runtime. Serve the bundled GGUF with Ollama on the ThoxOS host:

bash

ollama run Thox-ai/thoxforge-7b

ThoxOS points its chat and agent surfaces at the local Ollama endpoint (http://localhost:11434); no cloud account is required and prompts stay on the machine.

Use with MeshStack

On a MeshStack node, pull the model once and serve it to the rest of your mesh:

bash

ollama pull Thox-ai/thoxforge-7bollama serve

Other devices on the same mesh reach it through the node's OpenAI-compatible endpoint (http://<node>:11434/v1). The adapter form can equally be served from the Hugging Face files with llama.cpp:

bash

hf download Thox-ai/ThoxForge-7B --include '*.gguf' --local-dir ./ThoxForge-7Bllama-cli -m ./ThoxForge-7B/thoxforge-7b-Q4_K_M.gguf -p "Hello" -n 128

Intended use

Code-oriented and general text generation on hosts and edge machines within the THOX stack.
Not a safety-aligned public assistant unless deployed behind THOX guardrails.
Out of scope: medical, legal, financial, safety-critical, or other high-stakes decisions without human review; unattended control of physical devices without a confirmation step.

Training data and procedure

THOX fine-tune of mistralai/Mistral-7B-Instruct-v0.3. The corpus and procedure are described in this card as published at release (see Summary and Evaluation); no training beyond what this card describes is claimed for this repository.

Evaluation

No THOX GATE49 result is published for this model.

Limitations

No evaluation artifact or training log is published for this model; no quality figure is claimed.
Quantized and adapter models make factual mistakes and can produce confident but wrong output; verify important answers.
Behaviour and bias reflect the training data, which is mostly English; quality in other languages is lower.
Quantization trades accuracy for size.
Not qualified on THOX device hardware; sized for hosts with at least 8 GB RAM.

Provenance

Published by THOX.ai as Thox-ai/ThoxForge-7B. Upstream base: mistralai/Mistral-7B-Instruct-v0.3. This card was conformed to THOX Model Card Standard v1.0 on 2026-10-31 (frontmatter, tags, header, files, and section structure); the technical content is as published at release.

License

Apache-2.0. The THOX fine-tune and additions in this repo are covered under Apache-2.0; see the license text for terms.

THOX.ai — Your AI. Your Data. Your Rules.™

Citation

bibtex

@misc{thoxai2026thoxforge7b,      title={ThoxForge-7B},      author={THOX.ai},      year={2026},      url={https://huggingface.co/Thox-ai/ThoxForge-7B}}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

Thox-ai

Model Tree

Base

mistralai/Mistral-7B-Instruct-v0.3

Adapter

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Summary

Highlights

ThoxForge-7B is THOX's code-oriented assistant model: a LoRA fine-tune (rank 8) published as an adapter with a bundled Q4_K_M GGUF for direct use.
Bundled GGUF (Ollama) bash ollama run Thox-ai/thoxforge-7b

Specifications

Table

Base model	mistralai/Mistral-7B-Instruct-v0.3
Parameters	7B
Formats	Safetensors weights · GGUF: Q4_K_M · LoRA adapter files
Training	LoRA fine-tune (rank 8) published as an adapter with a bundled Q4_K_M GGUF for direct use
License	Apache-2.0. The THOX fine-tune and additions in this repo are covered under Apache-2.0; see the license text for terms.
This repository contains	LoRA adapter (safetensors), the bundled Q4_K_M GGUF (the full runnable build), and tokenizer in this repo

Files

Table with columns: File, Size, SHA-256
File	Size	SHA-256
`adapter_model.safetensors`	83,945,296 B	`89a24a33339c8b177123860912c3f144e054af4355d17e124bd7fc5c98b9a737`
`thoxforge-7b-Q4_K_M.gguf`	4,372,812,160 B	`c360ea661231df0f6c907a2c79254323bd42c5b27bc3228f904c0055dbc95a33`

Run it

Bundled GGUF (Ollama)

bash

ollama run Thox-ai/thoxforge-7b

Bundled GGUF (llama.cpp)

bash

hf download Thox-ai/ThoxForge-7B --include '*.gguf' --local-dir ./ThoxForge-7Bllama-cli -m ./ThoxForge-7B/thoxforge-7b-Q4_K_M.gguf -p "Hello" -n 128

hf download Thox-ai/ThoxForge-7B --include '*.gguf' --local-dir ./ThoxForge-7Bllama-cli -m ./ThoxForge-7B/thoxforge-7b-Q4_K_M.gguf -p "Hello" -n 128

Adapter (Transformers + PEFT)

Load the base model named in this card's metadata, then attach the adapter from this repo:

python

from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = "<base model named in this card's metadata>"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")model = PeftModel.from_pretrained(model, "Thox-ai/ThoxForge-7B")

from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = "<base model named in this card's metadata>"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")model = PeftModel.from_pretrained(model, "Thox-ai/ThoxForge-7B")

Chat template: <s>[INST] {prompt} [/INST]

Platforms

Table with columns: Platform / device, Run path
Platform / device	Run path
Ollama (laptop / desktop)	`ollama run Thox-ai/thoxforge-7b`
Hugging Face	Download the builds listed under Files from this repo (see Run it)

Use with ThoxOS

ThoxOS loads this model as a host-class assistant through its local model runtime. Serve the bundled GGUF with Ollama on the ThoxOS host:

bash

ollama run Thox-ai/thoxforge-7b

ThoxOS points its chat and agent surfaces at the local Ollama endpoint (http://localhost:11434); no cloud account is required and prompts stay on the machine.

Use with MeshStack

On a MeshStack node, pull the model once and serve it to the rest of your mesh:

bash

ollama pull Thox-ai/thoxforge-7bollama serve

ollama pull Thox-ai/thoxforge-7bollama serve

Other devices on the same mesh reach it through the node's OpenAI-compatible endpoint (http://<node>:11434/v1). The adapter form can equally be served from the Hugging Face files with llama.cpp:

bash

hf download Thox-ai/ThoxForge-7B --include '*.gguf' --local-dir ./ThoxForge-7Bllama-cli -m ./ThoxForge-7B/thoxforge-7b-Q4_K_M.gguf -p "Hello" -n 128

hf download Thox-ai/ThoxForge-7B --include '*.gguf' --local-dir ./ThoxForge-7Bllama-cli -m ./ThoxForge-7B/thoxforge-7b-Q4_K_M.gguf -p "Hello" -n 128

Intended use

Code-oriented and general text generation on hosts and edge machines within the THOX stack.
Not a safety-aligned public assistant unless deployed behind THOX guardrails.
Out of scope: medical, legal, financial, safety-critical, or other high-stakes decisions without human review; unattended control of physical devices without a confirmation step.

Training data and procedure

Evaluation

No THOX GATE49 result is published for this model.

Limitations

No evaluation artifact or training log is published for this model; no quality figure is claimed.
Quantized and adapter models make factual mistakes and can produce confident but wrong output; verify important answers.
Behaviour and bias reflect the training data, which is mostly English; quality in other languages is lower.
Quantization trades accuracy for size.
Not qualified on THOX device hardware; sized for hosts with at least 8 GB RAM.

Provenance

License

Apache-2.0. The THOX fine-tune and additions in this repo are covered under Apache-2.0; see the license text for terms.

THOX.ai — Your AI. Your Data. Your Rules.™

Citation

bibtex

@misc{thoxai2026thoxforge7b,      title={ThoxForge-7B},      author={THOX.ai},      year={2026},      url={https://huggingface.co/Thox-ai/ThoxForge-7B}}

@misc{thoxai2026thoxforge7b,      title={ThoxForge-7B},      author={THOX.ai},      year={2026},      url={https://huggingface.co/Thox-ai/ThoxForge-7B}}