Thox-ai
/

README

Model card Files Files and versions

xet

Community

tommytracx commited on Aug 5

Commit

2be8ad7

verified ·

1 Parent(s): 7dbef2b

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +77 -76

README.md CHANGED Viewed

@@ -1,76 +1,77 @@
----
-title: THOX.ai
----
-# THOX.ai
-Edge and on-device language models. We build small models that run on hardware
-people actually own — laptops, USB sticks, single-board computers, and
-microcontrollers.
-**13 models are published here.** Everything listed below is real and
-downloadable; nothing on this page links to a repository you cannot open.
----
-## Open — no access request
-| model | what it is | size |
-|---|---|---|
-| [**ThoxMicro-1bit-9M**](https://huggingface.co/Thox-ai/ThoxMicro-1bit-9M) | BitNet b1.58 **ternary** LM, trained from scratch. Writes children's stories; not an assistant. Research artifact for microcontroller-class targets. | 6.3 MB |
-| [**thox-micro-125m**](https://huggingface.co/Thox-ai/thox-micro-125m) · [GGUF](https://huggingface.co/Thox-ai/thox-micro-125m-GGUF) | 123.6M base LM trained from scratch. Completion only. | 81–247 MB |
-| [**ThoxSpeech-ASR-BitNet**](https://huggingface.co/Thox-ai/ThoxSpeech-ASR-BitNet) | BitNet speech recognition, redistributed byte-identical with published SHA-256. | 0.7–1.0 GB |
-## Access-gated
-Adapters and derived models. Request access on the model page.
-| model | base | type |
-|---|---|---|
-| [ThoxMini-3B](https://huggingface.co/Thox-ai/ThoxMini-3B) | Llama-3.2-3B-Instruct | LoRA + GGUF |
-| [ThoxForge-7B](https://huggingface.co/Thox-ai/ThoxForge-7B) | Mistral-7B-Instruct-v0.3 | LoRA + GGUF |
-| [ThoxGlobal-7B](https://huggingface.co/Thox-ai/ThoxGlobal-7B) | Qwen2.5-7B-Instruct | LoRA + GGUF |
-| [ThoxWave-8B](https://huggingface.co/Thox-ai/ThoxWave-8B) | Llama-3.1-8B | LoRA + GGUF |
-| [ThoxNova-12B-Core](https://huggingface.co/Thox-ai/ThoxNova-12B-Core) · [Agent](https://huggingface.co/Thox-ai/ThoxNova-12B-Agent) | Gemma-4-12B-it | LoRA + GGUF |
-| [fable5-agentic-qwen2.5-14b-lora](https://huggingface.co/Thox-ai/fable5-agentic-qwen2.5-14b-lora) | Qwen2.5-14B-Instruct | QLoRA adapter |
-> **On the adapter cards:** these were trained against `unsloth/*-bnb-4bit`
-> re-uploads of the listed bases, not the original repositories. Several cards
-> still name the original in frontmatter. Treat the base as "the unsloth 4-bit
-> re-upload of the listed model" until the cards are corrected.
-## Documentation-only
-These contain **no weights**, deliberately, and say so on their own pages:
-- [ThoxForge-7B-GGUF](https://huggingface.co/Thox-ai/ThoxForge-7B-GGUF) — the
-  quantized build did not pass our factuality gate; publishing it anyway to make
-  the repo look complete would route around that control.
-- [ThoxWebby-Gemma-4-E2B](https://huggingface.co/Thox-ai/ThoxWebby-Gemma-4-E2B) —
-  the browser app pulls upstream weights; we do not re-host them.
----
-## Where our models run
-- **Ollama** — [`ollama.com/thox-ai`](https://ollama.com/thox-ai)
-- **llama.cpp** — every GGUF above
-- **ThoxKey / ThoxKey Pro** — USB sticks that carry a model set and a local runtime
-- **ThoxMicro / ThoxOS devices** — ESP32-S3 and Raspberry Pi class hardware
-## How we publish
-- **Measured, not estimated.** Numbers on our cards come from runs we did. Where
-  a figure is inherited from an upstream benchmark, the card says so.
-- **Negative results ship too.** ThoxMicro-1bit-9M's card leads with the fact
-  that ternary quantization costs it 21.4% perplexity, and that the penalty grew
-  rather than shrank with more training data.
-- **Empty is better than misleading.** A repo with no weights and an honest
-  explanation beats one with weights that failed their gate.
-- **Licence honesty.** Where downstream terms are genuinely unsettled we say
-  `license: other` and explain, rather than picking a permissive licence because
-  it is convenient.
-## Contact
-[thox.ai](https://thox.ai)

+---
+title: THOX.ai
+---
+# THOX.ai
+Edge and on-device language models. We build small models that run on hardware
+people actually own — laptops, USB sticks, single-board computers, and
+microcontrollers.
+**13 models are published here.** Everything listed below is real and
+downloadable; nothing on this page links to a repository you cannot open.
+---
+## Open — no access request
+| model | what it is | size |
+|---|---|---|
+| [**ThoxMicro-1bit-9M**](https://huggingface.co/Thox-ai/ThoxMicro-1bit-9M) | BitNet b1.58 **ternary** LM, trained from scratch. Writes children's stories; not an assistant. Research artifact for microcontroller-class targets. | 6.3 MB |
+| [**thox-micro-125m**](https://huggingface.co/Thox-ai/thox-micro-125m) · [GGUF](https://huggingface.co/Thox-ai/thox-micro-125m-GGUF) | 123.6M base LM trained from scratch. Completion only. | 81–247 MB |
+| [**ThoxSpeech-ASR-BitNet**](https://huggingface.co/Thox-ai/ThoxSpeech-ASR-BitNet) | BitNet speech recognition, redistributed byte-identical with published SHA-256. | 0.7–1.0 GB |
+## Access-gated
+Adapters and derived models. Request access on the model page.
+| model | base | type |
+|---|---|---|
+| [ThoxMini-3B](https://huggingface.co/Thox-ai/ThoxMini-3B) | Llama-3.2-3B-Instruct | LoRA + GGUF |
+| [ThoxForge-7B](https://huggingface.co/Thox-ai/ThoxForge-7B) | Mistral-7B-Instruct-v0.3 | LoRA + GGUF |
+| [ThoxGlobal-7B](https://huggingface.co/Thox-ai/ThoxGlobal-7B) | Qwen2.5-7B-Instruct | LoRA + GGUF |
+| [ThoxWave-8B](https://huggingface.co/Thox-ai/ThoxWave-8B) | dolphin-2.9-llama3-8b | LoRA + GGUF |
+| [ThoxNova-12B-Core](https://huggingface.co/Thox-ai/ThoxNova-12B-Core) · [Agent](https://huggingface.co/Thox-ai/ThoxNova-12B-Agent) | Gemma-4-12B-it | LoRA + GGUF |
+| [fable5-agentic-qwen2.5-14b-lora](https://huggingface.co/Thox-ai/fable5-agentic-qwen2.5-14b-lora) | Qwen2.5-14B-Instruct | QLoRA adapter |
+> **On the adapter bases:** ThoxMini, ThoxForge, ThoxGlobal and both ThoxNova
+> adapters were trained against `unsloth/*` re-uploads of the listed models, not
+> the original repositories. Each card's `base_model` now states the re-upload it
+> was actually trained on, with the upstream lineage recorded in the body.
+> ThoxWave-8B trains directly on `dphn/dolphin-2.9-llama3-8b`.
+## Documentation-only
+These contain **no weights**, deliberately, and say so on their own pages:
+- [ThoxForge-7B-GGUF](https://huggingface.co/Thox-ai/ThoxForge-7B-GGUF) — the
+  quantized build did not pass our factuality gate; publishing it anyway to make
+  the repo look complete would route around that control.
+- [ThoxWebby-Gemma-4-E2B](https://huggingface.co/Thox-ai/ThoxWebby-Gemma-4-E2B) —
+  the browser app pulls upstream weights; we do not re-host them.
+---
+## Where our models run
+- **Ollama** — [`ollama.com/thox-ai`](https://ollama.com/thox-ai)
+- **llama.cpp** — every GGUF above
+- **ThoxKey / ThoxKey Pro** — USB sticks that carry a model set and a local runtime
+- **ThoxMicro / ThoxOS devices** — ESP32-S3 and Raspberry Pi class hardware
+## How we publish
+- **Measured, not estimated.** Numbers on our cards come from runs we did. Where
+  a figure is inherited from an upstream benchmark, the card says so.
+- **Negative results ship too.** ThoxMicro-1bit-9M's card leads with the fact
+  that ternary quantization costs it 21.4% perplexity, and that the penalty grew
+  rather than shrank with more training data.
+- **Empty is better than misleading.** A repo with no weights and an honest
+  explanation beats one with weights that failed their gate.
+- **Licence honesty.** Where downstream terms are genuinely unsettled we say
+  `license: other` and explain, rather than picking a permissive licence because
+  it is convenient.
+## Contact
+[thox.ai](https://thox.ai)