Instructions to use Frankenstein-Labs/cortex.6.sol with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Frankenstein-Labs/cortex.6.sol with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Frankenstein-Labs/cortex.6.sol")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Frankenstein-Labs/cortex.6.sol")
model = AutoModelForCausalLM.from_pretrained("Frankenstein-Labs/cortex.6.sol", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Frankenstein-Labs/cortex.6.sol with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Frankenstein-Labs/cortex.6.sol"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Frankenstein-Labs/cortex.6.sol",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Frankenstein-Labs/cortex.6.sol

SGLang

How to use Frankenstein-Labs/cortex.6.sol with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Frankenstein-Labs/cortex.6.sol" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Frankenstein-Labs/cortex.6.sol",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Frankenstein-Labs/cortex.6.sol" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Frankenstein-Labs/cortex.6.sol",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Frankenstein-Labs/cortex.6.sol with Docker Model Runner:
```
docker model run hf.co/Frankenstein-Labs/cortex.6.sol
```

openhands openhands commited on 24 days ago

Commit

e1985ae

1 Parent(s): 8fd8333

docs(cortex): trim redundant model card tags

Browse files

Drop tags that duplicate Hub metadata or each other (cortex-ai, frankenstein-labs,
reasoning, long-context, fp8). Keep base_model and license: mit because the weights
are still the byte-identical upstream files, so the parent relation and the MIT
attribution remain factually and legally required.

Co-authored-by: openhands <openhands@all-hands.dev>

Files changed (2) hide show

AGENTS.md +12 -3
README.md +0 -5

AGENTS.md CHANGED Viewed

@@ -13,9 +13,18 @@ or repeat claims that turn out to be wrong.
   product. The base model is named only in the frontmatter `base_model` key, in the technical
   overview (architecture names) and in the "Provenance, license and attribution" section. Do not
   move that attribution back into the opening or drop it — the MIT license requires it.
-- Card frontmatter `tags` were changed from `francophone`/`afrique` to `cortex`, `cortex-ai`,
-  `frankenstein-labs`, `code-generation`, `web-development`, `software-engineering`. `base_model`
-  and `license: mit` are unchanged, and the Hub still derives `base_model:quantized:...`.
 - All 66 `model-*.safetensors` shards plus `model.safetensors.index.json` have SHA-256
   **identical to upstream** (67/67 LFS objects match). Verified via the HF tree API.
 - There is no `git-lfs` binary in this image. Fetch weights as pointer files only:

   product. The base model is named only in the frontmatter `base_model` key, in the technical
   overview (architecture names) and in the "Provenance, license and attribution" section. Do not
   move that attribution back into the opening or drop it — the MIT license requires it.
+- Card frontmatter `tags` were cleaned up to the minimum that adds signal: `cortex`,
+  `text-generation`, `code-generation`, `web-development`, `software-engineering`, `moe`.
+  Removed as redundant with the Hugging Face metadata or with each other: `cortex-ai` (repo
+  slug), `frankenstein-labs` (namespace), `reasoning` / `long-context` (already implied by
+  `text-generation` + the architecture), `fp8` (already exposed by the Hub as `8-bit` from
+  `config.json`). Hub-derived tags (`transformers`, `safetensors`, `deepseek_v4`, `8-bit`,
+  `endpoints_compatible`, `region:us`) come from `config.json` and cannot be removed from the
+  card.
+- `base_model: deepseek-ai/DeepSeek-V4-Pro-0813` and `license: mit` are **kept on purpose**.
+  The 67 LFS objects are byte-identical to upstream, so the parent relationship is factual and
+  the MIT attribution is legally required. Do not remove either without evidence that the
+  weights were replaced by independently trained ones.
 - All 66 `model-*.safetensors` shards plus `model.safetensors.index.json` have SHA-256
   **identical to upstream** (67/67 LFS objects match). Verified via the HF tree API.
 - There is no `git-lfs` binary in this image. Fetch weights as pointer files only:

README.md CHANGED Viewed

@@ -9,16 +9,11 @@ pipeline_tag: text-generation
 base_model: deepseek-ai/DeepSeek-V4-Pro-0813
 tags:
 - cortex
-- cortex-ai
-- frankenstein-labs
 - text-generation
 - code-generation
 - web-development
 - software-engineering
-- reasoning
-- long-context
 - moe
-- fp8
 ---
 # CORTEX

 base_model: deepseek-ai/DeepSeek-V4-Pro-0813
 tags:
 - cortex
 - text-generation
 - code-generation
 - web-development
 - software-engineering
 - moe
 ---
 # CORTEX