Text Generation
Transformers
Safetensors
MLX
code
llama
fill-in-the-middle
multi-token-prediction
speculative-decoding
apple-silicon
text-generation-inference
Instructions to use philipjohnbasile/wisp-coder-110m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use philipjohnbasile/wisp-coder-110m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="philipjohnbasile/wisp-coder-110m")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("philipjohnbasile/wisp-coder-110m") model = AutoModelForCausalLM.from_pretrained("philipjohnbasile/wisp-coder-110m", device_map="auto") - MLX
How to use philipjohnbasile/wisp-coder-110m with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("philipjohnbasile/wisp-coder-110m") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- vLLM
How to use philipjohnbasile/wisp-coder-110m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "philipjohnbasile/wisp-coder-110m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "philipjohnbasile/wisp-coder-110m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/philipjohnbasile/wisp-coder-110m
- SGLang
How to use philipjohnbasile/wisp-coder-110m 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 "philipjohnbasile/wisp-coder-110m" \ --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": "philipjohnbasile/wisp-coder-110m", "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 "philipjohnbasile/wisp-coder-110m" \ --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": "philipjohnbasile/wisp-coder-110m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - MLX LM
How to use philipjohnbasile/wisp-coder-110m with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "philipjohnbasile/wisp-coder-110m" --prompt "Once upon a time"
- Docker Model Runner
How to use philipjohnbasile/wisp-coder-110m with Docker Model Runner:
docker model run hf.co/philipjohnbasile/wisp-coder-110m
- Atomic Chat
Commit History
-
Give the Wisp Fieldbook room to grow
Verified signatureUse bounded fit-content sizing to reclaim the model-card right gutter on larger screens, with a full-width mobile fallback. Contain the architecture flower float, restore the two-column runtime comparison, and add an illustrated guide to the twelve trunk layers and shared MTP block. Preserve all scientific text, six original code examples, metadata, links, and thirteen default-open panels. Reviewed the complete sanitized desktop and mobile previews.ad6d201 -
Unify the Wisp Fieldbook into a continuous illustrated page
Verified signatureReplace the fragmented card layout with one paper canvas, a continuous chapter line, borderless editorial sections, integrated botanical artwork and an inline chapter index. Preserve hover behavior and default all 13 research panels to open. Retain every original technical paragraph, table entry, code block, metadata field, link and section anchor. Verified the complete Hugging Face Preview at desktop reading width and 390px mobile width, with no horizontal overflow and six native code blocks.b4dae39 -
Open all Fieldbook panels by default
Verified signatureDefault all 13 details panels to open. Remove exclusive grouping from the three FIM panels so they can stay open together, and update the expansion hints. Each panel can still be collapsed individually.a4a24e8 -
Create the interactive Wisp Fieldbook
Verified signatureGive the model card its own Mind the gap identity with botanical hover motion, responsive navigation and release-route cards, three interactive FIM prompt panels, six specimen notes, and native fold-out research sections. Use Hugging Face-supported CSS utilities and semantic details/summary controls. Preserve every original technical statement, code block, result, metadata field, link and section anchor. Verified hover styles, keyboard toggles, reduced-motion duration and mobile overflow in the complete card preview; corrected explicit repository file links.fb6c6dd -
Add visual FIM guide and editorial research cards
Verified signatureExtend the floral model-card design with a responsive prefix/middle/suffix illustration, six paper-style fact cards, and an evidence overview. Fit the hero heading to the model page column. Preserve original technical content, metadata, code blocks, links and section anchors. Reviewed the full merged card in Hugging Face Preview at desktop reading width and mobile width.1fa32f7 -
Bring the Wisp garden identity to the model card
Verified signatureAdd a responsive floral introduction, section signposts and footer using the original Wisp Space artwork. Preserve all technical text, code examples, evaluation results, metadata and existing links. Model weights, tokenizer, runtime and evidence files are unchanged. Validated the complete card in Hugging Face Preview and checked mobile layout.b8df715
-
Clarify release scope and connect the model portfolio
Verified signatureAdd model-guide navigation and evidence-scoped artifact information. Correct applicable links, size units, runtime status, or unsupported comparisons. Preserve weights and original evaluation receipts. Wisp refreshes only the README entry in its active export manifest.5919d57 -
Add a practical start guide with runtime, memory, attribution, and evidence scope
Verified signatureAdd the CPU demo and a pinned quick start. Require the existing NOTICE file in the strict package allowlist, and update the README/runtime-source manifest hashes. All weight, tokenizer, checkpoint, and evaluation hashes are unchanged. Verified the package and confirmed that README and NOTICE tampering is rejected.6ca84fe
-
Add registered competitive short-hole FIM v1 evidence (null result)
Verified signature186479f -
Publish audited Wisp Coder 110M release
Verified signatureAtomic package from the local schema-2 release audit aeecb3ba42b6e3d930c041b5a5a70a37a0e3873dcb247daf799166e1401003dd. Publication attempt nonce: a6ac020a5928cb18a4ae903ef8ef9654c23ad774611877429f0a4defbff90a4f Payload manifest SHA-256: 773d4ba114f47bd52f4d346472b856eac50a5f97ff14a45faa45ac66ed86e15d Expected parent commit: a9bb1bd2923d57cb17be3d7f772c052f53e2acaa818282c -
Clear prior rendered model card before superseding publication
Verified signaturea9bb1bd -
Clear prior release revision payload for superseding publication
Verified signature76becf5 -
Publish audited Wisp Coder 110M release
Verified signatureAtomic package from the local schema-2 release audit fc6f647bbba23139e993783323f5258178e293a9fded9dd194ff135516c88f91. Publication attempt nonce: 2a406476e65c4cde6a8f04ae4ff84f30e6bab32a0f1cfef4c948ab04366fba98 Payload manifest SHA-256: 11bdcf700eb4b68d6eff008f49c08a4fbbd94cff1687397c92e3a4cfc50c450d Expected parent commit: 194f16470ace0d0b8113438a20f6d04ab03916f65c724af -
Remove namespace-reservation placeholder before audited release publication
Verified signature194f164
-
Upload README.md with huggingface_hub
Verified signature43a8306 -
initial commit
Verified signature9221a23