Instructions to use dcostenco/prism-coder-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dcostenco/prism-coder-8b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dcostenco/prism-coder-8b",
	filename="prism-aac-8b-q4km.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use dcostenco/prism-coder-8b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dcostenco/prism-coder-8b
# Run inference directly in the terminal:
llama-cli -hf dcostenco/prism-coder-8b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dcostenco/prism-coder-8b
# Run inference directly in the terminal:
llama-cli -hf dcostenco/prism-coder-8b

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf dcostenco/prism-coder-8b
# Run inference directly in the terminal:
./llama-cli -hf dcostenco/prism-coder-8b

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf dcostenco/prism-coder-8b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dcostenco/prism-coder-8b

Use Docker

docker model run hf.co/dcostenco/prism-coder-8b

LM Studio
Jan
Ollama
How to use dcostenco/prism-coder-8b with Ollama:
```
ollama run hf.co/dcostenco/prism-coder-8b
```

Unsloth Studio

How to use dcostenco/prism-coder-8b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for dcostenco/prism-coder-8b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for dcostenco/prism-coder-8b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dcostenco/prism-coder-8b to start chatting

How to use dcostenco/prism-coder-8b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf dcostenco/prism-coder-8b

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "dcostenco/prism-coder-8b"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dcostenco/prism-coder-8b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf dcostenco/prism-coder-8b

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default dcostenco/prism-coder-8b

Run Hermes

hermes

Docker Model Runner
How to use dcostenco/prism-coder-8b with Docker Model Runner:
```
docker model run hf.co/dcostenco/prism-coder-8b
```

Lemonade

How to use dcostenco/prism-coder-8b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dcostenco/prism-coder-8b

Run and chat with the model

lemonade run user.prism-coder-8b-{{QUANT_TAG}}

List all available models

lemonade list

dcostenco commited on 21 days ago

Commit

395cd09

verified ·

1 Parent(s): 8cfe73e

Update model card: add v31 (95.1% BFCL, smem/know boundary fix)

Browse files

Files changed (1) hide show

README.md +38 -36

README.md CHANGED Viewed

@@ -1,56 +1,58 @@
 ---
 language: en
 license: apache-2.0
-base_model: Qwen/Qwen3-8B
 tags:
-  - tool-calling
-  - routing
-  - aac
   - gguf
 ---
-# prism-coder:8b — AAC Tool Router (8B)
-Fine-tuned from **Qwen3-8B** for deterministic tool routing in the [Prism AAC](https://github.com/dcostenco/prism-aac) system.
-**BFCL accuracy: 95%** on 100-case × 3 seeds routing benchmark (v30 corpus).
-## What it does
-Routes user messages to one of 6 tools or plain text. Intermediate quality tier in the desktop cascade (14B → 32B → cloud). 8B is retained as an **iOS/edge** tier for 8GB-RAM devices where 14B does not fit.
-| Tool | Trigger |
-|------|---------|
-| `session_load_context` | Load/fetch context for project X |
-| `session_save_ledger` | Note / jot down / log / remember |
-| `session_save_handoff` | Handoff to next agent / pass on |
-| `session_compact_ledger` | Compact/archive/trim the ledger |
-| `session_search_memory` | What did we discuss / recall session |
-| `knowledge_search` | What do I know / stored notes |
-| *(plain text)* | AAC phrases, math, facts, translation, time |
-## Deployment
-```bash
-ollama run dcostenco/prism-coder:8b-v30
-```
-## Files
-| File | Size | Format |
-|------|------|--------|
-| `prism-coder-8b-v30-q4km.gguf` | 4.7 GB | Q4_K_M GGUF (v30, recommended) |
-| `prism-aac-8b-q4km.gguf` | 5.0 GB | Q4_K_M GGUF (legacy v29) |
-## Training
-- **Base**: Qwen3-8B
-- **Method**: MLX LoRA fine-tuning (mlx_lm.lora)
-- **Dataset**: v36_1b7 routing corpus (6-tool system prompt)
-- **Hardware**: Apple Silicon (M-series)
-- **Eval**: BFCL 100-case benchmark → **95%**
-## Cascade position
-Desktop cascade: **14B → 32B → cloud Claude**
-iOS cascade: **8B** (primary offline tier for 8GB-RAM devices)

 ---
 language: en
 license: apache-2.0
 tags:
+  - tool-routing
+  - function-calling
+  - prism-aac
+  - qwen3
   - gguf
+base_model: Qwen/Qwen3-8B
 ---
+# prism-coder:8b — Tool Routing Model (iOS Tier)
+Fine-tuned Qwen3-8B for 6-tool routing in the Prism AAC system.
+Primary deployment: **iOS/edge** via llama.cpp GGUF.
+## Versions
+| Version | File | BFCL | Notes |
+|---------|------|------|-------|
+| v31 | `qwen3-8b-v31-q4km.gguf` | 95.1% | Surgical smem/know boundary + save fixes |
+| v30 | `qwen3-8b-v30-q4km.gguf` | 95.0% | Routing corpus v36_1b7 |
+## BFCL Routing Benchmark (v31)
+- **95.1%** — 3-seed mean (seeds 2027/2028/2029), 100 cases each
+- Eval: MLX inference, greedy (temp=0), Qwen3 thinking suppressed
+- Gate: ≥90% = deploy
+## Tools
+1. `session_load_context` — load/fetch/resume project context
+2. `session_save_ledger` — note/log/remember/record
+3. `session_save_handoff` — handoff/relay/next-agent transition
+4. `session_compact_ledger` — compact/archive ledger
+5. `session_search_memory` — recall past sessions/conversations
+6. `knowledge_search` — search stored notes/knowledge base
+## Cascade Role
+iOS fallback tier. Desktop cascade uses 14B → 32B → cloud Claude.
+8B handles edge/offline scenarios where RAM < 6GB.
+## Usage (Ollama)
+```bash
+ollama pull dcostenco/prism-coder:8b-v30
+ollama run dcostenco/prism-coder:8b-v30
+```
+## Training
+- Base: `Qwen3-8B` (MLX 4-bit)
+- Framework: MLX-LM LoRA (8 layers, batch 2, grad-checkpoint)
+- v31 data: 361 train / 41 valid (targeted smem/know boundary augmentations)
+- v31 LR: 3e-6 (surgical, 200 iters)
+- Peak memory: 7.0 GB