Instructions to use dcostenco/prism-coder-1.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dcostenco/prism-coder-1.7b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dcostenco/prism-coder-1.7b",
	filename="prism-aac-1b7-q4km.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use dcostenco/prism-coder-1.7b 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-1.7b:Q8_0
# Run inference directly in the terminal:
llama-cli -hf dcostenco/prism-coder-1.7b:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dcostenco/prism-coder-1.7b:Q8_0
# Run inference directly in the terminal:
llama-cli -hf dcostenco/prism-coder-1.7b:Q8_0

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-1.7b:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf dcostenco/prism-coder-1.7b:Q8_0

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-1.7b:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dcostenco/prism-coder-1.7b:Q8_0

Use Docker

docker model run hf.co/dcostenco/prism-coder-1.7b:Q8_0

LM Studio
Jan
Ollama
How to use dcostenco/prism-coder-1.7b with Ollama:
```
ollama run hf.co/dcostenco/prism-coder-1.7b:Q8_0
```

Unsloth Studio new

How to use dcostenco/prism-coder-1.7b 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-1.7b 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-1.7b 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-1.7b to start chatting

Pi new

How to use dcostenco/prism-coder-1.7b 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-1.7b:Q8_0

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-1.7b:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dcostenco/prism-coder-1.7b 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-1.7b:Q8_0

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-1.7b:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use dcostenco/prism-coder-1.7b with Docker Model Runner:
```
docker model run hf.co/dcostenco/prism-coder-1.7b:Q8_0
```

Lemonade

How to use dcostenco/prism-coder-1.7b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dcostenco/prism-coder-1.7b:Q8_0

Run and chat with the model

lemonade run user.prism-coder-1.7b-Q8_0

List all available models

lemonade list

dcostenco commited on 8 days ago

Commit

8e12d5c

verified ·

1 Parent(s): 6ee010d

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +48 -53

README.md CHANGED Viewed

@@ -1,84 +1,79 @@
 ---
 language: en
 license: apache-2.0
-base_model: Qwen/Qwen3-1.7B
 tags:
   - tool-routing
   - function-calling
   - prism-aac
   - qwen3
   - gguf
 ---
-# prism-coder:1b7 — Tool Routing Model (Ultra-Compact / iOS Tier)
 Fine-tuned Qwen3-1.7B for 6-tool routing in the [Prism AAC](https://github.com/dcostenco/prism-aac) system.
-Primary deployment: **on-device iOS inference** via llama.cpp (1.1 GB GGUF, Q4_K_M).
-## BFCL Routing Benchmark — v41 (Current)
-**Mean: 96.1%** (3-seed average, seeds 2027/2028/2029, 102 cases each)
-| Category | Description | Accuracy |
-|----------|-------------|:--------:|
-| aac | AAC phrase requests → plain text | 100% |
-| cmpct | Ledger compaction | 83% |
-| edge | Multi-step / compound requests | 83% |
-| hand | Agent handoff / relay | 100% |
-| info | General facts → plain text | 100% |
-| irrel | Irrelevant / live queries → plain text | 90% |
-| know | Knowledge base search | 100% |
-| load | Session context loading | 89% |
-| pred | Factual / knowledge queries → plain text | 100% |
-| save | Session ledger save | 100% |
-| smem | Session memory search | 100% |
-| tran | Translation requests → plain text | 100% |
-Eval: Ollama inference, temperature=0, Qwen3 thinking suppressed (`<think>\n\n</think>`), num_predict=160.
 Gate: ≥90% = deploy.
 ## Version History
 | Version | BFCL | Notes |
 |---------|------|-------|
-| v41 | 96.1% | Current — routing corpus v41 |
-| v40 | ~95% | Routing corpus v40 |
-| v39 | ~94% | Routing corpus v39 |
-| v36 | 100% | Previous — routing corpus v36 (small eval set) |
 ## Tools
-The model routes between exactly 6 tools:
-1. `session_load_context` — load/fetch/resume project context
-2. `session_save_ledger` — note/log/remember/record progress
-3. `session_save_handoff` — handoff/relay to next agent/session
-4. `session_compact_ledger` — compact/archive/shrink ledger
-5. `session_search_memory` — recall past sessions/conversations
-6. `knowledge_search` — search stored notes/knowledge base
-## Files
-| File | Size | Use |
-|------|------|-----|
-| `prism-coder-1b7-v41-q4km.gguf` | 1.1 GB | Ollama / desktop |
-| `prism-aac-1b7-q4km.gguf` | 1.1 GB | iOS app download |
-## Cascade Role
-Ultra-compact iOS/edge tier. Desktop cascade: **1.7B → 8B → 14B → 32B → cloud Claude**.
-1.7B handles offline on-device routing where memory is tightly constrained (< 2 GB available).
-## Usage (Ollama)
 ```bash
-ollama run dcostenco/prism-coder:1b7
 ```
-## Training
-- **Base**: `Qwen/Qwen3-1.7B` (fp16, 1.7B params)
-- **Framework**: MLX-LM LoRA (rank=8, scale=20, 4 layers)
-- **Data**: v41 routing corpus
-- **Merge**: Direct safetensors manipulation (delta = scale/rank × B^T A^T)
-- **Peak memory**: ~4 GB (M-series Mac)

 ---
 language: en
 license: apache-2.0
 tags:
   - tool-routing
   - function-calling
   - prism-aac
   - qwen3
   - gguf
+base_model: Qwen/Qwen3-1.7B
 ---
+# prism-coder:1.7b — Tool Routing Model (Always-Fits Tier)
 Fine-tuned Qwen3-1.7B for 6-tool routing in the [Prism AAC](https://github.com/dcostenco/prism-aac) system.
+Primary deployment: **any iOS device** via llama.cpp GGUF — the guaranteed fallback for all device tiers.
+## BFCL Routing Benchmark — v42 (Current)
+**Mean: 100.0%** (3-seed average, seeds 2027/2028/2029, 102 cases each)
+| Category | Count | Description | Accuracy |
+|----------|------:|-------------|:--------:|
+| aac | 12 | AAC phrase requests → plain text | 100% |
+| cmpct | 6 | Ledger compaction | 100% |
+| edge | 6 | Multi-step / compound requests | 100% |
+| hand | 8 | Agent handoff / relay | 100% |
+| info | 5 | General facts → plain text | 100% |
+| irrel | 10 | Irrelevant / live queries → plain text | 100% |
+| know | 7 | Knowledge base search | 100% |
+| load | 9 | Session context loading | 100% |
+| pred | 8 | Factual / knowledge queries → plain text | 100% |
+| save | 13 | Session ledger save | 100% |
+| smem | 12 | Session memory search | 100% |
+| tran | 6 | Translation requests → plain text | 100% |
+Eval: MLX inference + thinking, temperature=0, 3-seed mean.
 Gate: ≥90% = deploy.
 ## Version History
 | Version | BFCL | Notes |
 |---------|------|-------|
+| v42 | **100.0%** | Fixed 4 deterministic failures: cmpct tool name, compound edge, write-code irrel, pull-context load |
+| v41 | 96.1% | Proper safetensors merge — fixes mlx_lm.fuse LoRA loss |
+| v36 | 94.1% | LoRA rank=16, all 28 layers, mask-prompt |
+| v19 | ~88% | Baseline 1.7B routing |
 ## Tools
+The model routes to exactly 6 tools:
+| Tool | Trigger |
+|------|---------|
+| `session_load_context` | Load/resume/pull project context |
+| `session_save_ledger` | Note/log/record/remember something |
+| `session_save_handoff` | Pass state to next agent/session |
+| `session_compact_ledger` | Compact/shrink/prune ledger |
+| `session_search_memory` | Recall prior session discussions |
+| `knowledge_search` | Search stored knowledge base ("what do I know") |
+Plain text (no tool) for: AAC phrases, translations, weather, general facts, code/regex/functions, math.
+## Model Details
+- **Base**: Qwen/Qwen3-1.7B
+- **Format**: GGUF Q4_K_M (~1.2 GB)
+- **Context**: 32,768 tokens
+- **Training**: MLX LoRA, rank=16, all 28 layers, 800 iters, LR=5e-5, v42 corpus (1028 train / 79 valid)
+- **Merge**: direct safetensors merge (scale/rank × B.T @ A.T) → llama.cpp convert → Q4_K_M quantization
+## Usage
 ```bash
+ollama pull dcostenco/prism-coder:1b7
+ollama run prism-coder:1b7
 ```
+Or in [Prism AAC](https://github.com/dcostenco/prism-aac) — the app downloads and loads this model automatically on devices with <8 GB RAM.