Instructions to use strykes/emberforge-3b-reasoner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use strykes/emberforge-3b-reasoner with Transformers:

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

pipe = pipeline("text-generation", model="strykes/emberforge-3b-reasoner")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("strykes/emberforge-3b-reasoner", dtype="auto")

PEFT
How to use strykes/emberforge-3b-reasoner with PEFT:
```
Task type is invalid.
```

llama-cpp-python

How to use strykes/emberforge-3b-reasoner with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="strykes/emberforge-3b-reasoner",
	filename="gguf/Nanbeige4.1-3B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use strykes/emberforge-3b-reasoner with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf strykes/emberforge-3b-reasoner:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf strykes/emberforge-3b-reasoner:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf strykes/emberforge-3b-reasoner:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf strykes/emberforge-3b-reasoner:Q4_K_M

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 strykes/emberforge-3b-reasoner:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf strykes/emberforge-3b-reasoner:Q4_K_M

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 strykes/emberforge-3b-reasoner:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf strykes/emberforge-3b-reasoner:Q4_K_M

Use Docker

docker model run hf.co/strykes/emberforge-3b-reasoner:Q4_K_M

LM Studio
Jan

vLLM

How to use strykes/emberforge-3b-reasoner with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "strykes/emberforge-3b-reasoner"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "strykes/emberforge-3b-reasoner",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/strykes/emberforge-3b-reasoner:Q4_K_M

SGLang

How to use strykes/emberforge-3b-reasoner 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 "strykes/emberforge-3b-reasoner" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "strykes/emberforge-3b-reasoner",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "strykes/emberforge-3b-reasoner" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "strykes/emberforge-3b-reasoner",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use strykes/emberforge-3b-reasoner with Ollama:
```
ollama run hf.co/strykes/emberforge-3b-reasoner:Q4_K_M
```

Unsloth Studio

How to use strykes/emberforge-3b-reasoner 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 strykes/emberforge-3b-reasoner 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 strykes/emberforge-3b-reasoner to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for strykes/emberforge-3b-reasoner to start chatting

How to use strykes/emberforge-3b-reasoner with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf strykes/emberforge-3b-reasoner:Q4_K_M

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": "strykes/emberforge-3b-reasoner:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use strykes/emberforge-3b-reasoner with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf strykes/emberforge-3b-reasoner:Q4_K_M

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 strykes/emberforge-3b-reasoner:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use strykes/emberforge-3b-reasoner with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf strykes/emberforge-3b-reasoner:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "strykes/emberforge-3b-reasoner:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use strykes/emberforge-3b-reasoner with Docker Model Runner:
```
docker model run hf.co/strykes/emberforge-3b-reasoner:Q4_K_M
```

Lemonade

How to use strykes/emberforge-3b-reasoner with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull strykes/emberforge-3b-reasoner:Q4_K_M

Run and chat with the model

lemonade run user.emberforge-3b-reasoner-Q4_K_M

List all available models

lemonade list

strykes commited on Feb 23

Commit

13c1865

verified ·

1 Parent(s): 47cd4e3

upload README.md

Browse files

Files changed (1) hide show

README.md +14 -38

README.md CHANGED Viewed

@@ -1,18 +1,14 @@
 ---
 language:
 - en
-- zh
 license: apache-2.0
 tags:
 - transformers
 - safetensors
-- llama.cpp
 - gguf
 - peft
 - qlora
 - reasoning
-- math
-- code
 base_model:
 - Nanbeige/Nanbeige4.1-3B
 library_name: transformers
@@ -21,47 +17,27 @@ pipeline_tag: text-generation
 # EmberForge-3B-Reasoner
-EmberForge-3B-Reasoner is a private finetuned Nanbeige 4.1 3B reasoning model release by `strykes`.
-## What is included
-This repo intentionally includes multiple artifact types:
-- **Merged full model (Safetensors)** at repo root (for Transformers / benchmark pipelines)
-- **LoRA adapter** in `adapter/`
-- **GGUF quants** in `gguf/`:
   - `Nanbeige4.1-3B-Q5_K_M.gguf`
   - `Nanbeige4.1-3B-Q4_K_M.gguf`
   - `Nanbeige4.1-3B-f16.gguf`
-## Training summary
-- Base model: `Nanbeige/Nanbeige4.1-3B`
-- Method: QLoRA with Unsloth, merged to full weights
-- Dataset: synthetic reasoning instruction dataset (`3500` samples)
-- Epochs: `2`
-- Effective batch size: `16` (batch 1 x grad acc 16)
-- Max sequence length: `4096`
-- Learning rate: `1e-4` with cosine schedule
-- Final reported training loss: `~1.28`
-## Quick usage (Transformers)
-```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-model_id = "strykes/emberforge-3b-reasoner"
-tok = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
-```
-## Quick usage (llama.cpp)
-Use files in `gguf/`, e.g. `Q5_K_M` for stronger quality or `Q4_K_M` for lower RAM.
 ## Notes
-- This is a finetuned model intended for research/benchmarking.
-- Follow upstream Nanbeige license and applicable usage policies.
-- Outputs can still contain errors; validate for critical tasks.

 ---
 language:
 - en
 license: apache-2.0
 tags:
 - transformers
 - safetensors
 - gguf
 - peft
 - qlora
 - reasoning
 base_model:
 - Nanbeige/Nanbeige4.1-3B
 library_name: transformers
 # EmberForge-3B-Reasoner
+Private finetuned Nanbeige4.1-3B reasoning release by `strykes`.
+## Included Artifacts
+- Merged full model (Safetensors) at repo root for HF benchmarking
+- LoRA adapter in `adapter/`
+- GGUF in `gguf/`:
   - `Nanbeige4.1-3B-Q5_K_M.gguf`
   - `Nanbeige4.1-3B-Q4_K_M.gguf`
   - `Nanbeige4.1-3B-f16.gguf`
+- Optional archive in `archives/`
+## Training Snapshot
+- Base: `Nanbeige/Nanbeige4.1-3B`
+- Method: Unsloth QLoRA -> merged weights
+- Data: ~3.5k synthetic reasoning samples
+- Epochs: 2
+- Sequence length: 4096
 ## Notes
+- Intended for research and benchmarking.
+- Validate outputs before critical use.