Instructions to use ductai199x/utter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ductai199x/utter 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 ductai199x/utter:Q4_0
# Run inference directly in the terminal:
llama cli -hf ductai199x/utter:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ductai199x/utter:Q4_0
# Run inference directly in the terminal:
llama cli -hf ductai199x/utter:Q4_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf ductai199x/utter:Q4_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf ductai199x/utter:Q4_0

Use Docker

docker model run hf.co/ductai199x/utter:Q4_0

Llama new
LM Studio
Jan
Ollama
How to use ductai199x/utter with Ollama:
```
ollama run hf.co/ductai199x/utter:Q4_0
```
Unsloth Desktop

How to use ductai199x/utter with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ductai199x/utter:Q4_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ductai199x/utter:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ductai199x/utter with Docker Model Runner:
```
docker model run hf.co/ductai199x/utter:Q4_0
```

Lemonade

How to use ductai199x/utter with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ductai199x/utter:Q4_0

Run and chat with the model

lemonade run user.utter-Q4_0

List all available models

lemonade list

Hermes Agent

How to use ductai199x/utter with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ductai199x/utter:Q4_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 ductai199x/utter:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ductai199x/utter with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ductai199x/utter:Q4_0

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 "ductai199x/utter:Q4_0" \
  --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"

ductai199x commited on 17 days ago

Commit

5844d96

verified ·

1 Parent(s): fb937c5

v2: Quality (E4B) and Light (E2B) trained on dictation-to-text with the shipped recipe

Browse files

Files changed (7) hide show

.gitattributes +2 -0
adapters/utter-light-v2/adapter_config.json +43 -0
adapters/utter-light-v2/adapter_model.safetensors +3 -0
adapters/utter-quality-v2/adapter_config.json +43 -0
adapters/utter-quality-v2/adapter_model.safetensors +3 -0
utter-light-v2-q4_0.gguf +3 -0
utter-quality-v2-q4_0.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 utter-quality-v1-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
 utter-light-v1-q4_0.gguf filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 utter-quality-v1-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
 utter-light-v1-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+utter-quality-v2-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+utter-light-v2-q4_0.gguf filter=lfs diff=lfs merge=lfs -text

adapters/utter-light-v2/adapter_config.json ADDED Viewed

	@@ -0,0 +1,43 @@

+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-4-E2B-it-qat-q4_0-unquantized",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.2",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": ".*language_model.*\\.(q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapters/utter-light-v2/adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:40e37df5d9032a2aec1e4d9a684465b4461423220a5081865f8ddc0e12b9bd0b
+size 96693360

adapters/utter-quality-v2/adapter_config.json ADDED Viewed

	@@ -0,0 +1,43 @@

+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-4-e4b-it-qat-q4_0-unquantized",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.2",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": ".*language_model.*\\.(q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapters/utter-quality-v2/adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:eb3bf7e91d7a37db029f3038b0de22f9ef2015d04c082f2c17c0c21c6233fc86
+size 139602808

utter-light-v2-q4_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5f74fa6e74b29547f2000b7a515939070e3a44ef7f81942d869de762bc434c
+size 3349515808

utter-quality-v2-q4_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7629c1d3b1a7124388ea3afb5210378ce429fc623e9330b994c351f17d2d58
+size 5154940832