Instructions to use wilsonramos/llama31-8b-rh-questionnaire-lora-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use wilsonramos/llama31-8b-rh-questionnaire-lora-gguf 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 wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf wilsonramos/llama31-8b-rh-questionnaire-lora-gguf: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 wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf wilsonramos/llama31-8b-rh-questionnaire-lora-gguf: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 wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M

Use Docker

docker model run hf.co/wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use wilsonramos/llama31-8b-rh-questionnaire-lora-gguf with Ollama:
```
ollama run hf.co/wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M
```
Unsloth Desktop

How to use wilsonramos/llama31-8b-rh-questionnaire-lora-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M

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": "wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use wilsonramos/llama31-8b-rh-questionnaire-lora-gguf with Docker Model Runner:
```
docker model run hf.co/wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M
```

Lemonade

How to use wilsonramos/llama31-8b-rh-questionnaire-lora-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M

Run and chat with the model

lemonade run user.llama31-8b-rh-questionnaire-lora-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use wilsonramos/llama31-8b-rh-questionnaire-lora-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wilsonramos/llama31-8b-rh-questionnaire-lora-gguf: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 wilsonramos/llama31-8b-rh-questionnaire-lora-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use wilsonramos/llama31-8b-rh-questionnaire-lora-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wilsonramos/llama31-8b-rh-questionnaire-lora-gguf: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 "wilsonramos/llama31-8b-rh-questionnaire-lora-gguf: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"

wilsonramos commited on May 27

Commit

f12d8f5

verified ·

1 Parent(s): b7a0d6d

Upload evaluation files

Browse files

Files changed (4) hide show

eval/test_metrics.json +7 -0
eval/test_metrics_llama31_8b_lora_50samples.json +14 -0
eval/test_predictions_llama31_8b_lora_50samples.jsonl +0 -0
eval/val_metrics.json +9 -0

eval/test_metrics.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "n_test_samples": 50,
+  "prediction_json_valid_rate": 1,
+  "target_json_valid_rate": 1,
+  "avg_prediction_chars": 6254.58,
+  "avg_target_chars": 5991.26
+}

eval/test_metrics_llama31_8b_lora_50samples.json ADDED Viewed

	@@ -0,0 +1,14 @@

+{
+  "model_name": "meta-llama/Llama-3.1-8B-Instruct + LoRA",
+  "fine_tuned": true,
+  "n_test_samples": 50,
+  "batch_size": 8,
+  "prediction_json_valid_rate": 1,
+  "target_json_valid_rate": 1,
+  "prediction_structure_valid_rate": 1,
+  "target_structure_valid_rate": 1,
+  "avg_prediction_chars": 6254.58,
+  "avg_target_chars": 5991.26,
+  "avg_input_tokens": 1477.28,
+  "avg_generated_tokens": 1855.04
+}

eval/test_predictions_llama31_8b_lora_50samples.jsonl ADDED Viewed

The diff for this file is too large to render. See raw diff

eval/val_metrics.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "val_metrics": {
+    "eval_loss": 0.8205441832542419,
+    "eval_entropy": 0.8040949488541045,
+    "eval_num_tokens": 19087305.0,
+    "eval_mean_token_accuracy": 0.8164775476037743
+  },
+  "val_perplexity": 2.2717357417714457
+}