Instructions to use saadxsalman/SS-Talk-2-Bash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use saadxsalman/SS-Talk-2-Bash with PEFT:
```
Task type is invalid.
```

How to use saadxsalman/SS-Talk-2-Bash with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="saadxsalman/SS-Talk-2-Bash",
	filename="ss-talk-2-bash.Q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use saadxsalman/SS-Talk-2-Bash with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf saadxsalman/SS-Talk-2-Bash:Q8_0
# Run inference directly in the terminal:
llama-cli -hf saadxsalman/SS-Talk-2-Bash:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf saadxsalman/SS-Talk-2-Bash:Q8_0
# Run inference directly in the terminal:
llama-cli -hf saadxsalman/SS-Talk-2-Bash: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 saadxsalman/SS-Talk-2-Bash:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf saadxsalman/SS-Talk-2-Bash: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 saadxsalman/SS-Talk-2-Bash:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf saadxsalman/SS-Talk-2-Bash:Q8_0

Use Docker

docker model run hf.co/saadxsalman/SS-Talk-2-Bash:Q8_0

LM Studio
Jan

vLLM

How to use saadxsalman/SS-Talk-2-Bash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saadxsalman/SS-Talk-2-Bash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saadxsalman/SS-Talk-2-Bash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/saadxsalman/SS-Talk-2-Bash:Q8_0

Ollama
How to use saadxsalman/SS-Talk-2-Bash with Ollama:
```
ollama run hf.co/saadxsalman/SS-Talk-2-Bash:Q8_0
```

Unsloth Studio new

How to use saadxsalman/SS-Talk-2-Bash 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 saadxsalman/SS-Talk-2-Bash 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 saadxsalman/SS-Talk-2-Bash to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for saadxsalman/SS-Talk-2-Bash to start chatting

Pi new

How to use saadxsalman/SS-Talk-2-Bash with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf saadxsalman/SS-Talk-2-Bash: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": "saadxsalman/SS-Talk-2-Bash:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use saadxsalman/SS-Talk-2-Bash with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf saadxsalman/SS-Talk-2-Bash: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 saadxsalman/SS-Talk-2-Bash:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use saadxsalman/SS-Talk-2-Bash with Docker Model Runner:
```
docker model run hf.co/saadxsalman/SS-Talk-2-Bash:Q8_0
```

Lemonade

How to use saadxsalman/SS-Talk-2-Bash with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull saadxsalman/SS-Talk-2-Bash:Q8_0

Run and chat with the model

lemonade run user.SS-Talk-2-Bash-Q8_0

List all available models

lemonade list

SS-Talk-2-Bash (LFM-350M-Hardcoded)

This model is a fine-tuned version of LiquidAI/LFM2.5-350M designed specifically for deterministic natural language to Bash command translation. It uses a Strict Hard-Coding training method to minimize linguistic "chatter" and maximize structural accuracy.

1. Model Description

Developed by: saadxsalman
Model type: Causal Language Model (LFM)
Language(s): English (Input) to Bash (Output)
License: Apache 2.0
Finetuned from model: LiquidAI/LFM2.5-350M

2. Training Strategy: "The Hard-Coding Engine"

Unlike standard instruction-tuned models that learn to be "helpful assistants," this model was trained using a Masking Collator strategy:

Label Masking: All natural language tokens (the prompt) are masked during training ($loss = -100$). The model only calculates loss on the Bash command itself.
Zero Chatter: The model does not learn to say "Sure, here is your command." It is trained to jump directly from the [CL] token to the syntax.
Greedy Decoding: The generation_config.json is locked to do_sample: False and temperature: 0.0 to ensure the same input always produces the same output.

3. Training Data

The model was fine-tuned on the emirkaanozdemr/bash_command_data_6K dataset. The data was restructured into a rigid non-linguistic format: [NL] {Natural Language Prompt} [CL] {Bash Command} [END]

4. Intended Use & Prompting

To get the best results, you must use the specific trigger tokens used during training.

Correct Prompt Format: [NL] find all files larger than 100MB in the current directory [CL]

5. How to Use (Inference)

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "saadxsalman/SS-Talk-2-Bash"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

prompt = "[NL] list all files in long format [CL]"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens=64)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

6. Limitations and Biases

Logic Only: This model has "forgotten" how to converse. It will not answer general questions or write Python code.
Bash Specific: It is optimized for standard Linux Bash commands. It may struggle with complex shell scripting logic if not represented in the 6K training samples.
Formatting Sensitive: If the [NL] or [CL] tokens are omitted, the model performance will degrade significantly.

7. Training Hyperparameters

Parameter	Value
Learning Rate	$1 \times 10^{-4}$
Optimizer	Paged AdamW 8-bit
LoRA R	64
LoRA Alpha	128
Batch Size	16 (4 per device $\times$ 4 grad accum)
Precision	Mixed Precision (FP16)

Downloads last month: 12

Safetensors

Model size

0.4B params

Tensor type

F16

Model tree for saadxsalman/SS-Talk-2-Bash

Base model

LiquidAI/LFM2.5-350M-Base

Finetuned

LiquidAI/LFM2.5-350M

Adapter

(10)

this model

saadxsalman
/

SS-Talk-2-Bash