Instructions to use epscylonb/1386.ai.rocm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use epscylonb/1386.ai.rocm 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 epscylonb/1386.ai.rocm:F16
# Run inference directly in the terminal:
llama cli -hf epscylonb/1386.ai.rocm:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf epscylonb/1386.ai.rocm:F16
# Run inference directly in the terminal:
llama cli -hf epscylonb/1386.ai.rocm:F16

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 epscylonb/1386.ai.rocm:F16
# Run inference directly in the terminal:
./llama-cli -hf epscylonb/1386.ai.rocm:F16

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 epscylonb/1386.ai.rocm:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf epscylonb/1386.ai.rocm:F16

Use Docker

docker model run hf.co/epscylonb/1386.ai.rocm:F16

Llama new
LM Studio
Jan

vLLM

How to use epscylonb/1386.ai.rocm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "epscylonb/1386.ai.rocm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "epscylonb/1386.ai.rocm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/epscylonb/1386.ai.rocm:F16

Ollama
How to use epscylonb/1386.ai.rocm with Ollama:
```
ollama run hf.co/epscylonb/1386.ai.rocm:F16
```
Unsloth Desktop
Docker Model Runner
How to use epscylonb/1386.ai.rocm with Docker Model Runner:
```
docker model run hf.co/epscylonb/1386.ai.rocm:F16
```

Lemonade

How to use epscylonb/1386.ai.rocm with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull epscylonb/1386.ai.rocm:F16

Run and chat with the model

lemonade run user.1386.ai.rocm-F16

List all available models

lemonade list

Atomic Chat

1386.ai.rocm / tokenizer_config.json

epscylonb

Plasma 1.1 GGUFs (RoPE-correct) + config/tokenizer

f0b7f38 verified 20 days ago

Raw History Blame Contribute Delete

304 Bytes

{
 "add_bos_token": true,
 "add_eos_token": false,
 "bos_token": "<s>",
 "clean_up_tokenization_spaces": false,
 "eos_token": "</s>",
 "model_max_length": 2048,
 "pad_token": "<pad>",
 "tokenizer_class": "LlamaTokenizer",
 "unk_token": "<unk>",
 "use_default_system_prompt": false,
 "vocab_size": 48000
}

	{
	"add_bos_token": true,
	"add_eos_token": false,
	"bos_token": "<s>",
	"clean_up_tokenization_spaces": false,
	"eos_token": "</s>",
	"model_max_length": 2048,
	"pad_token": "<pad>",
	"tokenizer_class": "LlamaTokenizer",
	"unk_token": "<unk>",
	"use_default_system_prompt": false,
	"vocab_size": 48000
	}