metadata
widget:
- messages:
- role: system
content: >-
You are a career counselor. The user will provide you with an
individual looking for guidance in their professional life, and your
task is to assist them in determining what careers they are most
suited for based on their skills, interests, and experience. You
should also conduct research into the various options available,
explain the job market trends in different industries, and advice on
which qualifications would be beneficial for pursuing particular
fields.
- role: user
content: Hey friend!
- role: assistant
content: Hi! How may I help you?
- role: user
content: >-
I am interested in developing a career in software engineering. What
would you recommend me to do?
- messages:
- role: system
content: You are a knowledgeable assistant. Help the user as much as you can.
- role: user
content: How to become smarter?
- messages:
- role: system
content: You are a helpful assistant who provides concise responses.
- role: user
content: Hi!
- role: assistant
content: Hello there! How may I help you?
- role: user
content: I need to cook a simple dinner. What ingredients should I prepare for?
- messages:
- role: system
content: >-
You are a very creative assistant. User will give you a task, which
you should complete with all your knowledge.
- role: user
content: >-
Write the novel story of an RPG game about group of survivor post
apocalyptic world.
inference:
parameters:
max_new_tokens: 256
temperature: 0.6
top_p: 0.95
top_k: 50
repetition_penalty: 1.2
base_model: frankenmerger/MiniLlama-1.8b-Chat-v0.1
license: apache-2.0
language:
- en
pipeline_tag: text-generation
datasets:
- Locutusque/Hercules-v3.0
- Locutusque/hyperion-v2.0
- argilla/OpenHermes2.5-dpo-binarized-alpha
tags:
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
frankenmerger/MiniLlama-1.8b-Chat-v0.1 - GGUF
This repo contains GGUF format model files for frankenmerger/MiniLlama-1.8b-Chat-v0.1.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
Prompt template
<|system|>
{system_prompt}</s>
<|user|>
{prompt}</s>
<|assistant|>
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| MiniLlama-1.8b-Chat-v0.1-Q2_K.gguf | Q2_K | 0.724 GB | smallest, significant quality loss - not recommended for most purposes |
| MiniLlama-1.8b-Chat-v0.1-Q3_K_S.gguf | Q3_K_S | 0.840 GB | very small, high quality loss |
| MiniLlama-1.8b-Chat-v0.1-Q3_K_M.gguf | Q3_K_M | 0.930 GB | very small, high quality loss |
| MiniLlama-1.8b-Chat-v0.1-Q3_K_L.gguf | Q3_K_L | 1.008 GB | small, substantial quality loss |
| MiniLlama-1.8b-Chat-v0.1-Q4_0.gguf | Q4_0 | 1.083 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| MiniLlama-1.8b-Chat-v0.1-Q4_K_S.gguf | Q4_K_S | 1.090 GB | small, greater quality loss |
| MiniLlama-1.8b-Chat-v0.1-Q4_K_M.gguf | Q4_K_M | 1.145 GB | medium, balanced quality - recommended |
| MiniLlama-1.8b-Chat-v0.1-Q5_0.gguf | Q5_0 | 1.311 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| MiniLlama-1.8b-Chat-v0.1-Q5_K_S.gguf | Q5_K_S | 1.311 GB | large, low quality loss - recommended |
| MiniLlama-1.8b-Chat-v0.1-Q5_K_M.gguf | Q5_K_M | 1.343 GB | large, very low quality loss - recommended |
| MiniLlama-1.8b-Chat-v0.1-Q6_K.gguf | Q6_K | 1.554 GB | very large, extremely low quality loss |
| MiniLlama-1.8b-Chat-v0.1-Q8_0.gguf | Q8_0 | 2.012 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/MiniLlama-1.8b-Chat-v0.1-GGUF --include "MiniLlama-1.8b-Chat-v0.1-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/MiniLlama-1.8b-Chat-v0.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'