metadata
library_name: transformers
license: apache-2.0
datasets:
- OpenAssistant/oasst2
- nvidia/HelpSteer
language:
- en
- ja
tags:
- mixtral
- steerlm
- TensorBlock
- GGUF
base_model: karakuri-ai/karakuri-lm-8x7b-chat-v0.1
model-index:
- name: karakuri-ai/karakuri-lm-8x7b-chat-v0.1
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: MT-Bench
type: unknown
metrics:
- type: unknown
value: 7.39375
name: score
- type: unknown
value: 7.540625
name: score
source:
url: https://huggingface.co/spaces/lmsys/mt-bench
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
karakuri-ai/karakuri-lm-8x7b-chat-v0.1 - GGUF
This repo contains GGUF format model files for karakuri-ai/karakuri-lm-8x7b-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
<s>[INST] <<SYS>>
{system_prompt}
<</SYS>>
{prompt} [ATTR] helpfulness: 4 correctness: 4 coherence: 4 complexity: 4 verbosity: 4 quality: 4 toxicity: 0 humor: 0 creativity: 0 [/ATTR] [/INST]
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| karakuri-lm-8x7b-chat-v0.1-Q2_K.gguf | Q2_K | 17.311 GB | smallest, significant quality loss - not recommended for most purposes |
| karakuri-lm-8x7b-chat-v0.1-Q3_K_S.gguf | Q3_K_S | 20.433 GB | very small, high quality loss |
| karakuri-lm-8x7b-chat-v0.1-Q3_K_M.gguf | Q3_K_M | 22.546 GB | very small, high quality loss |
| karakuri-lm-8x7b-chat-v0.1-Q3_K_L.gguf | Q3_K_L | 24.170 GB | small, substantial quality loss |
| karakuri-lm-8x7b-chat-v0.1-Q4_0.gguf | Q4_0 | 26.444 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| karakuri-lm-8x7b-chat-v0.1-Q4_K_S.gguf | Q4_K_S | 26.746 GB | small, greater quality loss |
| karakuri-lm-8x7b-chat-v0.1-Q4_K_M.gguf | Q4_K_M | 28.448 GB | medium, balanced quality - recommended |
| karakuri-lm-8x7b-chat-v0.1-Q5_0.gguf | Q5_0 | 32.231 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| karakuri-lm-8x7b-chat-v0.1-Q5_K_S.gguf | Q5_K_S | 32.231 GB | large, low quality loss - recommended |
| karakuri-lm-8x7b-chat-v0.1-Q5_K_M.gguf | Q5_K_M | 33.230 GB | large, very low quality loss - recommended |
| karakuri-lm-8x7b-chat-v0.1-Q6_K.gguf | Q6_K | 38.381 GB | very large, extremely low quality loss |
| karakuri-lm-8x7b-chat-v0.1-Q8_0.gguf | Q8_0 | 49.626 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/karakuri-lm-8x7b-chat-v0.1-GGUF --include "karakuri-lm-8x7b-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/karakuri-lm-8x7b-chat-v0.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'