Hugging Face's logo

tensorblock
/
stablelm-2-1_6b-chat-GGUF

GGUF
English
causal-lm
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
stablelm-2-1_6b-chat-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
5c3b6ae verified
preview code
|
raw
history blame contribute delete
5.01 kB
metadata
datasets:
  - HuggingFaceH4/ultrachat_200k
  - allenai/ultrafeedback_binarized_cleaned
  - meta-math/MetaMathQA
  - WizardLM/WizardLM_evol_instruct_V2_196k
  - openchat/openchat_sharegpt4_dataset
  - LDJnr/Capybara
  - Intel/orca_dpo_pairs
  - hkust-nlp/deita-10k-v0
  - teknium/OpenHermes-2.5
language:
  - en
tags:
  - causal-lm
  - TensorBlock
  - GGUF
extra_gated_fields:
  Name: text
  Email: text
  Country: text
  Organization or Affiliation: text
  I ALLOW Stability AI to email me about new model releases: checkbox
license: other
base_model: stabilityai/stablelm-2-1_6b-chat
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

stabilityai/stablelm-2-1_6b-chat - GGUF

This repo contains GGUF format model files for stabilityai/stablelm-2-1_6b-chat.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template 

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
stablelm-2-1_6b-chat-Q2_K.gguf Q2_K 0.646 GB smallest, significant quality loss - not recommended for most purposes
stablelm-2-1_6b-chat-Q3_K_S.gguf Q3_K_S 0.737 GB very small, high quality loss
stablelm-2-1_6b-chat-Q3_K_M.gguf Q3_K_M 0.799 GB very small, high quality loss
stablelm-2-1_6b-chat-Q3_K_L.gguf Q3_K_L 0.852 GB small, substantial quality loss
stablelm-2-1_6b-chat-Q4_0.gguf Q4_0 0.915 GB legacy; small, very high quality loss - prefer using Q3_K_M
stablelm-2-1_6b-chat-Q4_K_S.gguf Q4_K_S 0.921 GB small, greater quality loss
stablelm-2-1_6b-chat-Q4_K_M.gguf Q4_K_M 0.961 GB medium, balanced quality - recommended
stablelm-2-1_6b-chat-Q5_0.gguf Q5_0 1.083 GB legacy; medium, balanced quality - prefer using Q4_K_M
stablelm-2-1_6b-chat-Q5_K_S.gguf Q5_K_S 1.083 GB large, low quality loss - recommended
stablelm-2-1_6b-chat-Q5_K_M.gguf Q5_K_M 1.106 GB large, very low quality loss - recommended
stablelm-2-1_6b-chat-Q6_K.gguf Q6_K 1.261 GB very large, extremely low quality loss
stablelm-2-1_6b-chat-Q8_0.gguf Q8_0 1.632 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/stablelm-2-1_6b-chat-GGUF --include "stablelm-2-1_6b-chat-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/stablelm-2-1_6b-chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'