Hugging Face's logo

tensorblock
/
lambda-qwen2.5-32b-dpo-test-GGUF

Transformers
GGUF
alignment-handbook
trl
dpo
Generated from Trainer
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
lambda-qwen2.5-32b-dpo-test-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
92354e3 verified
preview code
|
raw
history blame contribute delete
5.37 kB
metadata
library_name: transformers
license: apache-2.0
base_model: tanliboy/lambda-qwen2.5-32b-dpo-test
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - TensorBlock
  - GGUF
datasets:
  - tanliboy/orca_dpo_pairs
model-index:
  - name: lambda-qwen2.5-32b-dpo-test
    results: []
TensorBlock

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

tanliboy/lambda-qwen2.5-32b-dpo-test - GGUF

This repo contains GGUF format model files for tanliboy/lambda-qwen2.5-32b-dpo-test.

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
lambda-qwen2.5-32b-dpo-test-Q2_K.gguf Q2_K 11.467 GB smallest, significant quality loss - not recommended for most purposes
lambda-qwen2.5-32b-dpo-test-Q3_K_S.gguf Q3_K_S 13.404 GB very small, high quality loss
lambda-qwen2.5-32b-dpo-test-Q3_K_M.gguf Q3_K_M 14.841 GB very small, high quality loss
lambda-qwen2.5-32b-dpo-test-Q3_K_L.gguf Q3_K_L 16.063 GB small, substantial quality loss
lambda-qwen2.5-32b-dpo-test-Q4_0.gguf Q4_0 17.360 GB legacy; small, very high quality loss - prefer using Q3_K_M
lambda-qwen2.5-32b-dpo-test-Q4_K_S.gguf Q4_K_S 17.494 GB small, greater quality loss
lambda-qwen2.5-32b-dpo-test-Q4_K_M.gguf Q4_K_M 18.488 GB medium, balanced quality - recommended
lambda-qwen2.5-32b-dpo-test-Q5_0.gguf Q5_0 21.084 GB legacy; medium, balanced quality - prefer using Q4_K_M
lambda-qwen2.5-32b-dpo-test-Q5_K_S.gguf Q5_K_S 21.084 GB large, low quality loss - recommended
lambda-qwen2.5-32b-dpo-test-Q5_K_M.gguf Q5_K_M 21.665 GB large, very low quality loss - recommended
lambda-qwen2.5-32b-dpo-test-Q6_K.gguf Q6_K 25.040 GB very large, extremely low quality loss
lambda-qwen2.5-32b-dpo-test-Q8_0.gguf Q8_0 32.429 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/lambda-qwen2.5-32b-dpo-test-GGUF --include "lambda-qwen2.5-32b-dpo-test-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/lambda-qwen2.5-32b-dpo-test-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'