Hugging Face's logo

tensorblock
/
ReflectionCoder-CL-34B-GGUF

GGUF
English
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
ReflectionCoder-CL-34B-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
e8af509 verified
preview code
|
raw
history blame contribute delete
4.74 kB
metadata
license: apache-2.0
datasets:
  - SenseLLM/ReflectionSeq-GPT
  - SenseLLM/ReflectionSeq-DS
language:
  - en
base_model: SenseLLM/ReflectionCoder-CL-34B
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

SenseLLM/ReflectionCoder-CL-34B - GGUF

This repo contains GGUF format model files for SenseLLM/ReflectionCoder-CL-34B.

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

Prompt template 

<|system|><|text|>{system_prompt}<|endofblock|><|endofmessage|><|user|><|text|>{prompt}<|endofblock|><|endofmessage|><|assistant|>

Model file specification

Filename Quant type File Size Description
ReflectionCoder-CL-34B-Q2_K.gguf Q2_K 11.647 GB smallest, significant quality loss - not recommended for most purposes
ReflectionCoder-CL-34B-Q3_K_S.gguf Q3_K_S 13.602 GB very small, high quality loss
ReflectionCoder-CL-34B-Q3_K_M.gguf Q3_K_M 15.186 GB very small, high quality loss
ReflectionCoder-CL-34B-Q3_K_L.gguf Q3_K_L 16.551 GB small, substantial quality loss
ReflectionCoder-CL-34B-Q4_0.gguf Q4_0 17.744 GB legacy; small, very high quality loss - prefer using Q3_K_M
ReflectionCoder-CL-34B-Q4_K_S.gguf Q4_K_S 17.874 GB small, greater quality loss
ReflectionCoder-CL-34B-Q4_K_M.gguf Q4_K_M 18.831 GB medium, balanced quality - recommended
ReflectionCoder-CL-34B-Q5_0.gguf Q5_0 21.641 GB legacy; medium, balanced quality - prefer using Q4_K_M
ReflectionCoder-CL-34B-Q5_K_S.gguf Q5_K_S 21.641 GB large, low quality loss - recommended
ReflectionCoder-CL-34B-Q5_K_M.gguf Q5_K_M 22.202 GB large, very low quality loss - recommended
ReflectionCoder-CL-34B-Q6_K.gguf Q6_K 25.783 GB very large, extremely low quality loss
ReflectionCoder-CL-34B-Q8_0.gguf Q8_0 33.394 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/ReflectionCoder-CL-34B-GGUF --include "ReflectionCoder-CL-34B-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/ReflectionCoder-CL-34B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'