Hugging Face's logo

legraphista
/
internlm2_5-20b-chat-IMat-GGUF

Text Generation
GGUF
quantized
GGUF
quantization
imat
imatrix
static
16bit
8bit
6bit
5bit
4bit
3bit
2bit
1bit
conversational
Model card Files Community
internlm2_5-20b-chat-IMat-GGUF / README.md
legraphista's picture
legraphista
Upload README.md with huggingface_hub
f01b285 verified
preview code
|
raw
history blame contribute delete
10 kB
metadata
base_model: internlm/internlm2_5-20b-chat
inference: false
library_name: gguf
license: other
pipeline_tag: text-generation
quantized_by: legraphista
tags:
  - quantized
  - GGUF
  - quantization
  - imat
  - imatrix
  - static
  - 16bit
  - 8bit
  - 6bit
  - 5bit
  - 4bit
  - 3bit
  - 2bit
  - 1bit

internlm2_5-20b-chat-IMat-GGUF

Llama.cpp imatrix quantization of internlm/internlm2_5-20b-chat

Original Model: internlm/internlm2_5-20b-chat
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp b3524
IMatrix dataset: here

Files

IMatrix

Status: ✅ Available
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
internlm2_5-20b-chat.Q8_0.gguf Q8_0 21.11GB ✅ Available ⚪ Static 📦 No
internlm2_5-20b-chat.Q6_K.gguf Q6_K 16.30GB ✅ Available ⚪ Static 📦 No
internlm2_5-20b-chat.Q4_K.gguf Q4_K 11.98GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.Q3_K.gguf Q3_K 9.72GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.Q2_K.gguf Q2_K 7.55GB ✅ Available 🟢 IMatrix 📦 No

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
internlm2_5-20b-chat.BF16.gguf BF16 39.73GB ✅ Available ⚪ Static 📦 No
internlm2_5-20b-chat.FP16.gguf F16 39.73GB ✅ Available ⚪ Static 📦 No
internlm2_5-20b-chat.Q8_0.gguf Q8_0 21.11GB ✅ Available ⚪ Static 📦 No
internlm2_5-20b-chat.Q6_K.gguf Q6_K 16.30GB ✅ Available ⚪ Static 📦 No
internlm2_5-20b-chat.Q5_K.gguf Q5_K 14.08GB ✅ Available ⚪ Static 📦 No
internlm2_5-20b-chat.Q5_K_S.gguf Q5_K_S 13.73GB ✅ Available ⚪ Static 📦 No
internlm2_5-20b-chat.Q4_K.gguf Q4_K 11.98GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.Q4_K_S.gguf Q4_K_S 11.40GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.IQ4_NL.gguf IQ4_NL 11.36GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.IQ4_XS.gguf IQ4_XS 10.77GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.Q3_K.gguf Q3_K 9.72GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.Q3_K_L.gguf Q3_K_L 10.55GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.Q3_K_S.gguf Q3_K_S 8.76GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.IQ3_M.gguf IQ3_M 9.12GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.IQ3_S.gguf IQ3_S 8.80GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.IQ3_XS.gguf IQ3_XS 8.36GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.IQ3_XXS.gguf IQ3_XXS 7.81GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.Q2_K.gguf Q2_K 7.55GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.Q2_K_S.gguf Q2_K_S 7.01GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.IQ2_M.gguf IQ2_M 6.97GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.IQ2_S.gguf IQ2_S 6.47GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.IQ2_XS.gguf IQ2_XS 6.10GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.IQ2_XXS.gguf IQ2_XXS 5.54GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.IQ1_M.gguf IQ1_M 4.92GB ✅ Available 🟢 IMatrix 📦 No
internlm2_5-20b-chat.IQ1_S.gguf IQ1_S 4.54GB ✅ Available 🟢 IMatrix 📦 No

Downloading using huggingface-cli

If you do not have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Download the specific file you want:

huggingface-cli download legraphista/internlm2_5-20b-chat-IMat-GGUF --include "internlm2_5-20b-chat.Q8_0.gguf" --local-dir ./

If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download legraphista/internlm2_5-20b-chat-IMat-GGUF --include "internlm2_5-20b-chat.Q8_0/*" --local-dir ./
# see FAQ for merging GGUF's

Inference

Simple chat template 

<s><|im_start|>user
{user_prompt}<|im_end|>
<|im_start|>assistant
{assistant_response}<|im_end|>
<|im_start|>user
{next_user_prompt}<|im_end|>

Chat template with system prompt 

<s><|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{user_prompt}<|im_end|>
<|im_start|>assistant
{assistant_response}<|im_end|>
<|im_start|>user
{next_user_prompt}<|im_end|>

Llama.cpp 

llama.cpp/main -m internlm2_5-20b-chat.Q8_0.gguf --color -i -p "prompt here (according to the chat template)"

FAQ

Why is the IMatrix not applied everywhere?

According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).

How do I merge a split GGUF?

  1. Make sure you have gguf-split available
  2. Locate your GGUF chunks folder (ex: internlm2_5-20b-chat.Q8_0)
  3. Run gguf-split --merge internlm2_5-20b-chat.Q8_0/internlm2_5-20b-chat.Q8_0-00001-of-XXXXX.gguf internlm2_5-20b-chat.Q8_0.gguf
    • Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!