legraphista's picture
Upload README.md with huggingface_hub
b5be5d4 verified
|
raw
history blame
6.57 kB
metadata
base_model: nvidia/Llama3-ChatQA-1.5-8B
inference: false
language:
  - en
library_name: gguf
license: llama3
pipeline_tag: text-generation
quantized_by: legraphista
tags:
  - quantized
  - GGUF
  - imatrix
  - quantization
  - imat
  - imatrix
  - static

Llama3-ChatQA-1.5-8B-IMat-GGUF

Llama.cpp imatrix quantization of nvidia/Llama3-ChatQA-1.5-8B

Original Model: nvidia/Llama3-ChatQA-1.5-8B
Original dtype: FP16 (float16)
Quantized by: llama.cpp b3003
IMatrix dataset: here


Files

IMatrix

Status: ⏳ Processing
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
Llama3-ChatQA-1.5-8B.Q8_0.gguf Q8_0 8.54GB βœ… Available βšͺ No πŸ“¦ No
Llama3-ChatQA-1.5-8B.Q6_K.gguf Q6_K 6.60GB βœ… Available βšͺ No πŸ“¦ No
Llama3-ChatQA-1.5-8B.Q4_K Q4_K - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.Q3_K Q3_K - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.Q2_K Q2_K - ⏳ Processing 🟒 Yes -

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
Llama3-ChatQA-1.5-8B.FP16 F16 - ⏳ Processing βšͺ No -
Llama3-ChatQA-1.5-8B.Q5_K.gguf Q5_K 5.73GB βœ… Available βšͺ No πŸ“¦ No
Llama3-ChatQA-1.5-8B.Q5_K_S.gguf Q5_K_S 5.60GB βœ… Available βšͺ No πŸ“¦ No
Llama3-ChatQA-1.5-8B.Q4_K_S Q4_K_S - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.Q3_K_L Q3_K_L - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.Q3_K_S Q3_K_S - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.Q2_K_S Q2_K_S - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.IQ4_NL IQ4_NL - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.IQ4_XS IQ4_XS - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.IQ3_M IQ3_M - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.IQ3_S IQ3_S - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.IQ3_XS IQ3_XS - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.IQ3_XXS IQ3_XXS - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.IQ2_M IQ2_M - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.IQ2_S IQ2_S - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.IQ2_XS IQ2_XS - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.IQ2_XXS IQ2_XXS - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.IQ1_M IQ1_M - ⏳ Processing 🟒 Yes -
Llama3-ChatQA-1.5-8B.IQ1_S IQ1_S - ⏳ Processing 🟒 Yes -

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/Llama3-ChatQA-1.5-8B-IMat-GGUF --include "Llama3-ChatQA-1.5-8B.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/Llama3-ChatQA-1.5-8B-IMat-GGUF --include "Llama3-ChatQA-1.5-8B.Q8_0/*" --local-dir Llama3-ChatQA-1.5-8B.Q8_0
# see FAQ for merging GGUF's

Inference

Simple chat template

<|begin_of_text|>System: This is a chat between a user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions based on the context. The assistant should also indicate when the answer cannot be found in the context.

User: Can you provide ways to eat combinations of bananas and dragonfruits?

Assistant: Sure! Here are some ways to eat bananas and dragonfruits together:
 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey.
 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey.

User: What about solving an 2x + 3 = 7 equation?

Assistant:

Llama.cpp

llama.cpp/main -m Llama3-ChatQA-1.5-8B.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: Llama3-ChatQA-1.5-8B.Q8_0)
  3. Run gguf-split --merge Llama3-ChatQA-1.5-8B.Q8_0/Llama3-ChatQA-1.5-8B.Q8_0-00001-of-XXXXX.gguf Llama3-ChatQA-1.5-8B.Q8_0.gguf
    • Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!