metadata

base_model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
datasets:
  - cognitivecomputations/Dolphin-2.9
  - teknium/OpenHermes-2.5
  - m-a-p/CodeFeedback-Filtered-Instruction
  - cognitivecomputations/dolphin-coder
  - cognitivecomputations/samantha-data
  - microsoft/orca-math-word-problems-200k
  - Locutusque/function-calling-chatml
  - internlm/Agent-FLAN
inference: false
library_name: gguf
license: llama3
model-index:
  - name: out
    results: []
pipeline_tag: text-generation
quantized_by: legraphista
tags:
  - quantized
  - GGUF
  - imatrix
  - quantization
  - imat
  - imatrix
  - static

dolphin-2.9.1-llama-3-70b-IMat-GGUF

Llama.cpp imatrix quantization of cognitivecomputations/dolphin-2.9.1-llama-3-70b

Original Model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp b3003
IMatrix dataset: here

dolphin-2.9.1-llama-3-70b-IMat-GGUF

Files

IMatrix

Status: ✅ Available
Link: here

Common Quants

Filename	Quant type	File Size	Status	Uses IMatrix	Is Split
dolphin-2.9.1-llama-3-70b.Q8_0/*	Q8_0	74.98GB	✅ Available	⚪ Static	✂ Yes
dolphin-2.9.1-llama-3-70b.Q6_K/*	Q6_K	57.89GB	✅ Available	⚪ Static	✂ Yes
dolphin-2.9.1-llama-3-70b.Q4_K.gguf	Q4_K	42.52GB	✅ Available	🟢 IMatrix	📦 No
dolphin-2.9.1-llama-3-70b.Q3_K.gguf	Q3_K	34.27GB	✅ Available	🟢 IMatrix	📦 No
dolphin-2.9.1-llama-3-70b.Q2_K.gguf	Q2_K	26.38GB	✅ Available	🟢 IMatrix	📦 No

All Quants

Filename	Quant type	File Size	Status	Uses IMatrix	Is Split
dolphin-2.9.1-llama-3-70b.FP16/*	F16	141.12GB	✅ Available	⚪ Static	✂ Yes
dolphin-2.9.1-llama-3-70b.BF16/*	BF16	141.12GB	✅ Available	⚪ Static	✂ Yes
dolphin-2.9.1-llama-3-70b.Q5_K/*	Q5_K	49.95GB	✅ Available	⚪ Static	✂ Yes
dolphin-2.9.1-llama-3-70b.Q5_K_S/*	Q5_K_S	48.66GB	✅ Available	⚪ Static	✂ Yes
dolphin-2.9.1-llama-3-70b.Q4_K_S.gguf	Q4_K_S	40.35GB	✅ Available	🟢 IMatrix	📦 No
dolphin-2.9.1-llama-3-70b.Q3_K_L.gguf	Q3_K_L	37.14GB	✅ Available	🟢 IMatrix	📦 No
dolphin-2.9.1-llama-3-70b.Q3_K_S.gguf	Q3_K_S	30.91GB	✅ Available	🟢 IMatrix	📦 No
dolphin-2.9.1-llama-3-70b.Q2_K_S.gguf	Q2_K_S	24.47GB	✅ Available	🟢 IMatrix	📦 No
dolphin-2.9.1-llama-3-70b.IQ4_NL.gguf	IQ4_NL	40.05GB	✅ Available	🟢 IMatrix	📦 No
dolphin-2.9.1-llama-3-70b.IQ4_XS.gguf	IQ4_XS	37.90GB	✅ Available	🟢 IMatrix	📦 No
dolphin-2.9.1-llama-3-70b.IQ3_M.gguf	IQ3_M	31.94GB	✅ Available	🟢 IMatrix	📦 No
dolphin-2.9.1-llama-3-70b.IQ3_S.gguf	IQ3_S	30.91GB	✅ Available	🟢 IMatrix	📦 No
dolphin-2.9.1-llama-3-70b.IQ3_XS.gguf	IQ3_XS	29.31GB	✅ Available	🟢 IMatrix	📦 No
dolphin-2.9.1-llama-3-70b.IQ3_XXS	IQ3_XXS	-	⏳ Processing	🟢 IMatrix	-
dolphin-2.9.1-llama-3-70b.IQ2_M	IQ2_M	-	⏳ Processing	🟢 IMatrix	-
dolphin-2.9.1-llama-3-70b.IQ2_S	IQ2_S	-	⏳ Processing	🟢 IMatrix	-
dolphin-2.9.1-llama-3-70b.IQ2_XS	IQ2_XS	-	⏳ Processing	🟢 IMatrix	-
dolphin-2.9.1-llama-3-70b.IQ2_XXS	IQ2_XXS	-	⏳ Processing	🟢 IMatrix	-
dolphin-2.9.1-llama-3-70b.IQ1_M	IQ1_M	-	⏳ Processing	🟢 IMatrix	-
dolphin-2.9.1-llama-3-70b.IQ1_S	IQ1_S	-	⏳ Processing	🟢 IMatrix	-

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/dolphin-2.9.1-llama-3-70b-IMat-GGUF --include "dolphin-2.9.1-llama-3-70b.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/dolphin-2.9.1-llama-3-70b-IMat-GGUF --include "dolphin-2.9.1-llama-3-70b.Q8_0/*" --local-dir dolphin-2.9.1-llama-3-70b.Q8_0
# see FAQ for merging GGUF's

Inference

Simple chat template

<|im_start|>user
Can you provide ways to eat combinations of bananas and dragonfruits?<|im_end|>
<|im_start|>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.<|im_end|>
<|im_start|>user
What about solving an 2x + 3 = 7 equation?<|im_end|>

Chat template with system prompt

<|im_start|>system
You are a helpful AI.<|im_end|>
<|im_start|>user
Can you provide ways to eat combinations of bananas and dragonfruits?<|im_end|>
<|im_start|>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.<|im_end|>
<|im_start|>user
What about solving an 2x + 3 = 7 equation?<|im_end|>

Llama.cpp

llama.cpp/main -m dolphin-2.9.1-llama-3-70b.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?

Make sure you have gguf-split available
- To get hold of gguf-split, navigate to https://github.com/ggerganov/llama.cpp/releases
- Download the appropriate zip for your system from the latest release
- Unzip the archive and you should be able to find gguf-split
Locate your GGUF chunks folder (ex: dolphin-2.9.1-llama-3-70b.Q8_0)
Run gguf-split --merge dolphin-2.9.1-llama-3-70b.Q8_0/dolphin-2.9.1-llama-3-70b.Q8_0-00001-of-XXXXX.gguf dolphin-2.9.1-llama-3-70b.Q8_0.gguf
- Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!