Downloads · 30 days
1.3K
11% of all-time downloads
duyntnet/Narwhal-7b-v3-imatrix-GGUF
Narwhal-7b-v3-imatrix-GGUF is a text generation model from duyntnet. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Quantizations of https://huggingface.co/Vezora/Narwhal-7b-v3
Downloads · 30 days
1.3K
11% of all-time downloads
All-time downloads
12.4K
Public
Repo size
99.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf99.9 GB · 100%
From the Hugging Face model README
Quantizations of https://huggingface.co/Vezora/Narwhal-7b-v3
This is a merge model using Tie merge method. Created using openchat 3.5 and una-cybertron-7b-v2-bf16.
Instruction template:
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("openchat/openchat_3.5")
# Single-turn
tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant:").input_ids
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
# Multi-turn
tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:").input_ids
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
# Coding Mode
tokens = tokenizer("Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:").input_ids
assert tokens == [1, 7596, 1247, 28747, 26256, 2936, 7653, 1413, 334, 1680, 32000, 7596, 21631, 28747]