Models
Search
Discord
GitHub
Download
Sign in
Blog
Discord
GitHub
Models
Sign in
Download
CognitiveComputations
/
dolphin-mistral-32k
156 Pulls
Updated 2 months ago
7b-v2.9.3-q8_0
7b-v2.9.3-q2_k
2.7GB
7b-v2.9.3-q3_k
3.5GB
7b-v2.9.3-q4_0
4.1GB
7b-v2.9.3-q4_k_s
4.1GB
7b-v2.9.3-q4_k_m
4.4GB
7b-v2.9.3-q5_0
5.0GB
7b-v2.9.3-q5_k_s
5.0GB
7b-v2.9.3-q5_k_m
5.1GB
7b-v2.9.3-q6_k
5.9GB
7b-v2.9.3-q8_0
7.7GB
10 Tags
Updated 2 months ago
2 months ago
2f76d1f73859 · 7.7GB
model
arch
llama
·
parameters
7.25B
·
quantization
Q8_0
7.7GB
template
<|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assistant
107B
params
{"num_ctx":32768,"stop":["<|im_start|>","<|im_end|>"]}
75B
Readme
No readme
Write
Preview
Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)