Tess-R1 is designed with test-time compute in mind, and has the capabilities to produce a Chain-of-Thought (CoT) reasoning before producing the final output.
70b
914 Pulls Updated 5 weeks ago
Updated 5 weeks ago
5 weeks ago
2505c6e46dbd · 43GB
model
archllama
·
parameters70.6B
·
quantizationQ4_K_M
43GB
params
{
"stop": [
"<|end_of_text|>",
"<|eot_id|>"
],
"temperature": 0.75,
102B
template
{{- if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>
{{- end }}
{{-
249B
system
You are Tess-R1, an advanced AI that was created for complex reasoning. Given a user query, you are
431B
Readme
This is an uncensored version of migtissera/Tess-R1-Limerick-Llama-3.1-70B created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
References
Donation
Your donation helps us continue our further development and improvement, a cup of coffee can do it.
- bitcoin:
bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge