uparekh01151 commited on
Commit
2ec7e68
·
1 Parent(s): 58f426e

Add GPT-OSS-120B and DeepSeek-R1-Distill-Llama-8B models with Nebius provider

Browse files
Files changed (1) hide show
  1. config/models.yaml +21 -1
config/models.yaml CHANGED
@@ -7,4 +7,24 @@ models:
7
  max_new_tokens: 256
8
  temperature: 0.1
9
  top_p: 0.9
10
- description: "Llama-3.1-8B-Instruct - Meta's instruction-following model via Nebius"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  max_new_tokens: 256
8
  temperature: 0.1
9
  top_p: 0.9
10
+ description: "Llama-3.1-8B-Instruct - Meta's instruction-following model via Nebius"
11
+
12
+ # GPT-OSS-120B with Nebius Provider
13
+ - name: "GPT-OSS-120B"
14
+ provider: "nebius"
15
+ model_id: "openai/gpt-oss-120b"
16
+ params:
17
+ max_new_tokens: 256
18
+ temperature: 0.1
19
+ top_p: 0.9
20
+ description: "GPT-OSS-120B - OpenAI's large language model via Nebius"
21
+
22
+ # DeepSeek-R1-Distill-Llama-8B with Nebius Provider
23
+ - name: "DeepSeek-R1-Distill-Llama-8B"
24
+ provider: "nebius"
25
+ model_id: "deepseek-ai/DeepSeek-R1-Distill-Llama-8B"
26
+ params:
27
+ max_new_tokens: 256
28
+ temperature: 0.1
29
+ top_p: 0.9
30
+ description: "DeepSeek-R1-Distill-Llama-8B - DeepSeek's reasoning model via Nebius"