feat: add GPT-OSS-120B model to SambaNova provider#8187
feat: add GPT-OSS-120B model to SambaNova provider#8187roomote[bot] wants to merge 1 commit intomainfrom
Conversation
- Added GPT-OSS-120B to SambaNovaModelId type - Added model configuration with 64K context window - Added test coverage for the new model Fixes #8185
dosubot
bot
added
size:S
![roomote[bot]](https://avatars.githubusercontent.com/in/1546624?s=60&v=4){kind=small}
| | "Llama-4-Maverick-17B-128E-Instruct" | ||
| | "Llama-3.3-Swallow-70B-Instruct-v0.4" | ||
| | "Qwen3-32B" | ||
| | "GPT-OSS-120B" |
There was a problem hiding this comment.
Issue #8185 mentions that SambaNova has both "deepseek v3.1 and gpt oss 120 b" available. While we've added GPT-OSS-120B, we're missing DeepSeek V3.1.
Looking at other providers in the codebase, they have DeepSeek V3.1 defined:
- Fireworks has it as "deepseek-v3.1"
- Chutes has it as "deepseek-ai/DeepSeek-V3.1"
- Vertex has it as "deepseek-v3.1-maas"
Should we add "DeepSeek-V3.1" here to fully address the issue? The existing "DeepSeek-V3-0324" appears to be a date-versioned model (March 24), not the V3.1 mentioned in the issue.
| }, | ||
| "GPT-OSS-120B": { | ||
| maxTokens: 8192, | ||
| contextWindow: 65536, |
There was a problem hiding this comment.
Have these specifications (64K context window, /bin/sh.6/.2 pricing) been verified against SambaNova's actual API documentation? It would be good to confirm these values are accurate.
| expect(model.info).toEqual(sambaNovaModels[testModelId]) | ||
| expect(model.info.contextWindow).toBe(65536) | ||
| expect(model.info.description).toContain("GPT-OSS 120B") | ||
| }) |
There was a problem hiding this comment.
Good test coverage for GPT-OSS-120B! If we add DeepSeek V3.1, we should add a similar test for it as well.
hannesrudolph
added
the
Issue/PR - Triage
|
solved in #8186 |
3 participants
This PR attempts to address Issue #8185 by updating the SambaNova model list.
Changes
Notes
The issue also mentioned DeepSeek v3.1, but the codebase already contains several DeepSeek models:
These existing models may already satisfy the DeepSeek requirement. If a specific DeepSeek v3.1 model is needed, please let me know and I can add it.
Testing
Fixes #8185
Feedback and guidance are welcome!
Important
Add
GPT-OSS-120Bmodel to SambaNova provider with test coverage insambanova.tsandsambanova.spec.ts.GPT-OSS-120Btosambanova.tswith 64K context window.GPT-OSS-120Binsambanova.spec.tsto verify model retrieval and properties.This description was created by
for d9e48db. You can customize this summary. It will automatically update as commits are pushed.