chore: update models for integration tests of cerebras and fireworks (#822)

## Description
<!-- What does this PR do? -->


## PR Type
<!-- Delete the types that don't apply -->

- 🆕 New Feature
- 🐛 Bug Fix
- 💅 Refactor
- 📚 Documentation
- 🚦 Infrastructure

## Relevant issues
<!-- e.g. "Fixes #123" -->

## Checklist
<!-- If this checklist is deleted from the PR submission it will be
immediately closed -->
- [ ] I understand the code I am submitting.
- [ ] I have added unit tests that prove my fix/feature works
- [ ] I have run this code locally and verified it fixes the issue.
- [ ] New and existing tests pass locally
- [ ] Documentation was updated where necessary
- [ ] I have read and followed the [contribution
guidelines](https://github.com/mozilla-ai/any-llm/blob/main/CONTRIBUTING.md)
- [ ] **AI Usage:**
    - [ ] No AI was used.
    - [ ] AI was used for drafting/refactoring.
    - [ ] This is fully AI-generated.

## AI Usage Information
<!-- We welcome the use of AI to aid in contribution! Optional: We're
interested in hearing about your setup. What LLM are you using (e.g.
Opus 4.5, GPT-5, Minimax), and which tooling (Claude Code, VsCode,
OpenCode, etc) -->

- AI Model used:
- AI Developer Tool used:
- Any other info you'd like to share:

When answering questions by the reviewer, please respond yourself, do
not copy/paste the reviewer comments into an AI system and paste back
its answer. We want to discuss with you, not your AI :)

Author: njbrake

tests/conftest.py

@@ -66,7 +66,7 @@ def provider_model_map() -> dict[LLMProvider, str]:
         LLMProvider.LMSTUDIO: "google/gemma-3n-e4b",  # You must have LM Studio running and the server enabled
         LLMProvider.VLLM: "Qwen/Qwen2.5-0.5B-Instruct",
         LLMProvider.COHERE: "command-a-03-2025",
-        LLMProvider.CEREBRAS: "llama-3.3-70b",
+        LLMProvider.CEREBRAS: "llama3.1-8b",
         LLMProvider.HUGGINGFACE: "huggingface/tgi",  # This is the syntax used in `litellm` when using HF Inference Endpoints (https://docs.litellm.ai/docs/providers/huggingface#dedicated-inference-endpoints)
         LLMProvider.BEDROCK: "amazon.nova-lite-v1:0",
         LLMProvider.SAGEMAKER: "<sagemaker_endpoint_name>",
@@ -95,7 +95,7 @@ def provider_image_model_map(provider_model_map: dict[LLMProvider, str]) -> dict
         LLMProvider.NEBIUS: "openai/gpt-oss-20b",
         LLMProvider.OPENROUTER: "google/gemini-2.5-flash-lite",
         LLMProvider.OLLAMA: "llava-phi3",  # Fast vision model compatible with OpenAI format
-        LLMProvider.FIREWORKS: "accounts/fireworks/models/qwen2p5-vl-32b-instruct",
+        LLMProvider.FIREWORKS: "accounts/fireworks/models/kimi-k2p5",
         LLMProvider.BEDROCK: "anthropic.claude-3-haiku-20240307-v1:0",  # Claude 3 Haiku with vision support
     }