Update README.md

README.md

@@ -133,11 +133,10 @@ Use the `main` transformers branch or pass `trust_remote_code=True` with a relea
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-model_id = "arcee-ai/Trinity-Large-Preview"
+model_id = "arcee-ai/Trinity-Large-Preview-FP8"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
-    torch_dtype=torch.bfloat16,
     device_map="auto",
     trust_remote_code=True
 )
@@ -156,9 +155,9 @@ outputs = model.generate(
     input_ids,
     max_new_tokens=256,
     do_sample=True,
-    temperature=0.5,
+    temperature=0.8,
     top_k=50,
-    top_p=0.95
+    top_p=0.8
 )
 
 response = tokenizer.decode(outputs[0], skip_special_tokens=True)
@@ -170,24 +169,11 @@ print(response)
 Supported in VLLM release 0.11.1+
 
 ```bash
-vllm serve arcee-ai/Trinity-Large-Preview \
-  --dtype bfloat16 \
+vllm serve arcee-ai/Trinity-Large-Preview-FP8 \
   --enable-auto-tool-choice \
   --tool-call-parser hermes
 ```
 
-### llama.cpp
-
-Supported in llama.cpp release b7061+
-
-```bash
-llama-server -hf arcee-ai/Trinity-Large-Preview-GGUF:q4_k_m
-```
-
-### LM Studio
-
-Supported in the latest LM Studio runtime. Search for `arcee-ai/Trinity-Large-Preview-GGUF` in Model Search.
-
 ### API
 
 Available on OpenRouter: