merge
This is a merge of cognitivecomputations/dolphin-2.9.1-llama-3-70b into itsself created using mergekit. Using the same technique as Llama-3-120b.
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- layer_range: [0, 20]
model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
- sources:
- layer_range: [10, 30]
model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
- sources:
- layer_range: [20, 40]
model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
- sources:
- layer_range: [30, 50]
model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
- sources:
- layer_range: [40, 60]
model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
- sources:
- layer_range: [50, 70]
model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
- sources:
- layer_range: [60, 80]
model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
merge_method: passthrough
dtype: float16
This model uses ChatML prompt template format.
example:
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "DarqueDante/LLama-3-Dolphin-2.9.1-120b"
messages = [{"role": "user", "content": "Who is Andrej Karpathy?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
π» Testing
I have not ran any benchmarking tests on the model yet, though that is my goal for this holiday weekend.
- Downloads last month
- 53
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.