metadata
tags:
- merge
- mergekit
- lazymergekit
- cognitivecomputations/dolphin-2.8-mistral-7b-v02
- Nondzu/Mistral-7B-Instruct-v0.2-code-ft
base_model:
- cognitivecomputations/dolphin-2.8-mistral-7b-v02
- Nondzu/Mistral-7B-Instruct-v0.2-code-ft
- cognitivecomputations/dolphin-2.8-mistral-7b-v02
- Nondzu/Mistral-7B-Instruct-v0.2-code-ft
- cognitivecomputations/dolphin-2.8-mistral-7b-v02
dolphin-2.8-mistral-11b-v02-code-ft
dolphin-2.8-mistral-11b-v02-code-ft is a merge of the following models using LazyMergekit:
- cognitivecomputations/dolphin-2.8-mistral-7b-v02
- Nondzu/Mistral-7B-Instruct-v0.2-code-ft
- cognitivecomputations/dolphin-2.8-mistral-7b-v02
- Nondzu/Mistral-7B-Instruct-v0.2-code-ft
- cognitivecomputations/dolphin-2.8-mistral-7b-v02
🧩 Configuration
slices:
- sources:
- model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
layer_range: [0, 8]
- sources:
- model: Nondzu/Mistral-7B-Instruct-v0.2-code-ft
layer_range: [4, 14]
- sources:
- model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
layer_range: [10, 20]
- sources:
- model: Nondzu/Mistral-7B-Instruct-v0.2-code-ft
layer_range: [16, 26]
- sources:
- model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
layer_range: [22, 32]
merge_method: passthrough
base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
dtype: float16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "frost19k/dolphin-2.8-mistral-11b-v02-code-ft"
messages = [{"role": "user", "content": "What is a large language model?"}]
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"])