README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - kodonho/Solar-OrcaDPO-Solar-Instruct-SLERP
  - VAGOsolutions/SauerkrautLM-SOLAR-Instruct
model-index:
  - name: SOLAR-10.7B-Instruct-ties
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 70.9
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=naseerfaheem/SOLAR-10.7B-Instruct-ties
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 88.58
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=naseerfaheem/SOLAR-10.7B-Instruct-ties
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 66.34
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=naseerfaheem/SOLAR-10.7B-Instruct-ties
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 71.88
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=naseerfaheem/SOLAR-10.7B-Instruct-ties
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 83.5
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=naseerfaheem/SOLAR-10.7B-Instruct-ties
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 64.06
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=naseerfaheem/SOLAR-10.7B-Instruct-ties
          name: Open LLM Leaderboard

SOLAR-10.7B-Instruct-ties

SOLAR-10.7B-Instruct-ties is a merge of the following models using mergekit:

• kodonho/Solar-OrcaDPO-Solar-Instruct-SLERP
• VAGOsolutions/SauerkrautLM-SOLAR-Instruct

🧩 Configuration

models:
  - model: upstage/SOLAR-10.7B-Instruct-v1.0
    # no parameters necessary for base model
  - model: kodonho/Solar-OrcaDPO-Solar-Instruct-SLERP
    parameters:
      density: 0.5
      weight: 0.5
  - model: VAGOsolutions/SauerkrautLM-SOLAR-Instruct
    parameters:
      density: 0.5
      weight: 0.3
merge_method: ties
base_model: upstage/SOLAR-10.7B-Instruct-v1.0
parameters:
  normalize: true
dtype: float16

💻 Example Python Code

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_name_or_path = "nfaheem/SOLAR-10.7B-Instruct-ties"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             revision="main")

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

prompt = "Write a story about llamas"
system_message = "You are a story writing assistant"
prompt_template=f'''{prompt}
'''

print("\n\n*** Generate:")

input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))

# Inference can also be done using transformers' pipeline

print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    repetition_penalty=1.1
)

print(pipe(prompt_template)[0]['generated_text'])

📋 Summary Eval:

Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
74.24	70.9	88.58	66.34	71.88	83.5	64.06

📈 Huggingface Leaderboard

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.21
AI2 Reasoning Challenge (25-Shot)	70.90
HellaSwag (10-Shot)	88.58
MMLU (5-Shot)	66.34
TruthfulQA (0-shot)	71.88
Winogrande (5-shot)	83.50
GSM8k (5-shot)	64.06