Quantization made by Richard Erkhov.
llama-3-experiment-v1-9B - GGUF
- Model creator: https://huggingface.co/grimjim/
- Original model: https://huggingface.co/grimjim/llama-3-experiment-v1-9B/
Original model description:
language: - en base_model: - meta-llama/Meta-Llama-3-8B-Instruct library_name: transformers tags: - meta - llama-3 - pytorch - mergekit - merge license: llama3 license_link: LICENSE pipeline_tag: text-generation widget: - example_title: Hello messages: - role: user content: Hey my name is Corwin! How are you? - example_title: Hellriding out of Amber messages: - role: system content: You are a helpful and honest assistant. Please, respond concisely and truthfully. - role: user content: Can you recommend a good destination for a hellride out of Amber? inference: parameters: max_new_tokens: 300 stop: - <|end_of_text|> - <|eot_id|> model-index: - name: grimjim/grimjim/llama-3-experiment-v1-9B 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: 66.41 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/grimjim/llama-3-experiment-v1-9B 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: 78.56 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B 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: 66.71 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B 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: 50.7 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B 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: 75.93 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B 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: 65.88 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B name: Open LLM Leaderboard
llama-3-experiment-v1-9B
This is an experimental merge, replicating additional layers to the model without post-merge healing. There is damage to the model, but it appears to be tolerable as is; the performance difference in benchmarks from the original 8B Instruct model does not appear to be significant. The resulting impact on narrative text completion may also be of interest.
Light testing performed with instruct prompting and the following sampler settings:
- temp=1 and minP=0.02
- temp=1 and smoothing factor=0.33
Full weights: grimjim/llama-3-experiment-v1-9B
GGUF quants: grimjim/llama-3-experiment-v1-9B-GGUF
This is a merge of pre-trained language model meta-llama/Meta-Llama-3-8B-Instruct created using mergekit.
Built with Meta Llama 3.
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
- meta-llama/Meta-Llama-3-8B-Instruct
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: meta-llama/Meta-Llama-3-8B-Instruct
layer_range: [0, 12]
- sources:
- model: meta-llama/Meta-Llama-3-8B-Instruct
layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
- Downloads last month
- 392