| |
|
| | --- |
| | |
| | base_model: |
| | - defog/llama-3-sqlcoder-8b |
| | - meta-llama/Meta-Llama-3-8B-Instruct |
| | library_name: transformers |
| | tags: |
| | - mergekit |
| | - merge |
| |
|
| |
|
| | --- |
| | |
| |  |
| |
|
| | # QuantFactory/sepctrum-ties-sqlcoder-8b-GGUF |
| | This is quantized version of [arcee-ai/sepctrum-ties-sqlcoder-8b](https://huggingface.co/arcee-ai/sepctrum-ties-sqlcoder-8b) created using llama.cpp |
| |
|
| | # Original Model Card |
| |
|
| | # merge |
| |
|
| | This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
| |
|
| | ## Merge Details |
| | ### Merge Method |
| |
|
| | This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) as a base. |
| |
|
| | ### Models Merged |
| |
|
| | The following models were included in the merge: |
| | * [defog/llama-3-sqlcoder-8b](https://huggingface.co/defog/llama-3-sqlcoder-8b) |
| |
|
| | ### Configuration |
| |
|
| | The following YAML configuration was used to produce this model: |
| |
|
| | ```yaml |
| | merge_method: ties |
| | base_model: meta-llama/Meta-Llama-3-8B-Instruct |
| | models: |
| | - model: defog/llama-3-sqlcoder-8b |
| | parameters: |
| | weight: |
| | - filter: mlp.down_proj |
| | value: [0, 0, 0, 0, 0, 0, 0, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0, 0.5, 0, 0, 0, 0, 0, 0.5, 0.5, 0.5, 0.5, 0.5, 0, 0, 0] |
| | - filter: mlp.gate_proj |
| | value: [0, 0, 0, 0, 0, 0, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.5, 0.5] |
| | - filter: mlp.up_proj |
| | value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.5, 0.5, 0, 0, 0, 0, 0.5, 0, 0.5, 0, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5] |
| | - filter: self_attn.k_proj |
| | value: [0.5, 0.5, 0.5, 0, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0, 0.5, 0.5, 0.5, 0.5, 0.5, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.5, 0] |
| | - filter: self_attn.o_proj |
| | value: [0.5, 0.5, 0.5, 0.5, 0.5, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.5, 0.5, 0.5, 0.5, 0.5, 0, 0.5, 0, 0, 0, 0.5, 0.5, 0.5, 0.5, 0.5, 0] |
| | - filter: self_attn.q_proj |
| | value: [0, 0, 0.5, 0.5, 0.5, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0, 0.5, 0.5, 0.5, 0.5, 0.5] |
| | - filter: self_attn.v_proj |
| | value: [0.5, 0, 0.5, 0, 0, 0.5, 0, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0, 0, 0, 0, 0.5, 0.5, 0, 0, 0, 0, 0.5, 0, 0, 0.5, 0, 0, 0.5, 0.5] |
| | - value: [0] |
| | density: 0.75 |
| | - model: meta-llama/Meta-Llama-3-8B-Instruct |
| | parameters: |
| | weight: |
| | - filter: mlp.down_proj |
| | value: [1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 0.5, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1] |
| | - filter: mlp.gate_proj |
| | value: [1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5] |
| | - filter: mlp.up_proj |
| | value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 1, 1, 1, 1, 0.5, 1, 0.5, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5] |
| | - filter: self_attn.k_proj |
| | value: [0.5, 0.5, 0.5, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 1] |
| | - filter: self_attn.o_proj |
| | value: [0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 0.5, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 1] |
| | - filter: self_attn.q_proj |
| | value: [1, 1, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 0.5, 0.5, 0.5, 0.5, 0.5] |
| | - filter: self_attn.v_proj |
| | value: [0.5, 1, 0.5, 1, 1, 0.5, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 0.5, 0.5, 1, 1, 1, 1, 0.5, 1, 1, 0.5, 1, 1, 0.5, 0.5] |
| | - value: [1] |
| | density: 1.0 |
| | parameters: {normalize: true, int8_mask: true} |
| | dtype: bfloat16 |
| | |
| | ``` |
| |
|
| |
|
