llasa-3b-upscaled

1
3.0B
llama
by
mergekit-community
Language Model
OTHER
3B params
New
0 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
7GB+ RAM
Mobile
Laptop
Server
Quick Summary

This is a merge of pre-trained language models created using mergekit.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
3GB+ RAM

Code Examples

Configurationyaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 21]
    model: srinivasbilla/llasa-3b
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [22, 28]
    model: srinivasbilla/llasa-3b
Configurationyaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 21]
    model: srinivasbilla/llasa-3b
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [22, 28]
    model: srinivasbilla/llasa-3b
Configurationyaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 21]
    model: srinivasbilla/llasa-3b
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [22, 28]
    model: srinivasbilla/llasa-3b
Configurationyaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 21]
    model: srinivasbilla/llasa-3b
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [22, 28]
    model: srinivasbilla/llasa-3b
Configurationyaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 21]
    model: srinivasbilla/llasa-3b
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [22, 28]
    model: srinivasbilla/llasa-3b
Configurationyaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 21]
    model: srinivasbilla/llasa-3b
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [22, 28]
    model: srinivasbilla/llasa-3b
Configurationyaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 21]
    model: srinivasbilla/llasa-3b
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [22, 28]
    model: srinivasbilla/llasa-3b
Configurationyaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 21]
    model: srinivasbilla/llasa-3b
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [22, 28]
    model: srinivasbilla/llasa-3b
Configurationyaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 21]
    model: srinivasbilla/llasa-3b
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [22, 28]
    model: srinivasbilla/llasa-3b
Configurationyaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 21]
    model: srinivasbilla/llasa-3b
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [11, 22]
    model: srinivasbilla/llasa-3b
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [22, 28]
    model: srinivasbilla/llasa-3b

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.