unclemusclez / smollm-135m-instruct-devinator

SmolLM 135M Instruct Trained on DEVINator Data for Open Hands (Open Devin)

6 Pulls Updated 3 days ago

3 days ago

d24a131eaedd · 271MB

model
llama
·
135M
·
F16
params
{"stop":["<|im_start|>","<|im_end|>"]}
template
{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user {{ .Prompt }}<|im_end|> {{ end }}<|im_start|>assistant {{ .Response }}<|im_end|>

Readme

https://huggingface.co/unclemusclez/SmolLM-135M-Instruct-DEVINator-v0.1
https://huggingface.co/unclemusclez/SmolLM-135M-Instruct-DEVINator-v0.2

library_name: sentence-transformers
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- autotrain
base_model: HuggingFaceTB/SmolLM-135M-Instruct
widget:
- source_sentence: ‘search_query: i love autotrain’
sentences:
- ‘search_query: huggingface auto train’
- ‘search_query: hugging face auto train’
- ‘search_query: i love autotrain’
pipeline_tag: sentence-similarity
datasets:

- skratos115/opendevin_DataDevinator

Model Trained Using AutoTrain

  • Problem type: Sentence Transformers

Validation Metrics

No validation metrics available

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the Hugging Face Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'search_query: autotrain',
    'search_query: auto train',
    'search_query: i love autotrain',
]
embeddings = model.encode(sentences)
print(embeddings.shape)

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)