Instructions to use Quazim0t0/Escarda-86M-Identity-Anti-DEG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Quazim0t0/Escarda-86M-Identity-Anti-DEG with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Quazim0t0/Escarda-86M-Identity-Anti-DEG", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Quazim0t0/Escarda-86M-Identity-Anti-DEG", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Quazim0t0/Escarda-86M-Identity-Anti-DEG with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Quazim0t0/Escarda-86M-Identity-Anti-DEG"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Quazim0t0/Escarda-86M-Identity-Anti-DEG",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Quazim0t0/Escarda-86M-Identity-Anti-DEG

SGLang

How to use Quazim0t0/Escarda-86M-Identity-Anti-DEG with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Quazim0t0/Escarda-86M-Identity-Anti-DEG" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Quazim0t0/Escarda-86M-Identity-Anti-DEG",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Quazim0t0/Escarda-86M-Identity-Anti-DEG" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Quazim0t0/Escarda-86M-Identity-Anti-DEG",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Quazim0t0/Escarda-86M-Identity-Anti-DEG with Docker Model Runner:
```
docker model run hf.co/Quazim0t0/Escarda-86M-Identity-Anti-DEG
```

Escarda-86M-Identity — Anti-DEG

A tuned build of Escarda-86M-Identity (86M parameters, SpikeWhaleLM) that follows a change of subject in conversation while keeping the Escarda identity.

Ships as a fully merged standalone model — no adapters or base model needed.

Why this build exists

The Escarda-86M-Base-JL-Anti-DEG build scores higher on factual questions but has no persona — asked "who are you" it answers "I am a young woman." This build applies the same treatment to the identity-tuned checkpoint instead, so the model still knows what it is:

"Who are you?" → "I'm Escarda, a helpful AI assistant created by Quazim0t0 (Dean Byrne)."

Scores

Loops measured on 6 prompt stems; topic adherence on 6 held-out multi-turn topic switches; factual accuracy on 73 unambiguous questions. All at effort n=2 with a 24-token minimum length.

	`Escarda-86M-Identity`	this model
topic adherence (1.0 = fully follows a subject change)	0.75	1.00
topic switches answered on the old subject	0 / 6	0 / 6
repetition loops	0 / 6	0 / 6
answers as "Escarda"	2 / 2	2 / 2
factual accuracy (73 items)	0.110 ± 0.037	0.068 ± 0.030

Read the factual row honestly: the difference is −0.042 with a 0.048 standard error on the difference — inside one standard error, i.e. not a measurable change. This build buys topic adherence at no detectable factual cost; it does not improve factual accuracy. For that, Escarda-86M-Base-JL-Anti-DEG scores 0.260 ± 0.051 (2.4σ better) but loses the persona entirely.

At 86M parameters this model is not a source of reliable facts either way.

Decoding matters

The scores above are measured with effort decoding (effort_decode.py, included) plus a 24-token minimum reply length. Greedy decoding does not reach them. Effort levels trade compute for quality: low draws a single sample, high draws six and returns the best.

python effort_decode.py --model Quazim0t0/Escarda-86M-Identity-Anti-DEG \
  --prompt "<|im_start|>user\nHow do I change a car tyre?<|im_end|>\n<|im_start|>assistant\n" \
  --question "How do I change a car tyre?" --level high

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained(
    "Quazim0t0/Escarda-86M-Identity-Anti-DEG", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    "Quazim0t0/Escarda-86M-Identity-Anti-DEG",
    trust_remote_code=True, dtype=torch.float32).eval()

Prompt format is ChatML:

<|im_start|>user
{question}<|im_end|>
<|im_start|>assistant

Limitations

86M parameters, and not instruction-tuned for factual accuracy. Output is often confidently wrong; do not rely on it for facts.
Native 4096-token context (no Jet-Long on this checkpoint).
Custom architecture and tokenizer — trust_remote_code=True is required.

Downloads last month: -

Safetensors

Model size

97.3M params

Tensor type

F32

Model tree for Quazim0t0/Escarda-86M-Identity-Anti-DEG

Base model

Quazim0t0/Escarda-86M-Identity

Finetuned

(2)

this model