You can deploy this model and start earning money today!

RichardErkhov/
miguelcarv_-_phi-1_5-slimorca-gguf

Name: miguelcarv_-_phi-1_5-slimorca-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

phi-1_5-slimorca - GGUF

Model creator: https://huggingface.co/miguelcarv/
Original model: https://huggingface.co/miguelcarv/phi-1_5-slimorca/

Name	Quant method	Size
phi-1_5-slimorca.Q2_K.gguf	Q2_K	0.54GB
phi-1_5-slimorca.Q3_K_S.gguf	Q3_K_S	0.61GB
phi-1_5-slimorca.Q3_K.gguf	Q3_K	0.69GB
phi-1_5-slimorca.Q3_K_M.gguf	Q3_K_M	0.69GB
phi-1_5-slimorca.Q3_K_L.gguf	Q3_K_L	0.75GB
phi-1_5-slimorca.IQ4_XS.gguf	IQ4_XS	0.74GB
phi-1_5-slimorca.Q4_0.gguf	Q4_0	0.77GB
phi-1_5-slimorca.IQ4_NL.gguf	IQ4_NL	0.78GB
phi-1_5-slimorca.Q4_K_S.gguf	Q4_K_S	0.78GB
phi-1_5-slimorca.Q4_K.gguf	Q4_K	0.83GB
phi-1_5-slimorca.Q4_K_M.gguf	Q4_K_M	0.83GB
phi-1_5-slimorca.Q4_1.gguf	Q4_1	0.85GB
phi-1_5-slimorca.Q5_0.gguf	Q5_0	0.92GB
phi-1_5-slimorca.Q5_K_S.gguf	Q5_K_S	0.92GB
phi-1_5-slimorca.Q5_K.gguf	Q5_K	0.96GB
phi-1_5-slimorca.Q5_K_M.gguf	Q5_K_M	0.96GB
phi-1_5-slimorca.Q5_1.gguf	Q5_1	1.0GB
phi-1_5-slimorca.Q6_K.gguf	Q6_K	1.09GB
phi-1_5-slimorca.Q8_0.gguf	Q8_0	1.41GB

Original model description:

For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1

Doc / guide: https://huggingface.co/docs/hub/model-cards

{}

Model Card for Phi 1.5 SlimOrca

Phi 1.5 finetuned on SlimOrca-Dedup. This model was trained with the goal of giving Phi 1.5 the ablity to generate the EOS token together with being capable of doing beam search. It can also follow custom system prompts as shown in the example below.

Model Details

How to Get Started with the Model

python

import torch
import transformers

model = transformers.AutoModelForCausalLM.from_pretrained(
    "miguelcarv/phi-1_5-slimorca",
    trust_remote_code=True
)
tokenizer = transformers.AutoTokenizer.from_pretrained("microsoft/phi-1_5")


SYSTEM_PROMPT = "You are an AI assistant. You will be given a task. You must generate a detailed and long answer."
input_text = f"""{SYSTEM_PROMPT}

Instruction: Give me the first 5 prime numbers and explain what prime numbers are.
Output:"""

with torch.no_grad():
    outputs = model.generate(
        tokenizer(input_text, return_tensors="pt")['input_ids'],
        max_length=1024,
        num_beams = 3,
        eos_token_id = tokenizer.eos_token_id
    )
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Details

Trained for one epoch on SlimOrca-Dedup
Learning rate: 2e-5
Cosine learning rate decay
Optimizer: AdamW
Batch size: 256
Trained with FP32

RichardErkhov/miguelcarv_-_phi-1_5-slimorca-gguf