Downloads · 30 days
133
9% of all-time downloads
RichardErkhov/MaziyarPanahi_-_calme-2.1-phi3.5-4b-gguf
MaziyarPanahi_-_calme-2.1-phi3.5-4b-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
133
9% of all-time downloads
All-time downloads
1.6K
Public
Repo size
43.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf51.1 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
calme-2.1-phi3.5-4b - GGUF
| Name | Quant method | Size |
|---|---|---|
| calme-2.1-phi3.5-4b.Q2_K.gguf | Q2_K | 1.32GB |
| calme-2.1-phi3.5-4b.IQ3_XS.gguf | IQ3_XS | 1.51GB |
| calme-2.1-phi3.5-4b.IQ3_S.gguf | IQ3_S | 1.57GB |
| calme-2.1-phi3.5-4b.Q3_K_S.gguf | Q3_K_S | 1.57GB |
| calme-2.1-phi3.5-4b.IQ3_M.gguf | IQ3_M | 1.73GB |
| calme-2.1-phi3.5-4b.Q3_K.gguf | Q3_K | 1.82GB |
| calme-2.1-phi3.5-4b.Q3_K_M.gguf | Q3_K_M | 1.82GB |
| calme-2.1-phi3.5-4b.Q3_K_L.gguf | Q3_K_L | 1.94GB |
| calme-2.1-phi3.5-4b.IQ4_XS.gguf | IQ4_XS | 1.93GB |
| calme-2.1-phi3.5-4b.Q4_0.gguf | Q4_0 | 2.03GB |
| calme-2.1-phi3.5-4b.IQ4_NL.gguf | IQ4_NL | 2.04GB |
| calme-2.1-phi3.5-4b.Q4_K_S.gguf | Q4_K_S | 2.04GB |
| calme-2.1-phi3.5-4b.Q4_K.gguf | Q4_K | 2.23GB |
| calme-2.1-phi3.5-4b.Q4_K_M.gguf | Q4_K_M | 2.23GB |
| calme-2.1-phi3.5-4b.Q4_1.gguf | Q4_1 | 2.24GB |
| calme-2.1-phi3.5-4b.Q5_0.gguf | Q5_0 | 2.46GB |
| calme-2.1-phi3.5-4b.Q5_K_S.gguf | Q5_K_S | 2.46GB |
| calme-2.1-phi3.5-4b.Q5_K.gguf | Q5_K | 2.62GB |
| calme-2.1-phi3.5-4b.Q5_K_M.gguf | Q5_K_M | 2.62GB |
| calme-2.1-phi3.5-4b.Q5_1.gguf | Q5_1 | 2.68GB |
| calme-2.1-phi3.5-4b.Q6_K.gguf | Q6_K | 2.92GB |
| calme-2.1-phi3.5-4b.Q8_0.gguf | Q8_0 | 3.78GB |
language:
This model is a fine-tuned version of the microsoft/Phi-3.5-mini-instruct, pushing the boundaries of natural language understanding and generation even further. My goal was to create a versatile and robust model that excels across a wide range of benchmarks and real-world applications.
This model is suitable for a wide range of applications, including but not limited to:
Here are the quants: calme-2.1-phi3.5-4b-GGUF
Coming soon!
This model uses ChatML prompt template:
<|system|>
You are a helpful assistant.<|end|>
<|user|>
How to explain Internet for a medieval knight?<|end|>
<|assistant|>
# Use a pipeline as a high-level helper
from transformers import pipeline
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="MaziyarPanahi/calme-2.1-phi3.5-4b")
pipe(messages)
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.1-phi3.5-4b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.1-phi3.5-4b")
As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 27.01 |
| IFEval (0-Shot) | 56.59 |
| BBH (3-Shot) | 36.11 |
| MATH Lvl 5 (4-Shot) | 14.43 |
| GPQA (0-shot) | 12.53 |
| MuSR (0-shot) | 9.77 |
| MMLU-PRO (5-shot) | 32.61 |