Downloads · 30 days
43
4% of all-time downloads
RichardErkhov/MaziyarPanahi_-_calme-2.8-qwen2-7b-gguf
MaziyarPanahi_-_calme-2.8-qwen2-7b-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
43
4% of all-time downloads
All-time downloads
997
Public
Repo size
88.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf102 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
calme-2.8-qwen2-7b - GGUF
| Name | Quant method | Size |
|---|---|---|
| calme-2.8-qwen2-7b.Q2_K.gguf | Q2_K | 2.81GB |
| calme-2.8-qwen2-7b.IQ3_XS.gguf | IQ3_XS | 3.12GB |
| calme-2.8-qwen2-7b.IQ3_S.gguf | IQ3_S | 3.26GB |
| calme-2.8-qwen2-7b.Q3_K_S.gguf | Q3_K_S | 3.25GB |
| calme-2.8-qwen2-7b.IQ3_M.gguf | IQ3_M | 3.33GB |
| calme-2.8-qwen2-7b.Q3_K.gguf | Q3_K | 3.55GB |
| calme-2.8-qwen2-7b.Q3_K_M.gguf | Q3_K_M | 3.55GB |
| calme-2.8-qwen2-7b.Q3_K_L.gguf | Q3_K_L | 3.81GB |
| calme-2.8-qwen2-7b.IQ4_XS.gguf | IQ4_XS | 3.96GB |
| calme-2.8-qwen2-7b.Q4_0.gguf | Q4_0 | 4.13GB |
| calme-2.8-qwen2-7b.IQ4_NL.gguf | IQ4_NL | 4.16GB |
| calme-2.8-qwen2-7b.Q4_K_S.gguf | Q4_K_S | 4.15GB |
| calme-2.8-qwen2-7b.Q4_K.gguf | Q4_K | 4.36GB |
| calme-2.8-qwen2-7b.Q4_K_M.gguf | Q4_K_M | 4.36GB |
| calme-2.8-qwen2-7b.Q4_1.gguf | Q4_1 | 4.54GB |
| calme-2.8-qwen2-7b.Q5_0.gguf | Q5_0 | 4.95GB |
| calme-2.8-qwen2-7b.Q5_K_S.gguf | Q5_K_S | 4.95GB |
| calme-2.8-qwen2-7b.Q5_K.gguf | Q5_K | 5.07GB |
| calme-2.8-qwen2-7b.Q5_K_M.gguf | Q5_K_M | 5.07GB |
| calme-2.8-qwen2-7b.Q5_1.gguf | Q5_1 | 5.36GB |
| calme-2.8-qwen2-7b.Q6_K.gguf | Q6_K | 5.82GB |
| calme-2.8-qwen2-7b.Q8_0.gguf | Q8_0 | 7.54GB |
language:
This is a fine-tuned version of the Qwen/Qwen2-7B model. It aims to improve the base model across all benchmarks.
All GGUF models are available here: MaziyarPanahi/calme-2.8-qwen2-7b-GGUF
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 19.22 |
| IFEval (0-Shot) | 27.75 |
| BBH (3-Shot) | 25.53 |
| MATH Lvl 5 (4-Shot) | 15.63 |
| GPQA (0-shot) | 5.82 |
| MuSR (0-shot) | 12.06 |
| MMLU-PRO (5-shot) | 28.51 |
This model uses ChatML prompt template:
<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{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-2.8-qwen2-7b")
pipe(messages)
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.8-qwen2-7b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.8-qwen2-7b")