Downloads · 30 days
25
6% of all-time downloads
RichardErkhov/mayacinka_-_West-Ramen-7Bx4-gguf
mayacinka_-_West-Ramen-7Bx4-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
25
6% of all-time downloads
All-time downloads
437
Public
Repo size
272 GB
Likes
0
Public
Click a slice to open those files.
.gguf316 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
West-Ramen-7Bx4 - GGUF
| Name | Quant method | Size |
|---|---|---|
| West-Ramen-7Bx4.Q2_K.gguf | Q2_K | 8.24GB |
| West-Ramen-7Bx4.IQ3_XS.gguf | IQ3_XS | 9.21GB |
| West-Ramen-7Bx4.IQ3_S.gguf | IQ3_S | 9.73GB |
| West-Ramen-7Bx4.Q3_K_S.gguf | Q3_K_S | 9.72GB |
| West-Ramen-7Bx4.IQ3_M.gguf | IQ3_M | 9.92GB |
| West-Ramen-7Bx4.Q3_K.gguf | Q3_K | 10.79GB |
| West-Ramen-7Bx4.Q3_K_M.gguf | Q3_K_M | 10.79GB |
| West-Ramen-7Bx4.Q3_K_L.gguf | Q3_K_L | 11.68GB |
| West-Ramen-7Bx4.IQ4_XS.gguf | IQ4_XS | 12.15GB |
| West-Ramen-7Bx4.Q4_0.gguf | Q4_0 | 12.69GB |
| West-Ramen-7Bx4.IQ4_NL.gguf | IQ4_NL | 12.81GB |
| West-Ramen-7Bx4.Q4_K_S.gguf | Q4_K_S | 12.8GB |
| West-Ramen-7Bx4.Q4_K.gguf | Q4_K | 13.61GB |
| West-Ramen-7Bx4.Q4_K_M.gguf | Q4_K_M | 13.61GB |
| West-Ramen-7Bx4.Q4_1.gguf | Q4_1 | 14.09GB |
| West-Ramen-7Bx4.Q5_0.gguf | Q5_0 | 15.48GB |
| West-Ramen-7Bx4.Q5_K_S.gguf | Q5_K_S | 15.48GB |
| West-Ramen-7Bx4.Q5_K.gguf | Q5_K | 15.96GB |
| West-Ramen-7Bx4.Q5_K_M.gguf | Q5_K_M | 15.96GB |
| West-Ramen-7Bx4.Q5_1.gguf | Q5_1 | 16.88GB |
| West-Ramen-7Bx4.Q6_K.gguf | Q6_K | 18.46GB |
| West-Ramen-7Bx4.Q8_0.gguf | Q8_0 | 23.9GB |
license: apache-2.0 model-index:
base_model: /home/Ubuntu/Desktop/mergekit/models/Mistral-7B-Instruct-v0.2
gate_mode: hidden
dtype: bfloat16
experts:
- source_model: /home/Ubuntu/Desktop/mergekit/models/Mistral-7B-Instruct-v0.2
positive_prompts:
- "instructions"
- "concise"
- "straightforward"
- "helpful"
- "assistant"
negative_prompts:
- "vague"
- "inaccurate"
- "verbose"
- "complicated"
- "speculative"
- source_model: /home/Ubuntu/Desktop/mergekit/models/NeuralOmniWestBeaglake-7B
positive_prompts:
- "storytelling"
- "role play"
- "imagine"
- "artistic"
- "narrative"
- source_model: /home/Ubuntu/Desktop/mergekit/models/Kunoichi-DPO-v2-7B
positive_prompts:
- "reason"
- "think step by step"
- "logic"
- "knowledge"
negative_prompts:
- "artistic"
- "speculative"
- "playful"
- source_model: /home/Ubuntu/Desktop/mergekit/models/Starling-LM-7B-alpha
positive_prompts:
- "code"
- "python"
- "javascript"
- "react"
- "clear"
- "programming"
negative_prompts:
- "error"
- "art"
- "role play"
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mayacinka/West-Ramen-7Bx4"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 69.33 |
| AI2 Reasoning Challenge (25-Shot) | 67.58 |
| HellaSwag (10-Shot) | 85.52 |
| MMLU (5-Shot) | 62.69 |
| TruthfulQA (0-shot) | 61.00 |
| Winogrande (5-shot) | 81.22 |
| GSM8k (5-shot) | 58.00 |