Views
No views yet
| Name | Quant method | Size |
|---|---|---|
| Neuraljack-12B-MoE.Q2_K.gguf | Q2_K | 4.43GB |
| Neuraljack-12B-MoE.IQ3_XS.gguf | IQ3_XS | 4.95GB |
| Neuraljack-12B-MoE.IQ3_S.gguf | IQ3_S | 5.22GB |
| Neuraljack-12B-MoE.Q3_K_S.gguf | Q3_K_S | 5.2GB |
| Neuraljack-12B-MoE.IQ3_M.gguf | IQ3_M | 5.35GB |
| Neuraljack-12B-MoE.Q3_K.gguf | Q3_K | 5.78GB |
| Neuraljack-12B-MoE.Q3_K_M.gguf | Q3_K_M | 5.78GB |
| Neuraljack-12B-MoE.Q3_K_L.gguf | Q3_K_L | 6.27GB |
| Neuraljack-12B-MoE.IQ4_XS.gguf | IQ4_XS | 6.5GB |
| Neuraljack-12B-MoE.Q4_0.gguf | Q4_0 | 6.78GB |
| Neuraljack-12B-MoE.IQ4_NL.gguf | IQ4_NL | 6.85GB |
| Neuraljack-12B-MoE.Q4_K_S.gguf | Q4_K_S | 6.84GB |
| Neuraljack-12B-MoE.Q4_K.gguf | Q4_K | 7.25GB |
| Neuraljack-12B-MoE.Q4_K_M.gguf | Q4_K_M | 7.25GB |
| Neuraljack-12B-MoE.Q4_1.gguf | Q4_1 | 7.52GB |
| Neuraljack-12B-MoE.Q5_0.gguf | Q5_0 | 8.26GB |
| Neuraljack-12B-MoE.Q5_K_S.gguf | Q5_K_S | 8.26GB |
| Neuraljack-12B-MoE.Q5_K.gguf | Q5_K | 8.51GB |
| Neuraljack-12B-MoE.Q5_K_M.gguf | Q5_K_M | 8.51GB |
| Neuraljack-12B-MoE.Q5_1.gguf | Q5_1 | 9.01GB |
| Neuraljack-12B-MoE.Q6_K.gguf | Q6_K | 9.84GB |
| Neuraljack-12B-MoE.Q8_0.gguf | Q8_0 | 12.75GB |
1base_model: allknowingroger/JaskierMistral-7B-slerp
2experts:
3 - source_model: allknowingroger/JaskierMistral-7B-slerp
4 positive_prompts: ["why"]
5 - source_model: Kukedlc/NeuralMaths-Experiment-7b
6 positive_prompts: ["math"]1!pip install -qU transformers bitsandbytes accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "allknowingroger/Neuraljack-12B-MoE"
8
9tokenizer = AutoTokenizer.from_pretrained(model)
10pipeline = transformers.pipeline(
11 "text-generation",
12 model=model,
13 model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
14)
15
16messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
17prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
18outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
19print(outputs[0]["generated_text"])