Views
No views yet
| Name | Quant method | Size |
|---|---|---|
| mamba-130m.Q2_K.gguf | Q2_K | 0.08GB |
| mamba-130m.IQ3_XS.gguf | IQ3_XS | 0.09GB |
| mamba-130m.IQ3_S.gguf | IQ3_S | 0.09GB |
| mamba-130m.Q3_K_S.gguf | Q3_K_S | 0.09GB |
| mamba-130m.IQ3_M.gguf | IQ3_M | 0.09GB |
| mamba-130m.Q3_K.gguf | Q3_K | 0.09GB |
| mamba-130m.Q3_K_M.gguf | Q3_K_M | 0.09GB |
| mamba-130m.Q3_K_L.gguf | Q3_K_L | 0.09GB |
| mamba-130m.IQ4_XS.gguf | IQ4_XS | 0.09GB |
| mamba-130m.Q4_0.gguf | Q4_0 | 0.1GB |
| mamba-130m.IQ4_NL.gguf | IQ4_NL | 0.1GB |
| mamba-130m.Q4_K_S.gguf | Q4_K_S | 0.1GB |
| mamba-130m.Q4_K.gguf | Q4_K | 0.1GB |
| mamba-130m.Q4_K_M.gguf | Q4_K_M | 0.1GB |
| mamba-130m.Q4_1.gguf | Q4_1 | 0.1GB |
| mamba-130m.Q5_0.gguf | Q5_0 | 0.11GB |
| mamba-130m.Q5_K_S.gguf | Q5_K_S | 0.11GB |
| mamba-130m.Q5_K.gguf | Q5_K | 0.11GB |
| mamba-130m.Q5_K_M.gguf | Q5_K_M | 0.11GB |
| mamba-130m.Q5_1.gguf | Q5_1 | 0.11GB |
| mamba-130m.Q6_K.gguf | Q6_K | 0.12GB |
| mamba-130m.Q8_0.gguf | Q8_0 | 0.14GB |
1>>> from transformers import MambaConfig, MambaForCausalLM, AutoTokenizer
2>>> import torch
3
4>>> tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b", padding_side = "left")
5>>> tokenizer.pad_token = tokenizer.eos_token
6
7>>> model = MambaForCausalLM.from_pretrained("state-spaces/mamba-130m", vocab_size=50280, num_hidden_layers=24, torch_dtype=torch.float32)
8>>> model.config.use_cache = True
9>>> input_ids = tokenizer(["Hey how are you doing?", "Explain how soy sauce is made"], padding=True, return_tensors= "pt")["input_ids"]
10
11>>> out = model.generate(input_ids, max_new_tokens=10)
12>>> print(tokenizer.batch_decode(out))
13["<|endoftext|>Hey how are you doing?\n\nI'm a newbie to the game", 'Explain how soy sauce is made.\n\n1. Add the soy sauce to']