Views
No views yet
| Name | Quant method | Size |
|---|---|---|
| context-3B.Q2_K.gguf | Q2_K | 1.19GB |
| context-3B.IQ3_XS.gguf | IQ3_XS | 1.3GB |
| context-3B.IQ3_S.gguf | IQ3_S | 1.36GB |
| context-3B.Q3_K_S.gguf | Q3_K_S | 1.35GB |
| context-3B.IQ3_M.gguf | IQ3_M | 1.39GB |
| context-3B.Q3_K.gguf | Q3_K | 1.48GB |
| context-3B.Q3_K_M.gguf | Q3_K_M | 1.48GB |
| context-3B.Q3_K_L.gguf | Q3_K_L | 1.59GB |
| context-3B.IQ4_XS.gguf | IQ4_XS | 1.63GB |
| context-3B.Q4_0.gguf | Q4_0 | 1.7GB |
| context-3B.IQ4_NL.gguf | IQ4_NL | 1.71GB |
| context-3B.Q4_K_S.gguf | Q4_K_S | 1.71GB |
| context-3B.Q4_K.gguf | Q4_K | 1.8GB |
| context-3B.Q4_K_M.gguf | Q4_K_M | 1.8GB |
| context-3B.Q4_1.gguf | Q4_1 | 1.86GB |
| context-3B.Q5_0.gguf | Q5_0 | 2.02GB |
| context-3B.Q5_K_S.gguf | Q5_K_S | 2.02GB |
| context-3B.Q5_K.gguf | Q5_K | 2.07GB |
| context-3B.Q5_K_M.gguf | Q5_K_M | 2.07GB |
| context-3B.Q5_1.gguf | Q5_1 | 2.18GB |
| context-3B.Q6_K.gguf | Q6_K | 2.36GB |
| context-3B.Q8_0.gguf | Q8_0 | 3.06GB |
1
2from transformers import AutoModelForCausalLM, AutoTokenizer
3
4model_path = "PATH_TO_THIS_REPO"
5
6tokenizer = AutoTokenizer.from_pretrained(model_path)
7model = AutoModelForCausalLM.from_pretrained(
8 model_path,
9 device_map="auto",
10 torch_dtype='auto'
11).eval()
12
13# Prompt content: "hi"
14messages = [
15 {"role": "user", "content": "hi"}
16]
17
18input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
19output_ids = model.generate(input_ids.to('cuda'))
20response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
21
22# Model response: "Hello! How can I assist you today?"
23print(response)