Views
No views yet
| Name | Quant method | Size |
|---|---|---|
| LLMModel.Q2_K.gguf | Q2_K | 0.08GB |
| LLMModel.IQ3_XS.gguf | IQ3_XS | 0.08GB |
| LLMModel.IQ3_S.gguf | IQ3_S | 0.08GB |
| LLMModel.Q3_K_S.gguf | Q3_K_S | 0.08GB |
| LLMModel.IQ3_M.gguf | IQ3_M | 0.08GB |
| LLMModel.Q3_K.gguf | Q3_K | 0.09GB |
| LLMModel.Q3_K_M.gguf | Q3_K_M | 0.09GB |
| LLMModel.Q3_K_L.gguf | Q3_K_L | 0.09GB |
| LLMModel.IQ4_XS.gguf | IQ4_XS | 0.09GB |
| LLMModel.Q4_0.gguf | Q4_0 | 0.09GB |
| LLMModel.IQ4_NL.gguf | IQ4_NL | 0.09GB |
| LLMModel.Q4_K_S.gguf | Q4_K_S | 0.1GB |
| LLMModel.Q4_K.gguf | Q4_K | 0.1GB |
| LLMModel.Q4_K_M.gguf | Q4_K_M | 0.1GB |
| LLMModel.Q4_1.gguf | Q4_1 | 0.09GB |
| LLMModel.Q5_0.gguf | Q5_0 | 0.1GB |
| LLMModel.Q5_K_S.gguf | Q5_K_S | 0.1GB |
| LLMModel.Q5_K.gguf | Q5_K | 0.1GB |
| LLMModel.Q5_K_M.gguf | Q5_K_M | 0.1GB |
| LLMModel.Q5_1.gguf | Q5_1 | 0.1GB |
| LLMModel.Q6_K.gguf | Q6_K | 0.13GB |
| LLMModel.Q8_0.gguf | Q8_0 | 0.13GB |
pip install transformers1from transformers import AutoModelForCausalLM, AutoTokenizer
2checkpoint = "HuggingFaceTB/SmolLM2-135M-Instruct"
3
4device = "cuda" # for GPU usage or "cpu" for CPU usage
5tokenizer = AutoTokenizer.from_pretrained(checkpoint)
6# for multiple GPUs install accelerate and do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")`
7model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
8
9messages = [{"role": "user", "content": "What is gravity?"}]
10input_text=tokenizer.apply_chat_template(messages, tokenize=False)
11print(input_text)
12inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
13outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)
14print(tokenizer.decode(outputs[0]))