Views
No views yet
| Name | Quant method | Size |
|---|---|---|
| Llama3-12b.Q2_K.gguf | Q2_K | 4.16GB |
| Llama3-12b.IQ3_XS.gguf | IQ3_XS | 4.61GB |
| Llama3-12b.IQ3_S.gguf | IQ3_S | 4.83GB |
| Llama3-12b.Q3_K_S.gguf | Q3_K_S | 4.81GB |
| Llama3-12b.IQ3_M.gguf | IQ3_M | 4.98GB |
| Llama3-12b.Q3_K.gguf | Q3_K | 5.3GB |
| Llama3-12b.Q3_K_M.gguf | Q3_K_M | 5.3GB |
| Llama3-12b.Q3_K_L.gguf | Q3_K_L | 5.73GB |
| Llama3-12b.IQ4_XS.gguf | IQ4_XS | 5.93GB |
| Llama3-12b.Q4_0.gguf | Q4_0 | 6.17GB |
| Llama3-12b.IQ4_NL.gguf | IQ4_NL | 6.23GB |
| Llama3-12b.Q4_K_S.gguf | Q4_K_S | 6.21GB |
| Llama3-12b.Q4_K.gguf | Q4_K | 6.53GB |
| Llama3-12b.Q4_K_M.gguf | Q4_K_M | 6.53GB |
| Llama3-12b.Q4_1.gguf | Q4_1 | 6.81GB |
| Llama3-12b.Q5_0.gguf | Q5_0 | 7.45GB |
| Llama3-12b.Q5_K_S.gguf | Q5_K_S | 7.45GB |
| Llama3-12b.Q5_K.gguf | Q5_K | 7.64GB |
| Llama3-12b.Q5_K_M.gguf | Q5_K_M | 7.64GB |
| Llama3-12b.Q5_1.gguf | Q5_1 | 8.09GB |
| Llama3-12b.Q6_K.gguf | Q6_K | 8.81GB |
| Llama3-12b.Q8_0.gguf | Q8_0 | 11.41GB |
1slices:
2 - sources:
3 - model: abhishek/autotrain-llama3-orpo-v2
4 layer_range: [0, 24]
5 - sources:
6 - model: abhishek/autotrain-llama3-orpo-v2
7 layer_range: [8, 32]
8merge_method: passthrough
9dtype: bfloat161!pip install -qU transformers accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "KingNish/NeuralPipe-7B-slerp"
8messages = [{"role": "user", "content": "What is a large language model?"}]
9
10tokenizer = AutoTokenizer.from_pretrained(model)
11prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
12pipeline = transformers.pipeline(
13 "text-generation",
14 model=model,
15 torch_dtype=torch.float16,
16 device_map="auto",
17)
18
19outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
20print(outputs[0]["generated_text"])