Views
No views yet
| Name | Quant method | Size |
|---|---|---|
| tinyllama_instruct.Q2_K.gguf | Q2_K | 0.4GB |
| tinyllama_instruct.IQ3_XS.gguf | IQ3_XS | 0.44GB |
| tinyllama_instruct.IQ3_S.gguf | IQ3_S | 0.47GB |
| tinyllama_instruct.Q3_K_S.gguf | Q3_K_S | 0.47GB |
| tinyllama_instruct.IQ3_M.gguf | IQ3_M | 0.48GB |
| tinyllama_instruct.Q3_K.gguf | Q3_K | 0.51GB |
| tinyllama_instruct.Q3_K_M.gguf | Q3_K_M | 0.51GB |
| tinyllama_instruct.Q3_K_L.gguf | Q3_K_L | 0.55GB |
| tinyllama_instruct.IQ4_XS.gguf | IQ4_XS | 0.57GB |
| tinyllama_instruct.Q4_0.gguf | Q4_0 | 0.59GB |
| tinyllama_instruct.IQ4_NL.gguf | IQ4_NL | 0.6GB |
| tinyllama_instruct.Q4_K_S.gguf | Q4_K_S | 0.6GB |
| tinyllama_instruct.Q4_K.gguf | Q4_K | 0.62GB |
| tinyllama_instruct.Q4_K_M.gguf | Q4_K_M | 0.62GB |
| tinyllama_instruct.Q4_1.gguf | Q4_1 | 0.65GB |
| tinyllama_instruct.Q5_0.gguf | Q5_0 | 0.71GB |
| tinyllama_instruct.Q5_K_S.gguf | Q5_K_S | 0.71GB |
| tinyllama_instruct.Q5_K.gguf | Q5_K | 0.73GB |
| tinyllama_instruct.Q5_K_M.gguf | Q5_K_M | 0.73GB |
| tinyllama_instruct.Q5_1.gguf | Q5_1 | 0.77GB |
| tinyllama_instruct.Q6_K.gguf | Q6_K | 0.84GB |
| tinyllama_instruct.Q8_0.gguf | Q8_0 | 1.09GB |
1from transformers import pipeline
2
3question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
4generator = pipeline("text-generation", model="jayanth070/tinyllama_instruct", device="cuda")
5output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
6print(output["generated_text"])
1@misc{vonwerra2022trl,
2 title = {{TRL: Transformer Reinforcement Learning}},
3 author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
4 year = 2020,
5 journal = {GitHub repository},
6 publisher = {GitHub},
7 howpublished = {\url{https://github.com/huggingface/trl}}
8}