| Quantization made by Richard Erkhov. | |
| [Github](https://github.com/RichardErkhov) | |
| [Discord](https://discord.gg/pvy7H8DZMG) | |
| [Request more models](https://github.com/RichardErkhov/quant_request) | |
| lmlab-mistral-1b-untrained - GGUF | |
| - Model creator: https://huggingface.co/lmlab/ | |
| - Original model: https://huggingface.co/lmlab/lmlab-mistral-1b-untrained/ | |
| | Name | Quant method | Size | | |
| | ---- | ---- | ---- | | |
| | [lmlab-mistral-1b-untrained.Q2_K.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q2_K.gguf) | Q2_K | 0.44GB | | |
| | [lmlab-mistral-1b-untrained.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.IQ3_XS.gguf) | IQ3_XS | 0.49GB | | |
| | [lmlab-mistral-1b-untrained.IQ3_S.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.IQ3_S.gguf) | IQ3_S | 0.5GB | | |
| | [lmlab-mistral-1b-untrained.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q3_K_S.gguf) | Q3_K_S | 0.5GB | | |
| | [lmlab-mistral-1b-untrained.IQ3_M.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.IQ3_M.gguf) | IQ3_M | 0.51GB | | |
| | [lmlab-mistral-1b-untrained.Q3_K.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q3_K.gguf) | Q3_K | 0.54GB | | |
| | [lmlab-mistral-1b-untrained.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q3_K_M.gguf) | Q3_K_M | 0.54GB | | |
| | [lmlab-mistral-1b-untrained.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q3_K_L.gguf) | Q3_K_L | 0.58GB | | |
| | [lmlab-mistral-1b-untrained.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.IQ4_XS.gguf) | IQ4_XS | 0.6GB | | |
| | [lmlab-mistral-1b-untrained.Q4_0.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q4_0.gguf) | Q4_0 | 0.63GB | | |
| | [lmlab-mistral-1b-untrained.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.IQ4_NL.gguf) | IQ4_NL | 0.63GB | | |
| | [lmlab-mistral-1b-untrained.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q4_K_S.gguf) | Q4_K_S | 0.63GB | | |
| | [lmlab-mistral-1b-untrained.Q4_K.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q4_K.gguf) | Q4_K | 0.66GB | | |
| | [lmlab-mistral-1b-untrained.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q4_K_M.gguf) | Q4_K_M | 0.66GB | | |
| | [lmlab-mistral-1b-untrained.Q4_1.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q4_1.gguf) | Q4_1 | 0.69GB | | |
| | [lmlab-mistral-1b-untrained.Q5_0.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q5_0.gguf) | Q5_0 | 0.74GB | | |
| | [lmlab-mistral-1b-untrained.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q5_K_S.gguf) | Q5_K_S | 0.74GB | | |
| | [lmlab-mistral-1b-untrained.Q5_K.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q5_K.gguf) | Q5_K | 0.76GB | | |
| | [lmlab-mistral-1b-untrained.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q5_K_M.gguf) | Q5_K_M | 0.76GB | | |
| | [lmlab-mistral-1b-untrained.Q5_1.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q5_1.gguf) | Q5_1 | 0.8GB | | |
| | [lmlab-mistral-1b-untrained.Q6_K.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q6_K.gguf) | Q6_K | 0.87GB | | |
| | [lmlab-mistral-1b-untrained.Q8_0.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q8_0.gguf) | Q8_0 | 1.12GB | | |
| Original model description: | |
| --- | |
| license: apache-2.0 | |
| language: | |
| - en | |
| pipeline_tag: text-generation | |
| --- | |
| Sorry everyone this got sort of popular but it doesnt generate understandable text - I think there's a way to make this generate good results w/ relatively little compute I'll experiment a bit later | |
| # LMLab Mistral 1B Untrained | |
| This is an untrained base model modified from Mistral-7B-Instruct. It has 1.13 billion parameters. | |
| ## Untrained | |
| This model is untrained. **This means it will not generate comprehensible text.** | |
| ## Model Details | |
| ### Model Description | |
| - **Developed by:** LMLab | |
| - **License:** Apache 2.0 | |
| - **Parameters:** 1.13 billion (1,134,596,096) | |
| - **Modified from model:** [`mistralai/Mistral-7B-v0.1`](https://huggingface.co/mistralai/Mistral-7B-v0.1) | |
| ### Model Architecture | |
| LMLab Mistral 1B is a transformer model, with the following architecture choices: | |
| * Grouped-Query Attention | |
| * Sliding-Window Attention | |
| * Byte-fallback BPE tokenizer | |
| ## Usage | |
| Use `MistralForCausalLM`. | |
| ```python | |
| from transformers import MistralForCausalLM, AutoTokenizer | |
| tokenizer = AutoTokenizer.from_pretrained('lmlab/lmlab-mistral-1b-untrained') | |
| model = MistralForCausalLM.from_pretrained('lmlab/lmlab-mistral-1b-untrained') | |
| text = "Once upon a time" | |
| encoded_input = tokenizer(text, return_tensors='pt') | |
| output = model.generate(**encoded_input) | |
| print(tokenizer.decode(output[0])) | |
| ``` | |
| ## Notice | |
| This model does not have any moderation systems. | |