96 lines
4.3 KiB
Markdown
96 lines
4.3 KiB
Markdown
---
|
|
license: cc-by-sa-4.0
|
|
datasets:
|
|
- ConvLab/dailydialog
|
|
language:
|
|
- en
|
|
base_model: Flexan/HumanPet-X1-1.7B
|
|
pipeline_tag: text-generation
|
|
new_version: Flexan/HumanPet-X2.2-1.7B-GGUF
|
|
---
|
|
|
|
# GGUF Files for HumanPet-X1-1.7B
|
|
|
|
These are the GGUF files for [Flexan/HumanPet-X1-1.7B](https://huggingface.co/Flexan/HumanPet-X1-1.7B).
|
|
|
|
## Downloads
|
|
|
|
| GGUF Link | Quantization | Description |
|
|
| ---- | ----- | ----------- |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.Q2_K.gguf) | Q2_K | Lowest quality |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.Q3_K_S.gguf) | Q3_K_S | |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.IQ3_S.gguf) | IQ3_S | Integer quant, preferable over Q3_K_S |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.IQ3_M.gguf) | IQ3_M | Integer quant |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.Q3_K_M.gguf) | Q3_K_M | |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.Q3_K_L.gguf) | Q3_K_L | |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.IQ4_XS.gguf) | IQ4_XS | Integer quant |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.Q4_K_S.gguf) | Q4_K_S | Fast with good performance |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.Q4_K_M.gguf) | Q4_K_M | **Recommended:** Perfect mix of speed and performance |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.Q5_K_S.gguf) | Q5_K_S | |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.Q5_K_M.gguf) | Q5_K_M | |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.Q6_K.gguf) | Q6_K | Very good quality |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.Q8_0.gguf) | Q8_0 | Best quality |
|
|
| [Download](https://huggingface.co/Flexan/HumanPet-X1-1.7B-GGUF/resolve/main/HumanPet-X1-1.7B.f16.gguf) | f16 | Full precision, don't bother; use a quant |
|
|
|
|
|
|
# HumanPet X1 1.7B
|
|
|
|
## Description
|
|
|
|
HumanPet X1 1.7B is an instruct LLM consisting of 1.7B parameters trained to talk in a human conversational manner. It does not support reasoning nor tool-calling (although the base model does).
|
|
The model was LoRA fine-tuned with [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) as base model.
|
|
|
|
The HumanPet series is part of an experiment. Do not expect consistent releases.
|
|
|
|
[Explanation of the experiment](https://huggingface.co/Flexan/HumanPet)
|
|
[Progress on the experiment](https://huggingface.co/Flexan/HumanPet#progress)
|
|
[Findings for HumanPet X1 1.7B](https://huggingface.co/Flexan/HumanPet#humanpet-x1-17b)
|
|
|
|
> [!NOTE]
|
|
> **Note:** the model files are **not released yet.** [Read section 'Stages' in the experiment explanation.](https://huggingface.co/Flexan/HumanPet#stages)
|
|
|
|
## Chat Format
|
|
|
|
HumanPet X1 1.7B uses the ChatML format, e.g.:
|
|
```text
|
|
<|im_start|>system
|
|
System message<|im_end|>
|
|
<|im_start|>user
|
|
User prompt<|im_end|>
|
|
<|im_start|>assistant
|
|
Assistant response<|im_end|>
|
|
```
|
|
|
|
## Usage
|
|
|
|
This model is not trained on system prompts. Therefore, it is recommended to not send any system messages. This includes tools (which this model also was not trained on).
|
|
|
|
The assistant response has the following format:
|
|
```text
|
|
<|im_start|>assistant
|
|
<think>
|
|
|
|
</think>
|
|
|
|
What happened?
|
|
|
|
<extra>
|
|
{"intent": "question", "emotion": "no emotion"}
|
|
</extra><|im_end|>
|
|
```
|
|
|
|
Note that the `<think>...</think>` tags are always empty, as this model was not trained on reasoning data.
|
|
The `<extra>...</extra>` tags contain JSON data of this schema:
|
|
```ts
|
|
{
|
|
intent: "directive" | "commissive" | "question" | "inform",
|
|
emotion: "no emotion" | "happiness" | "surprise" | "fear" | "disgust" | "sadness" | "anger"
|
|
}
|
|
```
|
|
|
|
If the model does not adhere to this schema, please let us know in the community tab.
|
|
|
|
## Datasets
|
|
|
|
1. **[ConvLab/dailydialog](https://huggingface.co/datasets/ConvLab/dailydialog)** *4.3k chats*
|
|
Only the conversations from the "Relationship" domain have been used. |