Downloads · 30 days
293
8% of all-time downloads
RichardErkhov/CreitinGameplays_-_ConvAI-9b-gguf
CreitinGameplays_-_ConvAI-9b-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
293
8% of all-time downloads
All-time downloads
3.5K
Public
Repo size
102 GB
Likes
0
Public
Click a slice to open those files.
.gguf118 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
ConvAI-9b - GGUF
| Name | Quant method | Size |
|---|---|---|
| ConvAI-9b.Q2_K.gguf | Q2_K | 3.13GB |
| ConvAI-9b.IQ3_XS.gguf | IQ3_XS | 3.48GB |
| ConvAI-9b.IQ3_S.gguf | IQ3_S | 3.67GB |
| ConvAI-9b.Q3_K_S.gguf | Q3_K_S | 3.65GB |
| ConvAI-9b.IQ3_M.gguf | IQ3_M | 3.79GB |
| ConvAI-9b.Q3_K.gguf | Q3_K | 4.05GB |
| ConvAI-9b.Q3_K_M.gguf | Q3_K_M | 4.05GB |
| ConvAI-9b.Q3_K_L.gguf | Q3_K_L | 4.41GB |
| ConvAI-9b.IQ4_XS.gguf | IQ4_XS | 4.55GB |
| ConvAI-9b.Q4_0.gguf | Q4_0 | 4.74GB |
| ConvAI-9b.IQ4_NL.gguf | IQ4_NL | 4.79GB |
| ConvAI-9b.Q4_K_S.gguf | Q4_K_S | 4.78GB |
| ConvAI-9b.Q4_K.gguf | Q4_K | 5.04GB |
| ConvAI-9b.Q4_K_M.gguf | Q4_K_M | 5.04GB |
| ConvAI-9b.Q4_1.gguf | Q4_1 | 5.26GB |
| ConvAI-9b.Q5_0.gguf | Q5_0 | 5.77GB |
| ConvAI-9b.Q5_K_S.gguf | Q5_K_S | 5.77GB |
| ConvAI-9b.Q5_K.gguf | Q5_K | 5.93GB |
| ConvAI-9b.Q5_K_M.gguf | Q5_K_M | 5.93GB |
| ConvAI-9b.Q5_1.gguf | Q5_1 | 6.29GB |
| ConvAI-9b.Q6_K.gguf | Q6_K | 6.87GB |
| ConvAI-9b.Q8_0.gguf | Q8_0 | 8.89GB |
license: mit datasets:

ConvAI-9b is a fine-tuned conversational AI model with 9 billion parameters. It is based on the following models:
The model was fine-tuned on a custom dataset of conversations between an AI assistant and a user. The dataset format followed a specific structure:
<|system|> (system prompt, e.g.: You are a helpful AI language model called ChatGPT, your goal is helping users with their questions) </s> <|user|> (user prompt) </s>
ConvAI-9b is intended for use in conversational AI applications, such as:
| Metrics | Value |
|---|---|
| ARC | 57.50 |
| HellaSwag | 80.34 |
| TruthfulQA | 49.54 |
| Winogrande | 76.24 |
More detailed evaluation here