metadata
license: apache-2.0
tags:
- LLMs
- mistral
- Intel
- TensorBlock
- GGUF
pipeline_tag: text-generation
base_model: Intel/neural-chat-7b-v3-1
datasets:
- Open-Orca/SlimOrca
language:
- en
model-index:
- name: neural-chat-7b-v3-1
results:
- task:
type: Large Language Model
name: Large Language Model
dataset:
name: Open-Orca/SlimOrca
type: Open-Orca/SlimOrca
metrics:
- type: ARC (25-shot)
value: 66.21
name: ARC (25-shot)
verified: true
- type: HellaSwag (10-shot)
value: 83.64
name: HellaSwag (10-shot)
verified: true
- type: MMLU (5-shot)
value: 62.37
name: MMLU (5-shot)
verified: true
- type: TruthfulQA (0-shot)
value: 59.65
name: TruthfulQA (0-shot)
verified: true
- type: Winogrande (5-shot)
value: 78.14
name: Winogrande (5-shot)
verified: true
- type: GSM8K (5-shot)
value: 19.56
name: GSM8K (5-shot)
verified: true
- type: DROP (3-shot)
value: 43.84
name: DROP (3-shot)
verified: true
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
Intel/neural-chat-7b-v3-1 - GGUF
This repo contains GGUF format model files for Intel/neural-chat-7b-v3-1.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
### System:
{system_prompt}
### User:
{prompt}
### Assistant:
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| neural-chat-7b-v3-1-Q2_K.gguf | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
| neural-chat-7b-v3-1-Q3_K_S.gguf | Q3_K_S | 2.947 GB | very small, high quality loss |
| neural-chat-7b-v3-1-Q3_K_M.gguf | Q3_K_M | 3.277 GB | very small, high quality loss |
| neural-chat-7b-v3-1-Q3_K_L.gguf | Q3_K_L | 3.560 GB | small, substantial quality loss |
| neural-chat-7b-v3-1-Q4_0.gguf | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| neural-chat-7b-v3-1-Q4_K_S.gguf | Q4_K_S | 3.856 GB | small, greater quality loss |
| neural-chat-7b-v3-1-Q4_K_M.gguf | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
| neural-chat-7b-v3-1-Q5_0.gguf | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| neural-chat-7b-v3-1-Q5_K_S.gguf | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
| neural-chat-7b-v3-1-Q5_K_M.gguf | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
| neural-chat-7b-v3-1-Q6_K.gguf | Q6_K | 5.534 GB | very large, extremely low quality loss |
| neural-chat-7b-v3-1-Q8_0.gguf | Q8_0 | 7.167 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/neural-chat-7b-v3-1-GGUF --include "neural-chat-7b-v3-1-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/neural-chat-7b-v3-1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'