metadata
license: apache-2.0
tags:
- LLMs
- mistral
- math
- Intel
- TensorBlock
- GGUF
base_model: Intel/neural-chat-7b-v3-3
model-index:
- name: neural-chat-7b-v3-3
results:
- task:
type: Large Language Model
name: Large Language Model
dataset:
name: meta-math/MetaMathQA
type: meta-math/MetaMathQA
metrics:
- type: ARC (25-shot)
value: 66.89
name: ARC (25-shot)
verified: true
- type: HellaSwag (10-shot)
value: 85.26
name: HellaSwag (10-shot)
verified: true
- type: MMLU (5-shot)
value: 63.07
name: MMLU (5-shot)
verified: true
- type: TruthfulQA (0-shot)
value: 63.01
name: TruthfulQA (0-shot)
verified: true
- type: Winogrande (5-shot)
value: 79.64
name: Winogrande (5-shot)
verified: true
- type: GSM8K (5-shot)
value: 61.11
name: GSM8K (5-shot)
verified: true
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 66.89
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 85.26
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 63.07
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 63.01
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 79.64
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 61.11
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-3
name: Open LLM Leaderboard
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
Intel/neural-chat-7b-v3-3 - GGUF
This repo contains GGUF format model files for Intel/neural-chat-7b-v3-3.
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-v3-3-Q2_K.gguf | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
| neural-chat-7b-v3-3-Q3_K_S.gguf | Q3_K_S | 2.947 GB | very small, high quality loss |
| neural-chat-7b-v3-3-Q3_K_M.gguf | Q3_K_M | 3.277 GB | very small, high quality loss |
| neural-chat-7b-v3-3-Q3_K_L.gguf | Q3_K_L | 3.560 GB | small, substantial quality loss |
| neural-chat-7b-v3-3-Q4_0.gguf | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| neural-chat-7b-v3-3-Q4_K_S.gguf | Q4_K_S | 3.856 GB | small, greater quality loss |
| neural-chat-7b-v3-3-Q4_K_M.gguf | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
| neural-chat-7b-v3-3-Q5_0.gguf | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| neural-chat-7b-v3-3-Q5_K_S.gguf | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
| neural-chat-7b-v3-3-Q5_K_M.gguf | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
| neural-chat-7b-v3-3-Q6_K.gguf | Q6_K | 5.534 GB | very large, extremely low quality loss |
| neural-chat-7b-v3-3-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-v3-3-GGUF --include "neural-chat-7b-v3-3-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-v3-3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'