Downloads · 30 days
13
6% of all-time downloads
granite-3.0-8b-instruct-Q4_K_M-GGUF
eformat/granite-3.0-8b-instruct-Q4_K_M-GGUF
granite-3.0-8b-instruct-Q4_K_M-GGUF is a text generation model from eformat. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Not all tools (vllm, llama.cpp) seem to support the new model config params it seems (25/10/2024).
All-time downloads
217
Public
Repo size
9.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf4.9 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Oct 25, 2024
- Updated
- Oct 25, 2024
- SHA
- b87ae9a0
Try a prompt
Base models
Model card
From the Hugging Face model README
eformat/granite-3.0-8b-instruct-Q4_K_M-GGUF
Not all tools (vllm, llama.cpp) seem to support the new model config params it seems (25/10/2024).
# config.json
"model_type": "granite"
"architectures": [
"GraniteForCausalLM"
]
This gguf conversion done using old ones
# config.json
"model_type": "llama"
"architectures": [
"LlamaForCausalLM"
]
This gguf loads OK - tested using:
# llama.cpp
./llama-server --verbose --gpu-layers 99999 --parallel 2 --ctx-size 4096 -m ~/instructlab/models/granite-3.0-8b-instruct-Q4_K_M.gguf
# vllm
vllm serve ~/instructlab/models/granite-3.0-8b-instruct-Q4_K_M.gguf
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Created
- Oct 25, 2024
- Updated
- Oct 25, 2024