Open-weight model
HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF
by John park rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF
This model was converted to GGUF format from naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.
Model Card
This model was converted to GGUF format from naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Install llama.cpp through brew (works on Mac and Linux) Invoke the llama.cpp server or the CLI. Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with LLAMACURL=1 flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).
Excerpt from the card by John park, licensed other.
Configuration
- Architecture
- LlamaForCausalLM
- Context length (tokens)
- 131,072
- Layers
- 24
- Hidden size
- 2,048
- Feed-forward size
- 7,168
- Attention heads
- 16
- Key/value heads
- 8
- Head dimension
- 128
- Vocabulary size
- 110,592
- RoPE base
- 100,000,000
- Stored precision
- bfloat16
- Model type
- llama
Identity and Version
- Repository
- rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF
- Publisher
- John park
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 3d2edd543d75372922aabd4ae538e6d181634b5d
- First published
- 2025-04-24
- Last updated
- 2025-04-28
Files and Weights
7 files, 1.1 GB in total. The weights are 1 file totalling 1.1 GB in gguf.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| hyperclovax-seed-text-instruct-1.5b-q4_k_m.gguf | Weights | 1.1 GB | 95659a99a087 |
| config.json | Configuration | 764 B | — |
| special_tokens_map.json | Configuration | 1.9 KB | — |
| README.md | Documentation | 2.1 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 8.0 MB | — |
| tokenizer_config.json | Tokenizer | 11.9 KB | — |
License and Download
- License
- other
- Access
- Open weights, no gate
- Download size
- 1.1 GB
Released by John park through its official repository on Hugging Face.
Built From
- Derived from naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B
- Quantized from naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF
What license is HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF released under?
other, as its publisher declares it. Read the license text before commercial use.
What is HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF's context length?
131,072 tokens, from the maximum position embeddings in its published configuration.