Hugging Face's logo

NeuraLakeAi
/
iSA-02-Nano-1B-Preview

Transformers
GGUF
PyTorch
text-generation-inference
facebook
meta
reasoning
context-dynamic
small-models
synthetic-data
function-calls
Synthetic
open-source
llama
NeuraLake
🇧🇷
256K
conversational
Model card Files Community
NeuraLake commited on
Commit
c472a0b
·
verified ·
1 Parent(s): 285cb29

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -147,22 +147,22 @@ Importantly, the iSA-02 series (and new models) was developed independently and
147
  ### Model Specifications
148
  | Version | Architecture | Quantization | Model Size |
149
  |---------|--------------|--------------|------------|
150
- | [F32](https://huggingface.co/NeuraLake/iSA-02-Nano-1B-Preview-R/resolve/main/iSA-02-Nano-1B-Preview.F32.gguf) | Custom llama 3.2 | FP32 | 1.24B params |
151
- | [F16](https://huggingface.co/NeuraLake/iSA-02-Nano-1B-Preview-R/resolve/main/iSA-02-Nano-1B-Preview.F16.gguf) | Custom llama 3.2 | FP16 | 1.24B params |
152
- | [Q4_0](https://huggingface.co/NeuraLake/iSA-02-Nano-1B-Preview-R/resolve/main/iSA-02-Nano-1B-Preview.Q4_0.gguf) | Custom llama 3.2 | 4-bit | 1.24B params |
153
- | [Q4_K_M](https://huggingface.co/NeuraLake/iSA-02-Nano-1B-Preview-R/resolve/main/iSA-02-Nano-1B-Preview.Q4_K_M.gguf) | Custom llama 3.2 | 4-bit | 1.24B params |
154
- | [Q5_K_M](https://huggingface.co/NeuraLake/iSA-02-Nano-1B-Preview-R/resolve/main/iSA-02-Nano-1B-Preview.Q5_K_M.gguf) | Custom llama 3.2 | 5-bit | 1.24B params |
155
- | [Q8_0](https://huggingface.co/NeuraLake/iSA-02-Nano-1B-Preview-R/resolve/main/iSA-02-Nano-1B-Preview.Q8_0.gguf) | Custom llama 3.2 | 8-bit | 1.24B params |
156
 
157
  ### Hardware Requirements
158
  | Version | Quantization | Size | Memory (RAM/vRAM) |
159
  |---------|--------------|------|-------------------|
160
- | [F32](https://huggingface.co/NeuraLake/iSA-02-Nano-1B-Preview-R/resolve/main/iSA-02-Nano-1B-Preview.F32.gguf) | FP32 | 4.95 GB | 9.9 GB |
161
- | [F16](https://huggingface.co/NeuraLake/iSA-02-Nano-1B-Preview-R/resolve/main/iSA-02-Nano-1B-Preview.F16.gguf) | FP16 | 2.48 GB | 4.96 GB |
162
- | [Q4_0](https://huggingface.co/NeuraLake/iSA-02-Nano-1B-Preview-R/resolve/main/iSA-02-Nano-1B-Preview.Q4_0.gguf) | 4-bit | 771 MB | 1.56 GB |
163
- | [Q4_K_M](https://huggingface.co/NeuraLake/iSA-02-Nano-1B-Preview-R/resolve/main/iSA-02-Nano-1B-Preview.Q4_K_M.gguf) | 4-bit | 808 MB | 1.62 GB |
164
- | [Q5_K_M](https://huggingface.co/NeuraLake/iSA-02-Nano-1B-Preview-R/resolve/main/iSA-02-Nano-1B-Preview.Q5_K_M.gguf) | 5-bit | 912 MB GB | 1.84 GB |
165
- | [Q8_0](https://huggingface.co/NeuraLake/iSA-02-Nano-1B-Preview-R/resolve/main/iSA-02-Nano-1B-Preview.Q8_0.gguf) | 8-bit | 1.32 GB | 2.64 GB |
166
 
167
  ## Training and Fine-Tuning
168
 
 
147
  ### Model Specifications
148
  | Version | Architecture | Quantization | Model Size |
149
  |---------|--------------|--------------|------------|
150
+ | [F32](https://huggingface.co/NeuraLakeAi/iSA-02-Nano-1B-Preview/resolve/main/iSA-02-Nano-1B-Preview.F32.gguf) | Custom llama 3.2 | FP32 | 1.24B params |
151
+ | [F16](https://huggingface.co/NeuraLakeAi/iSA-02-Nano-1B-Preview/resolve/main/iSA-02-Nano-1B-Preview.F16.gguf) | Custom llama 3.2 | FP16 | 1.24B params |
152
+ | [Q4_0](https://huggingface.co/NeuraLakeAi/iSA-02-Nano-1B-Preview/resolve/main/iSA-02-Nano-1B-Preview.Q4_0.gguf) | Custom llama 3.2 | 4-bit | 1.24B params |
153
+ | [Q4_K_M](https://huggingface.co/NeuraLakeAi/iSA-02-Nano-1B-Preview/resolve/main/iSA-02-Nano-1B-Preview.Q4_K_M.gguf) | Custom llama 3.2 | 4-bit | 1.24B params |
154
+ | [Q5_K_M](https://huggingface.co/NeuraLakeAi/iSA-02-Nano-1B-Preview/resolve/main/iSA-02-Nano-1B-Preview.Q5_K_M.gguf) | Custom llama 3.2 | 5-bit | 1.24B params |
155
+ | [Q8_0](https://huggingface.co/NeuraLakeAi/iSA-02-Nano-1B-Preview/resolve/main/iSA-02-Nano-1B-Preview.Q8_0.gguf) | Custom llama 3.2 | 8-bit | 1.24B params |
156
 
157
  ### Hardware Requirements
158
  | Version | Quantization | Size | Memory (RAM/vRAM) |
159
  |---------|--------------|------|-------------------|
160
+ | [F32](https://huggingface.co/NeuraLakeAi/iSA-02-Nano-1B-Preview/resolve/main/iSA-02-Nano-1B-Preview.F32.gguf) | FP32 | 4.95 GB | 9.9 GB |
161
+ | [F16](https://huggingface.co/NeuraLakeAi/iSA-02-Nano-1B-Preview/resolve/main/iSA-02-Nano-1B-Preview.F16.gguf) | FP16 | 2.48 GB | 4.96 GB |
162
+ | [Q4_0](https://huggingface.co/NeuraLakeAi/iSA-02-Nano-1B-Preview/resolve/main/iSA-02-Nano-1B-Preview.Q4_0.gguf) | 4-bit | 771 MB | 1.56 GB |
163
+ | [Q4_K_M](https://huggingface.co/NeuraLakeAi/iSA-02-Nano-1B-Preview/resolve/main/iSA-02-Nano-1B-Preview.Q4_K_M.gguf) | 4-bit | 808 MB | 1.62 GB |
164
+ | [Q5_K_M](https://huggingface.co/NeuraLakeAi/iSA-02-Nano-1B-Preview/resolve/main/iSA-02-Nano-1B-Preview.Q5_K_M.gguf) | 5-bit | 912 MB GB | 1.84 GB |
165
+ | [Q8_0](https://huggingface.co/NeuraLakeAi/iSA-02-Nano-1B-Preview/resolve/main/iSA-02-Nano-1B-Preview.Q8_0.gguf) | 8-bit | 1.32 GB | 2.64 GB |
166
 
167
  ## Training and Fine-Tuning
168