vincent-pro-ai
/

french-llm-from-scratch-GGUF

Model card Files Files and versions

french-llm-from-scratch-GGUF

7.41 GB

1 contributor

History: 22 commits

vincent-pro-ai's picture

Fix FFN dimensions: gate/up_proj now [1024,4096] (F16, 702MB)

0c13cbd verified 5 days ago

tokenizer
Add V3 mistral HF export (config+weights+tokenizer) 5 days ago
.gitattributes

2.08 kB

Add F16 GGUF (519MB, high precision) 5 days ago
README.md

2.23 kB

Update README with GGUF download instructions for LM Studio 5 days ago
config.json

543 Bytes

Add V3 mistral HF export (config+weights+tokenizer) 5 days ago
french-llm-from-scratch-Q4_K_M-mixed.gguf

1.17 GB
xet

Add GGUF quantized models (Q4_K_M, Q5_K_M, Q8_0) + FP32 15 days ago
french-llm-from-scratch-Q4_K_M.gguf

196 MB
xet

Add GGUF quantized models (Q4_K_M, Q5_K_M, Q8_0) + FP32 18 days ago
french-llm-from-scratch-Q5_K_M.gguf

223 MB
xet

Add GGUF quantized models (Q4_K_M, Q5_K_M, Q8_0) + FP32 18 days ago
french-llm-from-scratch-Q8_0.gguf

317 MB
xet

Add GGUF quantized models (Q4_K_M, Q5_K_M, Q8_0) + FP32 18 days ago
french-llm-from-scratch-f32.gguf

1.17 GB
xet

Add GGUF quantized models (Q4_K_M, Q5_K_M, Q8_0) + FP32 18 days ago
french-llm-v3-mistral-Q4_K_M.gguf

229 MB
xet

Fix FFN dimensions: gate/up_proj now [1024,4096] (Q4_K_M, 218MB) 5 days ago
french-llm-v3-mistral-f16.gguf

737 MB
xet

Fix FFN dimensions: gate/up_proj now [1024,4096] (F16, 702MB) 5 days ago
french_gpt2_lm_studio.gguf

652 MB
xet

Upload french_gpt2_lm_studio.gguf 6 days ago
metadata.json

560 Bytes

Add metadata.json 7 days ago
model.safetensors

498 MB
xet

Upload model.safetensors 6 days ago
model_pytorch.pt
Detected Pickle imports (3)
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage"
What is a pickle import?
1.17 GB
xet

Add model_pytorch.pt 7 days ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
1.04 GB
xet

Add V3 mistral HF export (config+weights+tokenizer) 5 days ago
training_metadata.json

340 Bytes

Add V3 mistral HF export (config+weights+tokenizer) 5 days ago