Hugging Face's logo

PrunaAI
/
42dot-42dot_LLM-PLM-1.3B-bnb-4bit-smashed

Text Generation
Transformers
Safetensors
llama
pruna-ai
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
5

Upload folder using huggingface_hub

#4
by sharpenb - opened
base: refs/heads/main
←
from: refs/pr/4
Discussion Files changed
+2
-2
Files changed (3) hide show
  1. config.json +1 -1
  2. plots.png +0 -0
  3. smash_config.json +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/tmp/tmpw0acys3j",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "/tmp/tmpahl9ahxq",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
plots.png CHANGED
smash_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "compilers": "[]",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
- "cache_dir": "/ceph/hdd/staff/charpent/.cache/models48vm_y7x",
12
  "batch_size": 1,
13
  "model_name": "42dot/42dot_LLM-PLM-1.3B",
14
  "pruning_ratio": 0.0,
 
8
  "compilers": "[]",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
+ "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsq_fbgga3",
12
  "batch_size": 1,
13
  "model_name": "42dot/42dot_LLM-PLM-1.3B",
14
  "pruning_ratio": 0.0,