Upload folder using huggingface_hub (#3)

- 246493c74ee66a49fb4760ce32da27098ea9ca4bb228a7a3edcdbc65615debd9 (3a142621e0c9dd9769046af792b68646c8495240)
- 71524ce7dda1f43f871551eb55f0e30624afcaaee7bb4a428717fd3c149dcaac (7fb0de8e73a25559d1071c444059ad3c1049a24f)

README.md

@@ -34,7 +34,7 @@ tags:
 
 ## Results
 
-Detailed efficiency metrics coming soon!
+![image info](./plots.png)
 
 **Frequently Asked Questions**
 - ***How does the compression work?*** The model is compressed with llm-int8.
@@ -61,7 +61,7 @@ You can run the smashed model with these steps:
    from transformers import AutoModelForCausalLM, AutoTokenizer
 
     model = AutoModelForCausalLM.from_pretrained("PrunaAI/luffycodes-vicuna-class-tutor-7b-ep3-bnb-4bit-smashed",
-                                                 trust_remote_code=True)
+                                                 trust_remote_code=True, device_map='auto')
     tokenizer = AutoTokenizer.from_pretrained("luffycodes/vicuna-class-tutor-7b-ep3")
     
     input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/tmp/tmpepsam21p",
+  "_name_or_path": "/tmp/tmpvbwj0woe",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -21,7 +21,7 @@
   "quantization_config": {
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": true,
+    "bnb_4bit_use_double_quant": false,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": [

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f293221a99a0e50d4ceca69f1cddaa7f619d388f5fe8c453e474ca170e4516cc
-size 3866042091
+oid sha256:695615c288c73b2772a8ecbe7ea076809727a83ea16eab421a8a8eba4107e35d
+size 4167722008

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/models__1s76xy",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsgireycy4",
         "batch_size": 1,
         "model_name": "luffycodes/vicuna-class-tutor-7b-ep3",
         "pruning_ratio": 0.0,