Upload folder using huggingface_hub (#2)

- 54b089c142fc38548035f34b1b18fe1014c736e2653fe173c78b356981812ec4 (500ef9922415ebcb1ed167c67c53f5cee7445678)
- c589b9abcc7eba81f9c4323bfe694752f8379e63e8b63de9a7ef4eaed8edd3b6 (7c42e3de28570e61c8bc67831cb85d888dd8b7a5)

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/microsoft-Orca-2-7b-bnb-4bit-smashed",
-                                                 trust_remote_code=True)
+                                                 trust_remote_code=True, device_map='auto')
     tokenizer = AutoTokenizer.from_pretrained("microsoft/Orca-2-7b")
     
     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/tmpof9d5gng",
+  "_name_or_path": "/tmp/tmpqndvwd_q",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -20,7 +20,7 @@
   "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 sha256:51f154879649bc14ecfe6faf904a3e1043c403d5154ff8a0cd971bdd7d28ea07
-size 3866091239
+oid sha256:77107d33c0eca05eb7434060276e62ea158795ad4d0f55c26175c2918ae35168
+size 4167771160

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsib_u73b1",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelspm7k69yx",
         "batch_size": 1,
         "model_name": "microsoft/Orca-2-7b",
         "pruning_ratio": 0.0,