Upload folder using huggingface_hub (#3)

- b69b90d55d89d39838034789c8260ff67d3c9df4fb456ce28846da6f7378468b (bfce5a1a18ae7642fdab7748a35dcd44679328b8)
- 80057609967c9b7407f7d6a0537276ee9e99085d1a79dc6719570659ffe4f5dd (b6bf197dc2bdcf059619c3ae6f444083341f1ce1)

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/scb10x-typhoon-7b-bnb-4bit-smashed",
-                                                 trust_remote_code=True)
+                                                 trust_remote_code=True, device_map='auto')
     tokenizer = AutoTokenizer.from_pretrained("scb10x/typhoon-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/tmpcu40hp9p",
+  "_name_or_path": "/tmp/tmpqj5gh7mg",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -18,7 +18,7 @@
   "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 sha256:4cdee5e477c9b34c11322928621ccb12a94b77f39d68257c79e56122f467f574
-size 4178427746
+oid sha256:2f994c448da2260497162225e153c3c27dd75073769e80337563d7df62039525
+size 4503577728

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelswrv9gad1",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelswgmyw_ib",
         "batch_size": 1,
         "model_name": "scb10x/typhoon-7b",
         "pruning_ratio": 0.0,