Upload folder using huggingface_hub (#3)

- 291eae373cd82b668236fef6ac2b882a600b67c5d7d6c95d1da19626b9a6895a (c2c075e3d723a10913afff24742b28f4a63b7f42)
- 793d34b4cada12e992d812e74a6450ccb175376a4d7f14c1023bea4dc75f574e (1c478a1b546195bf7c3aebd0a4bf593e18d8998a)

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/Intel-neural-chat-7b-v3-1-bnb-4bit-smashed",
-                                                 trust_remote_code=True)
+                                                 trust_remote_code=True, device_map='auto')
     tokenizer = AutoTokenizer.from_pretrained("Intel/neural-chat-7b-v3-1")
     
     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/tmptitdaezn",
+  "_name_or_path": "/tmp/tmp8b_gsg5f",
   "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 sha256:19fb6054a8a6a37dd9bba7ac01c21c57afd970faf36b975bb55fd7cfb0545b6d
-size 4125687614
+oid sha256:74755382848a244f54a0a93064e978be9c95a350dbe8600c9cc11c0a17cb8f6e
+size 4450837496

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/models5xt84bx0",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/models2dbk5ufl",
         "batch_size": 1,
         "model_name": "Intel/neural-chat-7b-v3-1",
         "pruning_ratio": 0.0,