Upload folder using huggingface_hub (#2)

- dba343b7cc73cae503e759ef0c79ac55a004322101ab15060b8be0da6955827d (48a4821e333a7c0b1af6d2c9e4e277cfeca9e166)
- a480672a9c14a0e312a2cde8f2b51987abef36d02dcf76a0cf68c4e647f02a3d (8f225b35608f61befbf821225a3c100270e44fc7)

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/vinai-PhoGPT-4B-Chat-bnb-4bit-smashed",
-                                                 trust_remote_code=True)
+                                                 trust_remote_code=True, device_map='auto')
     tokenizer = AutoTokenizer.from_pretrained("vinai/PhoGPT-4B-Chat")
     
     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/tmpf3a6eqds",
+  "_name_or_path": "/tmp/tmp8xp7i1km",
   "architectures": [
     "MPTForCausalLM"
   ],
@@ -65,7 +65,7 @@
   "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 sha256:84066123f3f5ea02f2d44d932466cc4ab0babda6a12f180a6abb8153fd042244
-size 1998125769
+oid sha256:8f45edcbe495a7ab845039dd8b6a6cab376c9e34f17da2ae5329d638c54df640
+size 2166938656

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/models3z6antmt",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/models_mtsi05f",
         "batch_size": 1,
         "model_name": "vinai/PhoGPT-4B-Chat",
         "pruning_ratio": 0.0,