5423df0d295b379501e2130cfb35920c27a899ced635f87aecdac35f42747337
Browse files- README.md +2 -2
- config.json +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +0 -0
- plots.png +0 -0
- smash_config.json +1 -1
README.md
CHANGED
|
@@ -34,7 +34,7 @@ tags:
|
|
| 34 |
|
| 35 |
## Results
|
| 36 |
|
| 37 |
-
|
| 38 |
|
| 39 |
**Frequently Asked Questions**
|
| 40 |
- ***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:
|
|
| 61 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 62 |
|
| 63 |
model = AutoModelForCausalLM.from_pretrained("PrunaAI/beomi-OPEN-SOLAR-KO-10.7B-bnb-4bit-smashed",
|
| 64 |
-
trust_remote_code=True)
|
| 65 |
tokenizer = AutoTokenizer.from_pretrained("beomi/OPEN-SOLAR-KO-10.7B")
|
| 66 |
|
| 67 |
input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
|
|
|
|
| 34 |
|
| 35 |
## Results
|
| 36 |
|
| 37 |
+
|
| 38 |
|
| 39 |
**Frequently Asked Questions**
|
| 40 |
- ***How does the compression work?*** The model is compressed with llm-int8.
|
|
|
|
| 61 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 62 |
|
| 63 |
model = AutoModelForCausalLM.from_pretrained("PrunaAI/beomi-OPEN-SOLAR-KO-10.7B-bnb-4bit-smashed",
|
| 64 |
+
trust_remote_code=True, device_map='auto')
|
| 65 |
tokenizer = AutoTokenizer.from_pretrained("beomi/OPEN-SOLAR-KO-10.7B")
|
| 66 |
|
| 67 |
input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/tmp/
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"quantization_config": {
|
| 22 |
"bnb_4bit_compute_dtype": "bfloat16",
|
| 23 |
"bnb_4bit_quant_type": "fp4",
|
| 24 |
-
"bnb_4bit_use_double_quant":
|
| 25 |
"llm_int8_enable_fp32_cpu_offload": false,
|
| 26 |
"llm_int8_has_fp16_weight": false,
|
| 27 |
"llm_int8_skip_modules": [
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/tmp/tmp6sjg8w72",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
| 21 |
"quantization_config": {
|
| 22 |
"bnb_4bit_compute_dtype": "bfloat16",
|
| 23 |
"bnb_4bit_quant_type": "fp4",
|
| 24 |
+
"bnb_4bit_use_double_quant": false,
|
| 25 |
"llm_int8_enable_fp32_cpu_offload": false,
|
| 26 |
"llm_int8_has_fp16_weight": false,
|
| 27 |
"llm_int8_skip_modules": [
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c99b5f6da860b29ed810ed4bffd6112b4fa981718e3711af0825dae9e26310e7
|
| 3 |
+
size 1674812136
|
model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
plots.png
ADDED
|
smash_config.json
CHANGED
|
@@ -8,7 +8,7 @@
|
|
| 8 |
"compilers": "None",
|
| 9 |
"task": "text_text_generation",
|
| 10 |
"device": "cuda",
|
| 11 |
-
"cache_dir": "/ceph/hdd/staff/charpent/.cache/
|
| 12 |
"batch_size": 1,
|
| 13 |
"model_name": "beomi/OPEN-SOLAR-KO-10.7B",
|
| 14 |
"pruning_ratio": 0.0,
|
|
|
|
| 8 |
"compilers": "None",
|
| 9 |
"task": "text_text_generation",
|
| 10 |
"device": "cuda",
|
| 11 |
+
"cache_dir": "/ceph/hdd/staff/charpent/.cache/modelswzjl4uav",
|
| 12 |
"batch_size": 1,
|
| 13 |
"model_name": "beomi/OPEN-SOLAR-KO-10.7B",
|
| 14 |
"pruning_ratio": 0.0,
|