Text Generation
Transformers
Safetensors
English
Chinese
glm_moe_dsa
conversational
4-bit precision
auto-round
Instructions to use INCModel2/GLM-5.2-W4A16-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use INCModel2/GLM-5.2-W4A16-AutoRound with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="INCModel2/GLM-5.2-W4A16-AutoRound") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("INCModel2/GLM-5.2-W4A16-AutoRound") model = AutoModelForCausalLM.from_pretrained("INCModel2/GLM-5.2-W4A16-AutoRound") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use INCModel2/GLM-5.2-W4A16-AutoRound with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "INCModel2/GLM-5.2-W4A16-AutoRound" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "INCModel2/GLM-5.2-W4A16-AutoRound", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/INCModel2/GLM-5.2-W4A16-AutoRound
- SGLang
How to use INCModel2/GLM-5.2-W4A16-AutoRound with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "INCModel2/GLM-5.2-W4A16-AutoRound" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "INCModel2/GLM-5.2-W4A16-AutoRound", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "INCModel2/GLM-5.2-W4A16-AutoRound" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "INCModel2/GLM-5.2-W4A16-AutoRound", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use INCModel2/GLM-5.2-W4A16-AutoRound with Docker Model Runner:
docker model run hf.co/INCModel2/GLM-5.2-W4A16-AutoRound
Upload folder using huggingface_hub (part 2)
Browse files- .gitattributes +1 -0
- model-00245-of-00282.safetensors +3 -0
- model-00246-of-00282.safetensors +3 -0
- model-00247-of-00282.safetensors +3 -0
- model-00248-of-00282.safetensors +3 -0
- model-00249-of-00282.safetensors +3 -0
- model-00250-of-00282.safetensors +3 -0
- model-00251-of-00282.safetensors +3 -0
- model-00252-of-00282.safetensors +3 -0
- model-00253-of-00282.safetensors +3 -0
- model-00254-of-00282.safetensors +3 -0
- model-00255-of-00282.safetensors +3 -0
- model-00256-of-00282.safetensors +3 -0
- model-00257-of-00282.safetensors +3 -0
- model-00258-of-00282.safetensors +3 -0
- model-00259-of-00282.safetensors +3 -0
- model-00260-of-00282.safetensors +3 -0
- model-00261-of-00282.safetensors +3 -0
- model-00262-of-00282.safetensors +3 -0
- model-00263-of-00282.safetensors +3 -0
- model-00264-of-00282.safetensors +3 -0
- model-00265-of-00282.safetensors +3 -0
- model-00266-of-00282.safetensors +3 -0
- model-00267-of-00282.safetensors +3 -0
- model-00268-of-00282.safetensors +3 -0
- model-00269-of-00282.safetensors +3 -0
- model-00270-of-00282.safetensors +3 -0
- model-00271-of-00282.safetensors +3 -0
- model-00272-of-00282.safetensors +3 -0
- model-00273-of-00282.safetensors +3 -0
- model-00274-of-00282.safetensors +3 -0
- model-00275-of-00282.safetensors +3 -0
- model-00276-of-00282.safetensors +3 -0
- model-00277-of-00282.safetensors +3 -0
- model-00278-of-00282.safetensors +3 -0
- model-00279-of-00282.safetensors +3 -0
- model-00280-of-00282.safetensors +3 -0
- model-00281-of-00282.safetensors +3 -0
- model-00282-of-00282.safetensors +3 -0
- model.safetensors.index.json +3 -0
- quantization_config.json +537 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
|
model-00245-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23e2f690485e1aaff2c87ff73fd5c4fad291dfd9197b350400d35440890850bc
|
| 3 |
+
size 1396216408
|
model-00246-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4968c889ecf8b6e0625881b82777b258761c4a08a3264da4b531ac254ec39385
|
| 3 |
+
size 1392505264
|
model-00247-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38da23b3408e352ecb45da02711d552fd969b3e3c98588eb83b205a3e608de13
|
| 3 |
+
size 1392505072
|
model-00248-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6245fb2c1c779b6800a6c07d45eea09b7b9cfe86da5abdfe20979a24a91bd6c6
|
| 3 |
+
size 1396427920
|
model-00249-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86439f2c38b3db96a5a64464e165bee313afc05209a31b2453c7c3b923e62ef0
|
| 3 |
+
size 1392505288
|
model-00250-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d18f62f24fcab8ba51e22d28eb8562a22c8582629e1415bdc48cf1b9745b469f
|
| 3 |
+
size 1392505264
|
model-00251-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aefa66ace6cc5361c6107a35f2bfc65084fe96405fa3188f1ea916e99d085ee3
|
| 3 |
+
size 1392504872
|
model-00252-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59f2052ce1f78a43056fd558833e0d57b5bc896c7e1fc2eee6ece504536b2d64
|
| 3 |
+
size 1396428160
|
model-00253-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cddec86ff7184eb608bb387b9feaf304be6202ddbbd78f7f96c4c1ac36920e4c
|
| 3 |
+
size 1392505280
|
model-00254-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0412981c2cf2c33100d387896eaa8fa862842e8180b0a37a17180cf980454c50
|
| 3 |
+
size 1392505272
|
model-00255-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34308a15fab442f77b594c4b7b404458cd0b243f8218e90d0166f14ebdcc43c1
|
| 3 |
+
size 1392504664
|
model-00256-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50640c0b7cb402291da47cd6fc108e58c1831f1dde873d6a5f98f31121afec20
|
| 3 |
+
size 1396428368
|
model-00257-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50e003d9f72ab00a866beb9a6475edeb96eb5e74b07f2518875e1f97b8703d96
|
| 3 |
+
size 1392505264
|
model-00258-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f6529fc0e40415002059e15cecafaffc5dc2c5ea6e71312c4213d237f101bfc
|
| 3 |
+
size 1392505096
|
model-00259-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a345b9d94c85c4ad535bcbc368f3c0d3906481d82db12596d95c6755babe052
|
| 3 |
+
size 1396215896
|
model-00260-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83c2568bd09c461f64b077d4147cbbda1c724e9320db17124623c7da69b21765
|
| 3 |
+
size 1392505288
|
model-00261-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58b324843ccee99868b2a9fc181edffc2058542844841d86047e351010bb1e15
|
| 3 |
+
size 1392505264
|
model-00262-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:968dcb0a9b4e7c3e4460caa2db753250304fa8bea4f5ffe4145849e5f6db619e
|
| 3 |
+
size 1392504904
|
model-00263-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2548b126da8dca83676500afda2bbe7df8d390026553171d549e910d5eb50fed
|
| 3 |
+
size 1396428136
|
model-00264-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f594b69cf1d3907870c02692c7ffbda4e1b6ae4857279aafa575ff7bfce271f0
|
| 3 |
+
size 1392505288
|
model-00265-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93f28956232fcc2c45bb2de43cee20030f63644e0acff96c4a8a73d06a174415
|
| 3 |
+
size 1392505264
|
model-00266-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d94cea40b7508fce53c4a1799d5b28e576be890fdf2cf5564bdfaaef61470006
|
| 3 |
+
size 1392504696
|
model-00267-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27740c26169eb98598cda702ab69bc605cb9b7ad6c8aa5b942586870650fa781
|
| 3 |
+
size 1396428336
|
model-00268-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4ec515290f5e73812139533e6d8dd54c2400d388694f90d9edd8eb6f2ad08b6
|
| 3 |
+
size 1392505272
|
model-00269-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3294299b0ee6cd0f593ba2725321b78c6c50d2e970f0c4d96c51f91b590bee7
|
| 3 |
+
size 1392505120
|
model-00270-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdd73634bc17d98140a3c74f40407c4ae4f5b83daafe5c1700ef51a7829dbae5
|
| 3 |
+
size 1396450784
|
model-00271-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b15ac264afecec4386b0b7c91e5d4cc9ece415e76b27c74cf5c9ca633f72985
|
| 3 |
+
size 1392505240
|
model-00272-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eed00d09a8c40f9738ce574d8b22a6fb48c0ba8bac9ba0ef290d2a673667cf40
|
| 3 |
+
size 1392505272
|
model-00273-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6096508304c897bf03b439cd8daf2edfa8d3ef4203cf655a0eb8cbbe94be569f
|
| 3 |
+
size 1392504936
|
model-00274-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcaf3373d79a30fae1c64810020511a5805900d471ef025d58421586ec621532
|
| 3 |
+
size 1396228296
|
model-00275-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c98a7a9c80ae565f1d79a82db786d2e5ec71041d90e00db3fcda5ffe049d2df
|
| 3 |
+
size 1392504640
|
model-00276-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b299eec983c3d57703c4a78f33f42ca4d9fd1066f9522677c76baf31e9e90b2
|
| 3 |
+
size 1392504632
|
model-00277-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5237febd3944e0794ea1e3b532dac9ab37fb1da8982a7620bde7d1830a38cdf2
|
| 3 |
+
size 1392504096
|
model-00278-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70ae408b28e0a36e48ca6183c9b358d3c6f7f9b56c1775c99f1f6d33faea571d
|
| 3 |
+
size 1396427672
|
model-00279-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ccd49455bfa496b9ecbc18e0d83ee558873cfc5237d6420540aff0f30565d44
|
| 3 |
+
size 1392504624
|
model-00280-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45069c250ce569fffe316aa9cdb322ea3b97c8dd8ee11a101f7f4dc9296cce56
|
| 3 |
+
size 1392504544
|
model-00281-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f62293d632085a0674c435b8f89f4c142bbb7f4de98de025976afe1efeb1ec8d
|
| 3 |
+
size 1385517896
|
model-00282-of-00282.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9ea14db7d99dbf72d34dc536d6ae4d57315fc891eda793dd16b4018cf8e055b
|
| 3 |
+
size 76285120
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5048c346eb14f0278cec1f7f64e73e8a0f7ec76ff5debf1968ed4783223813e0
|
| 3 |
+
size 16183512
|
quantization_config.json
ADDED
|
@@ -0,0 +1,537 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"quant_method": "auto-round",
|
| 3 |
+
"packing_format": "auto_round:auto_gptq",
|
| 4 |
+
"bits": 4,
|
| 5 |
+
"group_size": 128,
|
| 6 |
+
"sym": true,
|
| 7 |
+
"data_type": "int",
|
| 8 |
+
"iters": 0,
|
| 9 |
+
"model_free": true,
|
| 10 |
+
"autoround_version": "0.14.0",
|
| 11 |
+
"extra_config": {
|
| 12 |
+
"lm_head": {
|
| 13 |
+
"bits": 16,
|
| 14 |
+
"data_type": "float"
|
| 15 |
+
},
|
| 16 |
+
"model.embed_tokens": {
|
| 17 |
+
"bits": 16,
|
| 18 |
+
"data_type": "float"
|
| 19 |
+
},
|
| 20 |
+
"model.layers.0.mlp.down_proj": {
|
| 21 |
+
"bits": 16,
|
| 22 |
+
"data_type": "float"
|
| 23 |
+
},
|
| 24 |
+
"model.layers.0.mlp.gate_proj": {
|
| 25 |
+
"bits": 16,
|
| 26 |
+
"data_type": "float"
|
| 27 |
+
},
|
| 28 |
+
"model.layers.0.mlp.up_proj": {
|
| 29 |
+
"bits": 16,
|
| 30 |
+
"data_type": "float"
|
| 31 |
+
},
|
| 32 |
+
"model.layers.0.self_attn.indexer.weights_proj": {
|
| 33 |
+
"bits": 16,
|
| 34 |
+
"data_type": "float"
|
| 35 |
+
},
|
| 36 |
+
"model.layers.0.self_attn.indexer.wk": {
|
| 37 |
+
"bits": 16,
|
| 38 |
+
"data_type": "float"
|
| 39 |
+
},
|
| 40 |
+
"model.layers.1.mlp.down_proj": {
|
| 41 |
+
"bits": 16,
|
| 42 |
+
"data_type": "float"
|
| 43 |
+
},
|
| 44 |
+
"model.layers.1.mlp.gate_proj": {
|
| 45 |
+
"bits": 16,
|
| 46 |
+
"data_type": "float"
|
| 47 |
+
},
|
| 48 |
+
"model.layers.1.mlp.up_proj": {
|
| 49 |
+
"bits": 16,
|
| 50 |
+
"data_type": "float"
|
| 51 |
+
},
|
| 52 |
+
"model.layers.1.self_attn.indexer.weights_proj": {
|
| 53 |
+
"bits": 16,
|
| 54 |
+
"data_type": "float"
|
| 55 |
+
},
|
| 56 |
+
"model.layers.1.self_attn.indexer.wk": {
|
| 57 |
+
"bits": 16,
|
| 58 |
+
"data_type": "float"
|
| 59 |
+
},
|
| 60 |
+
"model.layers.11.mlp.gate": {
|
| 61 |
+
"bits": 16,
|
| 62 |
+
"data_type": "float"
|
| 63 |
+
},
|
| 64 |
+
"model.layers.10.mlp.gate": {
|
| 65 |
+
"bits": 16,
|
| 66 |
+
"data_type": "float"
|
| 67 |
+
},
|
| 68 |
+
"model.layers.10.self_attn.indexer.weights_proj": {
|
| 69 |
+
"bits": 16,
|
| 70 |
+
"data_type": "float"
|
| 71 |
+
},
|
| 72 |
+
"model.layers.10.self_attn.indexer.wk": {
|
| 73 |
+
"bits": 16,
|
| 74 |
+
"data_type": "float"
|
| 75 |
+
},
|
| 76 |
+
"model.layers.13.mlp.gate": {
|
| 77 |
+
"bits": 16,
|
| 78 |
+
"data_type": "float"
|
| 79 |
+
},
|
| 80 |
+
"model.layers.14.mlp.gate": {
|
| 81 |
+
"bits": 16,
|
| 82 |
+
"data_type": "float"
|
| 83 |
+
},
|
| 84 |
+
"model.layers.14.self_attn.indexer.weights_proj": {
|
| 85 |
+
"bits": 16,
|
| 86 |
+
"data_type": "float"
|
| 87 |
+
},
|
| 88 |
+
"model.layers.14.self_attn.indexer.wk": {
|
| 89 |
+
"bits": 16,
|
| 90 |
+
"data_type": "float"
|
| 91 |
+
},
|
| 92 |
+
"model.layers.12.mlp.gate": {
|
| 93 |
+
"bits": 16,
|
| 94 |
+
"data_type": "float"
|
| 95 |
+
},
|
| 96 |
+
"model.layers.19.mlp.gate": {
|
| 97 |
+
"bits": 16,
|
| 98 |
+
"data_type": "float"
|
| 99 |
+
},
|
| 100 |
+
"model.layers.2.mlp.down_proj": {
|
| 101 |
+
"bits": 16,
|
| 102 |
+
"data_type": "float"
|
| 103 |
+
},
|
| 104 |
+
"model.layers.2.mlp.gate_proj": {
|
| 105 |
+
"bits": 16,
|
| 106 |
+
"data_type": "float"
|
| 107 |
+
},
|
| 108 |
+
"model.layers.2.mlp.up_proj": {
|
| 109 |
+
"bits": 16,
|
| 110 |
+
"data_type": "float"
|
| 111 |
+
},
|
| 112 |
+
"model.layers.2.self_attn.indexer.weights_proj": {
|
| 113 |
+
"bits": 16,
|
| 114 |
+
"data_type": "float"
|
| 115 |
+
},
|
| 116 |
+
"model.layers.2.self_attn.indexer.wk": {
|
| 117 |
+
"bits": 16,
|
| 118 |
+
"data_type": "float"
|
| 119 |
+
},
|
| 120 |
+
"model.layers.15.mlp.gate": {
|
| 121 |
+
"bits": 16,
|
| 122 |
+
"data_type": "float"
|
| 123 |
+
},
|
| 124 |
+
"model.layers.16.mlp.gate": {
|
| 125 |
+
"bits": 16,
|
| 126 |
+
"data_type": "float"
|
| 127 |
+
},
|
| 128 |
+
"model.layers.17.mlp.gate": {
|
| 129 |
+
"bits": 16,
|
| 130 |
+
"data_type": "float"
|
| 131 |
+
},
|
| 132 |
+
"model.layers.18.mlp.gate": {
|
| 133 |
+
"bits": 16,
|
| 134 |
+
"data_type": "float"
|
| 135 |
+
},
|
| 136 |
+
"model.layers.18.self_attn.indexer.weights_proj": {
|
| 137 |
+
"bits": 16,
|
| 138 |
+
"data_type": "float"
|
| 139 |
+
},
|
| 140 |
+
"model.layers.18.self_attn.indexer.wk": {
|
| 141 |
+
"bits": 16,
|
| 142 |
+
"data_type": "float"
|
| 143 |
+
},
|
| 144 |
+
"model.layers.20.mlp.gate": {
|
| 145 |
+
"bits": 16,
|
| 146 |
+
"data_type": "float"
|
| 147 |
+
},
|
| 148 |
+
"model.layers.21.mlp.gate": {
|
| 149 |
+
"bits": 16,
|
| 150 |
+
"data_type": "float"
|
| 151 |
+
},
|
| 152 |
+
"model.layers.22.mlp.gate": {
|
| 153 |
+
"bits": 16,
|
| 154 |
+
"data_type": "float"
|
| 155 |
+
},
|
| 156 |
+
"model.layers.22.self_attn.indexer.weights_proj": {
|
| 157 |
+
"bits": 16,
|
| 158 |
+
"data_type": "float"
|
| 159 |
+
},
|
| 160 |
+
"model.layers.22.self_attn.indexer.wk": {
|
| 161 |
+
"bits": 16,
|
| 162 |
+
"data_type": "float"
|
| 163 |
+
},
|
| 164 |
+
"model.layers.23.mlp.gate": {
|
| 165 |
+
"bits": 16,
|
| 166 |
+
"data_type": "float"
|
| 167 |
+
},
|
| 168 |
+
"model.layers.25.mlp.gate": {
|
| 169 |
+
"bits": 16,
|
| 170 |
+
"data_type": "float"
|
| 171 |
+
},
|
| 172 |
+
"model.layers.24.mlp.gate": {
|
| 173 |
+
"bits": 16,
|
| 174 |
+
"data_type": "float"
|
| 175 |
+
},
|
| 176 |
+
"model.layers.26.mlp.gate": {
|
| 177 |
+
"bits": 16,
|
| 178 |
+
"data_type": "float"
|
| 179 |
+
},
|
| 180 |
+
"model.layers.26.self_attn.indexer.weights_proj": {
|
| 181 |
+
"bits": 16,
|
| 182 |
+
"data_type": "float"
|
| 183 |
+
},
|
| 184 |
+
"model.layers.26.self_attn.indexer.wk": {
|
| 185 |
+
"bits": 16,
|
| 186 |
+
"data_type": "float"
|
| 187 |
+
},
|
| 188 |
+
"model.layers.27.mlp.gate": {
|
| 189 |
+
"bits": 16,
|
| 190 |
+
"data_type": "float"
|
| 191 |
+
},
|
| 192 |
+
"model.layers.3.mlp.gate": {
|
| 193 |
+
"bits": 16,
|
| 194 |
+
"data_type": "float"
|
| 195 |
+
},
|
| 196 |
+
"model.layers.28.mlp.gate": {
|
| 197 |
+
"bits": 16,
|
| 198 |
+
"data_type": "float"
|
| 199 |
+
},
|
| 200 |
+
"model.layers.29.mlp.gate": {
|
| 201 |
+
"bits": 16,
|
| 202 |
+
"data_type": "float"
|
| 203 |
+
},
|
| 204 |
+
"model.layers.30.mlp.gate": {
|
| 205 |
+
"bits": 16,
|
| 206 |
+
"data_type": "float"
|
| 207 |
+
},
|
| 208 |
+
"model.layers.30.self_attn.indexer.weights_proj": {
|
| 209 |
+
"bits": 16,
|
| 210 |
+
"data_type": "float"
|
| 211 |
+
},
|
| 212 |
+
"model.layers.30.self_attn.indexer.wk": {
|
| 213 |
+
"bits": 16,
|
| 214 |
+
"data_type": "float"
|
| 215 |
+
},
|
| 216 |
+
"model.layers.31.mlp.gate": {
|
| 217 |
+
"bits": 16,
|
| 218 |
+
"data_type": "float"
|
| 219 |
+
},
|
| 220 |
+
"model.layers.32.mlp.gate": {
|
| 221 |
+
"bits": 16,
|
| 222 |
+
"data_type": "float"
|
| 223 |
+
},
|
| 224 |
+
"model.layers.33.mlp.gate": {
|
| 225 |
+
"bits": 16,
|
| 226 |
+
"data_type": "float"
|
| 227 |
+
},
|
| 228 |
+
"model.layers.34.mlp.gate": {
|
| 229 |
+
"bits": 16,
|
| 230 |
+
"data_type": "float"
|
| 231 |
+
},
|
| 232 |
+
"model.layers.34.self_attn.indexer.weights_proj": {
|
| 233 |
+
"bits": 16,
|
| 234 |
+
"data_type": "float"
|
| 235 |
+
},
|
| 236 |
+
"model.layers.34.self_attn.indexer.wk": {
|
| 237 |
+
"bits": 16,
|
| 238 |
+
"data_type": "float"
|
| 239 |
+
},
|
| 240 |
+
"model.layers.35.mlp.gate": {
|
| 241 |
+
"bits": 16,
|
| 242 |
+
"data_type": "float"
|
| 243 |
+
},
|
| 244 |
+
"model.layers.36.mlp.gate": {
|
| 245 |
+
"bits": 16,
|
| 246 |
+
"data_type": "float"
|
| 247 |
+
},
|
| 248 |
+
"model.layers.38.mlp.gate": {
|
| 249 |
+
"bits": 16,
|
| 250 |
+
"data_type": "float"
|
| 251 |
+
},
|
| 252 |
+
"model.layers.38.self_attn.indexer.weights_proj": {
|
| 253 |
+
"bits": 16,
|
| 254 |
+
"data_type": "float"
|
| 255 |
+
},
|
| 256 |
+
"model.layers.38.self_attn.indexer.wk": {
|
| 257 |
+
"bits": 16,
|
| 258 |
+
"data_type": "float"
|
| 259 |
+
},
|
| 260 |
+
"model.layers.37.mlp.gate": {
|
| 261 |
+
"bits": 16,
|
| 262 |
+
"data_type": "float"
|
| 263 |
+
},
|
| 264 |
+
"model.layers.39.mlp.gate": {
|
| 265 |
+
"bits": 16,
|
| 266 |
+
"data_type": "float"
|
| 267 |
+
},
|
| 268 |
+
"model.layers.4.mlp.gate": {
|
| 269 |
+
"bits": 16,
|
| 270 |
+
"data_type": "float"
|
| 271 |
+
},
|
| 272 |
+
"model.layers.40.mlp.gate": {
|
| 273 |
+
"bits": 16,
|
| 274 |
+
"data_type": "float"
|
| 275 |
+
},
|
| 276 |
+
"model.layers.42.mlp.gate": {
|
| 277 |
+
"bits": 16,
|
| 278 |
+
"data_type": "float"
|
| 279 |
+
},
|
| 280 |
+
"model.layers.42.self_attn.indexer.weights_proj": {
|
| 281 |
+
"bits": 16,
|
| 282 |
+
"data_type": "float"
|
| 283 |
+
},
|
| 284 |
+
"model.layers.42.self_attn.indexer.wk": {
|
| 285 |
+
"bits": 16,
|
| 286 |
+
"data_type": "float"
|
| 287 |
+
},
|
| 288 |
+
"model.layers.41.mlp.gate": {
|
| 289 |
+
"bits": 16,
|
| 290 |
+
"data_type": "float"
|
| 291 |
+
},
|
| 292 |
+
"model.layers.43.mlp.gate": {
|
| 293 |
+
"bits": 16,
|
| 294 |
+
"data_type": "float"
|
| 295 |
+
},
|
| 296 |
+
"model.layers.44.mlp.gate": {
|
| 297 |
+
"bits": 16,
|
| 298 |
+
"data_type": "float"
|
| 299 |
+
},
|
| 300 |
+
"model.layers.45.mlp.gate": {
|
| 301 |
+
"bits": 16,
|
| 302 |
+
"data_type": "float"
|
| 303 |
+
},
|
| 304 |
+
"model.layers.46.mlp.gate": {
|
| 305 |
+
"bits": 16,
|
| 306 |
+
"data_type": "float"
|
| 307 |
+
},
|
| 308 |
+
"model.layers.46.self_attn.indexer.weights_proj": {
|
| 309 |
+
"bits": 16,
|
| 310 |
+
"data_type": "float"
|
| 311 |
+
},
|
| 312 |
+
"model.layers.46.self_attn.indexer.wk": {
|
| 313 |
+
"bits": 16,
|
| 314 |
+
"data_type": "float"
|
| 315 |
+
},
|
| 316 |
+
"model.layers.47.mlp.gate": {
|
| 317 |
+
"bits": 16,
|
| 318 |
+
"data_type": "float"
|
| 319 |
+
},
|
| 320 |
+
"model.layers.48.mlp.gate": {
|
| 321 |
+
"bits": 16,
|
| 322 |
+
"data_type": "float"
|
| 323 |
+
},
|
| 324 |
+
"model.layers.49.mlp.gate": {
|
| 325 |
+
"bits": 16,
|
| 326 |
+
"data_type": "float"
|
| 327 |
+
},
|
| 328 |
+
"model.layers.5.mlp.gate": {
|
| 329 |
+
"bits": 16,
|
| 330 |
+
"data_type": "float"
|
| 331 |
+
},
|
| 332 |
+
"model.layers.50.mlp.gate": {
|
| 333 |
+
"bits": 16,
|
| 334 |
+
"data_type": "float"
|
| 335 |
+
},
|
| 336 |
+
"model.layers.50.self_attn.indexer.weights_proj": {
|
| 337 |
+
"bits": 16,
|
| 338 |
+
"data_type": "float"
|
| 339 |
+
},
|
| 340 |
+
"model.layers.50.self_attn.indexer.wk": {
|
| 341 |
+
"bits": 16,
|
| 342 |
+
"data_type": "float"
|
| 343 |
+
},
|
| 344 |
+
"model.layers.51.mlp.gate": {
|
| 345 |
+
"bits": 16,
|
| 346 |
+
"data_type": "float"
|
| 347 |
+
},
|
| 348 |
+
"model.layers.52.mlp.gate": {
|
| 349 |
+
"bits": 16,
|
| 350 |
+
"data_type": "float"
|
| 351 |
+
},
|
| 352 |
+
"model.layers.53.mlp.gate": {
|
| 353 |
+
"bits": 16,
|
| 354 |
+
"data_type": "float"
|
| 355 |
+
},
|
| 356 |
+
"model.layers.54.mlp.gate": {
|
| 357 |
+
"bits": 16,
|
| 358 |
+
"data_type": "float"
|
| 359 |
+
},
|
| 360 |
+
"model.layers.54.self_attn.indexer.weights_proj": {
|
| 361 |
+
"bits": 16,
|
| 362 |
+
"data_type": "float"
|
| 363 |
+
},
|
| 364 |
+
"model.layers.54.self_attn.indexer.wk": {
|
| 365 |
+
"bits": 16,
|
| 366 |
+
"data_type": "float"
|
| 367 |
+
},
|
| 368 |
+
"model.layers.56.mlp.gate": {
|
| 369 |
+
"bits": 16,
|
| 370 |
+
"data_type": "float"
|
| 371 |
+
},
|
| 372 |
+
"model.layers.55.mlp.gate": {
|
| 373 |
+
"bits": 16,
|
| 374 |
+
"data_type": "float"
|
| 375 |
+
},
|
| 376 |
+
"model.layers.57.mlp.gate": {
|
| 377 |
+
"bits": 16,
|
| 378 |
+
"data_type": "float"
|
| 379 |
+
},
|
| 380 |
+
"model.layers.58.mlp.gate": {
|
| 381 |
+
"bits": 16,
|
| 382 |
+
"data_type": "float"
|
| 383 |
+
},
|
| 384 |
+
"model.layers.58.self_attn.indexer.weights_proj": {
|
| 385 |
+
"bits": 16,
|
| 386 |
+
"data_type": "float"
|
| 387 |
+
},
|
| 388 |
+
"model.layers.58.self_attn.indexer.wk": {
|
| 389 |
+
"bits": 16,
|
| 390 |
+
"data_type": "float"
|
| 391 |
+
},
|
| 392 |
+
"model.layers.59.mlp.gate": {
|
| 393 |
+
"bits": 16,
|
| 394 |
+
"data_type": "float"
|
| 395 |
+
},
|
| 396 |
+
"model.layers.6.mlp.gate": {
|
| 397 |
+
"bits": 16,
|
| 398 |
+
"data_type": "float"
|
| 399 |
+
},
|
| 400 |
+
"model.layers.6.self_attn.indexer.weights_proj": {
|
| 401 |
+
"bits": 16,
|
| 402 |
+
"data_type": "float"
|
| 403 |
+
},
|
| 404 |
+
"model.layers.6.self_attn.indexer.wk": {
|
| 405 |
+
"bits": 16,
|
| 406 |
+
"data_type": "float"
|
| 407 |
+
},
|
| 408 |
+
"model.layers.60.mlp.gate": {
|
| 409 |
+
"bits": 16,
|
| 410 |
+
"data_type": "float"
|
| 411 |
+
},
|
| 412 |
+
"model.layers.61.mlp.gate": {
|
| 413 |
+
"bits": 16,
|
| 414 |
+
"data_type": "float"
|
| 415 |
+
},
|
| 416 |
+
"model.layers.63.mlp.gate": {
|
| 417 |
+
"bits": 16,
|
| 418 |
+
"data_type": "float"
|
| 419 |
+
},
|
| 420 |
+
"model.layers.62.mlp.gate": {
|
| 421 |
+
"bits": 16,
|
| 422 |
+
"data_type": "float"
|
| 423 |
+
},
|
| 424 |
+
"model.layers.62.self_attn.indexer.weights_proj": {
|
| 425 |
+
"bits": 16,
|
| 426 |
+
"data_type": "float"
|
| 427 |
+
},
|
| 428 |
+
"model.layers.62.self_attn.indexer.wk": {
|
| 429 |
+
"bits": 16,
|
| 430 |
+
"data_type": "float"
|
| 431 |
+
},
|
| 432 |
+
"model.layers.64.mlp.gate": {
|
| 433 |
+
"bits": 16,
|
| 434 |
+
"data_type": "float"
|
| 435 |
+
},
|
| 436 |
+
"model.layers.65.mlp.gate": {
|
| 437 |
+
"bits": 16,
|
| 438 |
+
"data_type": "float"
|
| 439 |
+
},
|
| 440 |
+
"model.layers.66.mlp.gate": {
|
| 441 |
+
"bits": 16,
|
| 442 |
+
"data_type": "float"
|
| 443 |
+
},
|
| 444 |
+
"model.layers.66.self_attn.indexer.weights_proj": {
|
| 445 |
+
"bits": 16,
|
| 446 |
+
"data_type": "float"
|
| 447 |
+
},
|
| 448 |
+
"model.layers.66.self_attn.indexer.wk": {
|
| 449 |
+
"bits": 16,
|
| 450 |
+
"data_type": "float"
|
| 451 |
+
},
|
| 452 |
+
"model.layers.67.mlp.gate": {
|
| 453 |
+
"bits": 16,
|
| 454 |
+
"data_type": "float"
|
| 455 |
+
},
|
| 456 |
+
"model.layers.7.mlp.gate": {
|
| 457 |
+
"bits": 16,
|
| 458 |
+
"data_type": "float"
|
| 459 |
+
},
|
| 460 |
+
"model.layers.68.mlp.gate": {
|
| 461 |
+
"bits": 16,
|
| 462 |
+
"data_type": "float"
|
| 463 |
+
},
|
| 464 |
+
"model.layers.69.mlp.gate": {
|
| 465 |
+
"bits": 16,
|
| 466 |
+
"data_type": "float"
|
| 467 |
+
},
|
| 468 |
+
"model.layers.71.mlp.gate": {
|
| 469 |
+
"bits": 16,
|
| 470 |
+
"data_type": "float"
|
| 471 |
+
},
|
| 472 |
+
"model.layers.70.mlp.gate": {
|
| 473 |
+
"bits": 16,
|
| 474 |
+
"data_type": "float"
|
| 475 |
+
},
|
| 476 |
+
"model.layers.70.self_attn.indexer.weights_proj": {
|
| 477 |
+
"bits": 16,
|
| 478 |
+
"data_type": "float"
|
| 479 |
+
},
|
| 480 |
+
"model.layers.70.self_attn.indexer.wk": {
|
| 481 |
+
"bits": 16,
|
| 482 |
+
"data_type": "float"
|
| 483 |
+
},
|
| 484 |
+
"model.layers.72.mlp.gate": {
|
| 485 |
+
"bits": 16,
|
| 486 |
+
"data_type": "float"
|
| 487 |
+
},
|
| 488 |
+
"model.layers.73.mlp.gate": {
|
| 489 |
+
"bits": 16,
|
| 490 |
+
"data_type": "float"
|
| 491 |
+
},
|
| 492 |
+
"model.layers.74.mlp.gate": {
|
| 493 |
+
"bits": 16,
|
| 494 |
+
"data_type": "float"
|
| 495 |
+
},
|
| 496 |
+
"model.layers.74.self_attn.indexer.weights_proj": {
|
| 497 |
+
"bits": 16,
|
| 498 |
+
"data_type": "float"
|
| 499 |
+
},
|
| 500 |
+
"model.layers.74.self_attn.indexer.wk": {
|
| 501 |
+
"bits": 16,
|
| 502 |
+
"data_type": "float"
|
| 503 |
+
},
|
| 504 |
+
"model.layers.75.mlp.gate": {
|
| 505 |
+
"bits": 16,
|
| 506 |
+
"data_type": "float"
|
| 507 |
+
},
|
| 508 |
+
"model.layers.76.mlp.gate": {
|
| 509 |
+
"bits": 16,
|
| 510 |
+
"data_type": "float"
|
| 511 |
+
},
|
| 512 |
+
"model.layers.77.mlp.gate": {
|
| 513 |
+
"bits": 16,
|
| 514 |
+
"data_type": "float"
|
| 515 |
+
},
|
| 516 |
+
"model.layers.78.mlp.gate": {
|
| 517 |
+
"bits": 16,
|
| 518 |
+
"data_type": "float"
|
| 519 |
+
},
|
| 520 |
+
"model.layers.78.self_attn.indexer.weights_proj": {
|
| 521 |
+
"bits": 16,
|
| 522 |
+
"data_type": "float"
|
| 523 |
+
},
|
| 524 |
+
"model.layers.78.self_attn.indexer.wk": {
|
| 525 |
+
"bits": 16,
|
| 526 |
+
"data_type": "float"
|
| 527 |
+
},
|
| 528 |
+
"model.layers.8.mlp.gate": {
|
| 529 |
+
"bits": 16,
|
| 530 |
+
"data_type": "float"
|
| 531 |
+
},
|
| 532 |
+
"model.layers.9.mlp.gate": {
|
| 533 |
+
"bits": 16,
|
| 534 |
+
"data_type": "float"
|
| 535 |
+
}
|
| 536 |
+
}
|
| 537 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
|
| 3 |
+
size 20217442
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"clean_up_tokenization_spaces": false,
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"extra_special_tokens": [
|
| 7 |
+
"<|endoftext|>",
|
| 8 |
+
"[MASK]",
|
| 9 |
+
"[gMASK]",
|
| 10 |
+
"[sMASK]",
|
| 11 |
+
"<sop>",
|
| 12 |
+
"<eop>",
|
| 13 |
+
"<|system|>",
|
| 14 |
+
"<|user|>",
|
| 15 |
+
"<|assistant|>",
|
| 16 |
+
"<|observation|>",
|
| 17 |
+
"<|begin_of_image|>",
|
| 18 |
+
"<|end_of_image|>",
|
| 19 |
+
"<|begin_of_video|>",
|
| 20 |
+
"<|end_of_video|>",
|
| 21 |
+
"<|begin_of_audio|>",
|
| 22 |
+
"<|end_of_audio|>",
|
| 23 |
+
"<|begin_of_transcription|>",
|
| 24 |
+
"<|end_of_transcription|>"
|
| 25 |
+
],
|
| 26 |
+
"is_local": true,
|
| 27 |
+
"model_max_length": 1048576,
|
| 28 |
+
"model_specific_special_tokens": {},
|
| 29 |
+
"pad_token": "<|endoftext|>",
|
| 30 |
+
"padding_side": "left",
|
| 31 |
+
"remove_space": false,
|
| 32 |
+
"tokenizer_class": "TokenizersBackend"
|
| 33 |
+
}
|