Add files using upload-large-folder tool
Browse files- README.md +6 -8
- model-00001-of-00007.safetensors +2 -2
- model-00002-of-00007.safetensors +2 -2
- model-00003-of-00007.safetensors +2 -2
- model-00004-of-00007.safetensors +2 -2
- model-00005-of-00007.safetensors +2 -2
- model-00006-of-00007.safetensors +2 -2
- model-00007-of-00007.safetensors +2 -2
- model.safetensors.index.json +0 -0
README.md
CHANGED
|
@@ -1,22 +1,20 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
-
|
| 4 |
-
|
| 5 |
library_name: mlx
|
| 6 |
license: mit
|
| 7 |
pipeline_tag: text-generation
|
| 8 |
tags:
|
| 9 |
- mlx
|
| 10 |
-
- transformers
|
| 11 |
base_model: zai-org/GLM-4.7-Flash
|
| 12 |
---
|
|
|
|
| 13 |
# mlx-community/GLM-4.7-Flash-8bit-gs32
|
| 14 |
|
| 15 |
This model [mlx-community/GLM-4.7-Flash-8bit-gs32](https://huggingface.co/mlx-community/GLM-4.7-Flash-8bit-gs32) was
|
| 16 |
converted to MLX format from [zai-org/GLM-4.7-Flash](https://huggingface.co/zai-org/GLM-4.7-Flash)
|
| 17 |
-
using mlx-lm version **0.30.
|
| 18 |
-
|
| 19 |
-
Why a group-size=32 version? Use the models in another (spoken) language, and you will see why.
|
| 20 |
|
| 21 |
## Use with mlx
|
| 22 |
|
|
@@ -34,8 +32,8 @@ prompt = "hello"
|
|
| 34 |
if tokenizer.chat_template is not None:
|
| 35 |
messages = [{"role": "user", "content": prompt}]
|
| 36 |
prompt = tokenizer.apply_chat_template(
|
| 37 |
-
messages, add_generation_prompt=True
|
| 38 |
)
|
| 39 |
|
| 40 |
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 41 |
-
```
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
+
- en
|
| 4 |
+
- zh
|
| 5 |
library_name: mlx
|
| 6 |
license: mit
|
| 7 |
pipeline_tag: text-generation
|
| 8 |
tags:
|
| 9 |
- mlx
|
|
|
|
| 10 |
base_model: zai-org/GLM-4.7-Flash
|
| 11 |
---
|
| 12 |
+
|
| 13 |
# mlx-community/GLM-4.7-Flash-8bit-gs32
|
| 14 |
|
| 15 |
This model [mlx-community/GLM-4.7-Flash-8bit-gs32](https://huggingface.co/mlx-community/GLM-4.7-Flash-8bit-gs32) was
|
| 16 |
converted to MLX format from [zai-org/GLM-4.7-Flash](https://huggingface.co/zai-org/GLM-4.7-Flash)
|
| 17 |
+
using mlx-lm version **0.30.5**.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Use with mlx
|
| 20 |
|
|
|
|
| 32 |
if tokenizer.chat_template is not None:
|
| 33 |
messages = [{"role": "user", "content": prompt}]
|
| 34 |
prompt = tokenizer.apply_chat_template(
|
| 35 |
+
messages, add_generation_prompt=True, return_dict=False,
|
| 36 |
)
|
| 37 |
|
| 38 |
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 39 |
+
```
|
model-00001-of-00007.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 sha256:99fb8f49c8724a5f7891e67e85df371cee5f7ee20e54ef5a7ce10e3734fa48e1
|
| 3 |
+
size 5218683006
|
model-00002-of-00007.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 sha256:4fca5a422ac54e1ccb62c060f354323dcc1b50188fe7f2b6a23cdd6f20f17bc2
|
| 3 |
+
size 5265814684
|
model-00003-of-00007.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 sha256:5b68fd4f7b6eb44b7905d0151cdb486c2e358d83ee812ed8fc1bab1aab6c3578
|
| 3 |
+
size 5230443185
|
model-00004-of-00007.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 sha256:5d65eadf756d15bf25a02bf0d8590b83b10022916b9aa93a2626c61e43bee5c5
|
| 3 |
+
size 5230443223
|
model-00005-of-00007.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 sha256:84e4b4739a29e9b6412a9d06093b45a66ca159a56c5f7380974e80285c339ecd
|
| 3 |
+
size 5265814822
|
model-00006-of-00007.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 sha256:99c951773ad5443a0f44c2fdb1d56b83711d88b60c809ad428a4600c6eed9df9
|
| 3 |
+
size 5230443117
|
model-00007-of-00007.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 sha256:21450816200835fbace70686807448fdae66e5eddf56259d2df35a6295859bad
|
| 3 |
+
size 2250422700
|
model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|