Transformers
GGUF
Inference Endpoints
LoneStriker commited on
Commit
d40723f
1 Parent(s): 7a59613

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -1,9 +1,5 @@
1
  gemma-7b-it-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
2
- gemma-7b-it-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
3
- gemma-7b-it-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
4
  gemma-7b-it-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
5
- gemma-7b-it-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
6
  gemma-7b-it-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
7
- gemma-7b-it-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
8
  gemma-7b-it-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
9
  gemma-7b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 
1
  gemma-7b-it-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
 
 
2
  gemma-7b-it-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 
3
  gemma-7b-it-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 
4
  gemma-7b-it-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
5
  gemma-7b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,14 +1,6 @@
1
  ---
2
  library_name: transformers
3
  tags: []
4
- widget:
5
- - text: |
6
- <start_of_turn>user
7
- How does the brain work?<end_of_turn>
8
- <start_of_turn>model
9
- inference:
10
- parameters:
11
- max_new_tokens: 200
12
  extra_gated_heading: "Access Gemma on Hugging Face"
13
  extra_gated_prompt: "To access Gemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging Face and click below. Requests are processed immediately."
14
  extra_gated_button_content: "Acknowledge license"
@@ -27,7 +19,7 @@ This model card corresponds to the 7B instruct version of the Gemma model. You c
27
 
28
  * [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
29
  * [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma)
30
- * [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-7b-it-gg-hf)
31
 
32
  **Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent)
33
 
@@ -73,9 +65,9 @@ tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it")
73
  model = AutoModelForCausalLM.from_pretrained("google/gemma-7b-it")
74
 
75
  input_text = "Write me a poem about Machine Learning."
76
- input_ids = tokenizer(input_text, return_tensors="pt")
77
 
78
- outputs = model.generate(**input_ids)
79
  print(tokenizer.decode(outputs[0]))
80
  ```
81
 
@@ -309,7 +301,7 @@ several advantages in this domain:
309
 
310
  ### Software
311
 
312
- Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture).
313
 
314
  JAX allows researchers to take advantage of the latest generation of hardware,
315
  including TPUs, for faster and more efficient training of large models.
 
1
  ---
2
  library_name: transformers
3
  tags: []
 
 
 
 
 
 
 
 
4
  extra_gated_heading: "Access Gemma on Hugging Face"
5
  extra_gated_prompt: "To access Gemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging Face and click below. Requests are processed immediately."
6
  extra_gated_button_content: "Acknowledge license"
 
19
 
20
  * [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
21
  * [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma)
22
+ * [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335)
23
 
24
  **Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent)
25
 
 
65
  model = AutoModelForCausalLM.from_pretrained("google/gemma-7b-it")
66
 
67
  input_text = "Write me a poem about Machine Learning."
68
+ input_ids = tokenizer(**input_text, return_tensors="pt")
69
 
70
+ outputs = model.generate(input_ids)
71
  print(tokenizer.decode(outputs[0]))
72
  ```
73
 
 
301
 
302
  ### Software
303
 
304
+ Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/ml-pathways).
305
 
306
  JAX allows researchers to take advantage of the latest generation of hardware,
307
  including TPUs, for faster and more efficient training of large models.
gemma-7b-it-Q3_K_L.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24d502df64ae27dc02e44567463184d9a00e433c02c73867dbe653d4dc3ed346
3
- size 4402039968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e817f0fc6f7c421cb314a9a19c9ed3b0f5474cd800b055b20566988c8496dc6
3
+ size 4709393568
gemma-7b-it-Q4_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd87fc03fe3d651ac419ae35f4a0e6d861167db156572b6c4b90fb81822a3547
3
- size 5127231648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c92ce72d07ba4f92b46a50f0e7e04d30ba4700dc49d34f4750e9dd366fbbecca
3
+ size 5330085024
gemma-7b-it-Q5_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:601ea5510042eb36434b85c024f8182350ed9b96b2efeee0157c8035a9042b79
3
- size 6040328352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec8a69c31575b174416d84adc169e8b5969bbe391d52513abfbe8feaa993c001
3
+ size 6144828576