Add Cohere2 model (#35224)

docs/source/en/_toctree.yml

@@ -362,6 +362,8 @@
         title: CodeLlama
       - local: model_doc/cohere
         title: Cohere
+      - local: model_doc/cohere2
+        title: Cohere2
       - local: model_doc/convbert
         title: ConvBERT
       - local: model_doc/cpm

docs/source/en/index.md

@@ -99,6 +99,7 @@ Flax), PyTorch, and/or TensorFlow.
 |                       [CodeGen](model_doc/codegen)                       |       ✅        |         ❌         |      ❌      |
 |                    [CodeLlama](model_doc/code_llama)                     |       ✅        |         ❌         |      ✅      |
 |                        [Cohere](model_doc/cohere)                        |       ✅        |         ❌         |      ❌      |
+|                       [Cohere2](model_doc/cohere2)                       |       ✅        |         ❌         |      ❌      |
 |              [Conditional DETR](model_doc/conditional_detr)              |       ✅        |         ❌         |      ❌      |
 |                      [ConvBERT](model_doc/convbert)                      |       ✅        |         ✅         |      ❌      |
 |                      [ConvNeXT](model_doc/convnext)                      |       ✅        |         ✅         |      ❌      |

docs/source/en/model_doc/cohere2.md

@@ -0,0 +1,44 @@
+# Cohere
+
+## Usage tips
+The model and tokenizer can be loaded via:
+
+```python
+# pip install transformers
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "CohereForAI/c4ai-command-r7b-12-2024"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+# Format message with the command-r chat template
+messages = [{"role": "user", "content": "Hello, how are you?"}]
+input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+
+gen_tokens = model.generate(
+    input_ids,
+    max_new_tokens=100,
+    do_sample=True,
+    temperature=0.3,
+    )
+
+gen_text = tokenizer.decode(gen_tokens[0])
+print(gen_text)
+```
+
+## Cohere2Config
+
+[[autodoc]] Cohere2Config
+
+## Cohere2Model
+
+[[autodoc]] Cohere2Model
+    - forward
+
+
+## Cohere2ForCausalLM
+
+[[autodoc]] Cohere2ForCausalLM
+    - forward
+
+

docs/source/en/perf_infer_gpu_one.md

@@ -43,6 +43,7 @@ FlashAttention-2 is currently supported for the following architectures:
 * [Chameleon](https://huggingface.co/docs/transformers/model_doc/chameleon#transformers.Chameleon)
 * [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPModel)
 * [Cohere](https://huggingface.co/docs/transformers/model_doc/cohere#transformers.CohereModel)
+* [Cohere2](https://huggingface.co/docs/transformers/model_doc/cohere2#transformers.Cohere2Model)
 * [GLM](https://huggingface.co/docs/transformers/model_doc/glm#transformers.GLMModel)
 * [Dbrx](https://huggingface.co/docs/transformers/model_doc/dbrx#transformers.DbrxModel)
 * [DistilBert](https://huggingface.co/docs/transformers/model_doc/distilbert#transformers.DistilBertModel)
@@ -227,6 +228,7 @@ For now, Transformers supports SDPA inference and training for the following arc
 * [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPModel)
 * [GLM](https://huggingface.co/docs/transformers/model_doc/glm#transformers.GLMModel)
 * [Cohere](https://huggingface.co/docs/transformers/model_doc/cohere#transformers.CohereModel)
+* [Cohere2](https://huggingface.co/docs/transformers/model_doc/cohere2#transformers.Cohere2Model)
 * [data2vec_audio](https://huggingface.co/docs/transformers/main/en/model_doc/data2vec#transformers.Data2VecAudioModel)
 * [Dbrx](https://huggingface.co/docs/transformers/model_doc/dbrx#transformers.DbrxModel)
 * [DeiT](https://huggingface.co/docs/transformers/model_doc/deit#transformers.DeiTModel)