Upload folder using huggingface_hub

README.md

@@ -186,7 +186,6 @@ extra_gated_fields:
 extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
 extra_gated_button_content: Submit
 ---
-# Not include _./original_ from original repo.
 
 ## Model Details
 
@@ -274,7 +273,9 @@ This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with
 
 ### Use with transformers
 
-See the snippet below for usage with Transformers:
+You can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the `generate()` function. Let's see examples of both.
+
+#### Transformers pipeline
 
 ```python
 import transformers
@@ -286,7 +287,7 @@ pipeline = transformers.pipeline(
     "text-generation",
     model=model_id,
     model_kwargs={"torch_dtype": torch.bfloat16},
-    device="cuda",
+    device="auto",
 )
 
 messages = [
@@ -301,8 +302,8 @@ prompt = pipeline.tokenizer.apply_chat_template(
 )
 
 terminators = [
-    tokenizer.eos_token_id,
-    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+    pipeline.tokenizer.eos_token_id,
+    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
 ]
 
 outputs = pipeline(
@@ -316,6 +317,50 @@ outputs = pipeline(
 print(outputs[0]["generated_text"][len(prompt):])
 ```
 
+#### Transformers AutoModelForCausalLM
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+response = outputs[0][input_ids.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))
+```
+
+
 ### Use with `llama3`
 
 Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3)

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "eos_token_id": [128001, 128009],
   "transformers_version": "4.40.0.dev0"
 }

tokenizer_config.json

@@ -2050,7 +2050,7 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
   "model_input_names": [