Upload LlamaForCausalLM

README.md

@@ -1,13 +1,14 @@
 ---
 extra_gated_heading: Access Llama 2 on Hugging Face
-extra_gated_description: >-
-  This is a form to enable access to Llama 2 on Hugging Face after you have been
-  granted access from Meta. Please visit the [Meta website](https://ai.meta.com/resources/models-and-libraries/llama-downloads) and accept our
-  license terms and acceptable use policy before submitting this form. Requests
-  will be processed in 1-2 days.
+extra_gated_description: This is a form to enable access to Llama 2 on Hugging Face
+  after you have been granted access from Meta. Please visit the [Meta website](https://ai.meta.com/resources/models-and-libraries/llama-downloads)
+  and accept our license terms and acceptable use policy before submitting this form.
+  Requests will be processed in 1-2 days.
 extra_gated_button_content: Submit
 extra_gated_fields:
-  I agree to share my name, email address and username with Meta and confirm that I have already been granted download access on the Meta website: checkbox
+  ? I agree to share my name, email address and username with Meta and confirm that
+    I have already been granted download access on the Meta website
+  : checkbox
 language:
 - en
 pipeline_tag: text-generation
@@ -18,6 +19,8 @@ tags:
 - pytorch
 - llama
 - llama-2
+- trl
+- sft
 ---
 # **Llama 2**
 Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.

config.json

@@ -1,25 +1,46 @@
 {
+  "_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 4096,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pad_token_id": 0,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.31.0.dev0",
-  "use_cache": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -1,10 +1,10 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
+  "do_sample": true,
   "eos_token_id": 2,
   "pad_token_id": 32000,
-  "do_sample": true,
   "temperature": 0.9,
   "top_p": 0.6,
-  "transformers_version": "4.31.0.dev0"
+  "transformers_version": "4.46.3"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66dec18c9f1705b9387d62f8485f4e7d871ca388718786737ed3c72dbfaac9fb
-size 9976576152
+oid sha256:3a1de4c58437e56a92c27a0a9333685a550b4bdf453481bebb3afda814eaf02c
+size 4807953512

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd6895090da1b2ccffdb93964847709a3b31e6b69fe7dc5a480dce37c811b1d
-size 3500296424
+oid sha256:e5d447419f1baed870ad522be6a83e9801e4a06f51b7aef0e82a1f6cf9e8a79e
+size 524288128