Upload LlamaForCausalLM

README.md

@@ -1,13 +1,13 @@
 ---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+language:
+- en
+license: llama3.1
+pipeline_tag: text-generation
 tags:
 - int8
 - w8a8
 - text-generation
-language:
-- en
-pipeline_tag: text-generation
-license: llama3.1
-base_model: meta-llama/Meta-Llama-3-8B-Instruct
 ---
 
 # Meta-Llama-3-8B-Instruct-quantized.w4a4

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./Meta-Llama-3-8B-Instruct-quantized.w8a8",
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -18,36 +18,12 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
-  "quantization_config": {
-    "batch_size": 1,
-    "bits": 8,
-    "block_name_to_quantize": null,
-    "cache_block_outputs": true,
-    "damp_percent": 0.01,
-    "dataset": null,
-    "desc_act": true,
-    "exllama_config": {
-      "version": 1
-    },
-    "group_size": -1,
-    "max_input_length": null,
-    "model_seqlen": null,
-    "module_name_preceding_first_block": null,
-    "modules_in_block_to_quantize": null,
-    "pad_token_id": null,
-    "quant_method": "gptq",
-    "sym": true,
-    "tokenizer": null,
-    "true_sequential": true,
-    "use_cuda_fp16": false,
-    "use_exllama": true
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.42.4",
+  "transformers_version": "4.43.4",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -1,6 +1,12 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 128000,
-  "eos_token_id": 128009,
-  "transformers_version": "4.42.4"
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.43.4"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5f3b86d455d87619e371e85a64e7b468e6ff0cf3dd93c4e40acef3644e70181
-size 4986235568
+oid sha256:f38dc229cd79c33c127a791782f9e78039fc57d10cc5148b23206de1d95e097a
+size 4999427512

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:306b103893f9aae093fa46f957c893ee07337b704de597333dee083f72dd94e8
-size 4104182696
+oid sha256:1eaf3136acc221ee97d29dbfce52e7abce46501745337fe6da05f5e13fd89fbb
+size 3559551840