Hubert commit

README.md

@@ -0,0 +1,15 @@
+---
+language:
+- pl
+datasets:
+  - Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
+license: other
+model_type: llama-2
+pipeline_tag: text-generation
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-2
+---

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "results/meta-llama/Llama-2-7b-hf-PL-lora/unload",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

gptq_model-4bit-128g.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da8cbbed10f34933a3af8a4264739c88ce2eeac38017ed3fa8ae9079f7bf149
+size 3896994967

quantize_config.json

@@ -0,0 +1,10 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}