Upload folder using huggingface_hub

README.md

@@ -0,0 +1,100 @@
+---
+license: apache-2.0
+tags:
+- finetuned
+- quantized
+- 4-bit
+- gptq
+- transformers
+- safetensors
+- llama
+- text-generation
+- dataset:ai2_arc
+- dataset:unalignment/spicy-3.1
+- dataset:codeparrot/apps
+- dataset:facebook/belebele
+- dataset:boolq
+- dataset:jondurbin/cinematika-v0.1
+- dataset:drop
+- dataset:lmsys/lmsys-chat-1m
+- dataset:TIGER-Lab/MathInstruct
+- dataset:cais/mmlu
+- dataset:Muennighoff/natural-instructions
+- dataset:openbookqa
+- dataset:piqa
+- dataset:Vezora/Tested-22k-Python-Alpaca
+- dataset:cakiki/rosetta-code
+- dataset:Open-Orca/SlimOrca
+- dataset:spider
+- dataset:squad_v2
+- dataset:migtissera/Synthia-v1.3
+- dataset:datasets/winogrande
+- dataset:nvidia/HelpSteer
+- dataset:Intel/orca_dpo_pairs
+- dataset:unalignment/toxic-dpo-v0.1
+- dataset:jondurbin/truthy-dpo-v0.1
+- dataset:allenai/ultrafeedback_binarized_cleaned
+- dataset:Squish42/bluemoon-fandom-1-1-rp-cleaned
+- dataset:LDJnr/Capybara
+- dataset:JULIELab/EmoBank
+- dataset:kingbri/PIPPA-shareGPT
+- license:other
+- autotrain_compatible
+- endpoints_compatible
+- text-generation-inference
+- region:us
+- has_space
+model_name: UNA-34Beagles-32K-bf16-v1-GPTQ
+base_model: one-man-army/UNA-34Beagles-32K-bf16-v1
+inference: false
+model_creator: one-man-army
+pipeline_tag: text-generation
+quantized_by: MaziyarPanahi
+---
+# Description
+[MaziyarPanahi/UNA-34Beagles-32K-bf16-v1-GPTQ](https://huggingface.co/MaziyarPanahi/UNA-34Beagles-32K-bf16-v1-GPTQ) is a quantized (GPTQ) version of [one-man-army/UNA-34Beagles-32K-bf16-v1](https://huggingface.co/one-man-army/UNA-34Beagles-32K-bf16-v1)
+
+## How to use
+### Install the necessary packages
+
+```
+pip install --upgrade accelerate auto-gptq transformers
+```
+
+### Example Python code
+
+
+```python
+from transformers import AutoTokenizer, pipeline
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+import torch
+
+model_id = "MaziyarPanahi/UNA-34Beagles-32K-bf16-v1-GPTQ"
+
+quantize_config = BaseQuantizeConfig(
+        bits=4,
+        group_size=128,
+        desc_act=False
+    )
+
+model = AutoGPTQForCausalLM.from_quantized(
+        model_id,
+        use_safetensors=True,
+        device="cuda:0",
+        quantize_config=quantize_config)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=512,
+    temperature=0.7,
+    top_p=0.95,
+    repetition_penalty=1.1
+)
+
+outputs = pipe("What is a large language model?")
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "one-man-army/UNA-34Beagles-32K-bf16-v1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2148e4c1d8590731fbd8d153aec95e8e712550cef51d62fa1b4766f1e28d5f70
+size 19248968072

quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.1,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' '  + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}