Upload folder using huggingface_hub

README.md

@@ -0,0 +1,52 @@
+---
+tags:
+- finetuned
+- quantized
+- 4-bit
+- AWQ
+- transformers
+- pytorch
+- safetensors
+- mistral
+- text-generation
+- finetuned
+- conversational
+- arxiv:2310.06825
+- license:apache-2.0
+- autotrain_compatible
+- has_space
+- text-generation-inference
+- region:us
+model_name: Mistral-7B-Instruct-v0.1-AWQ
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+inference: false
+model_creator: mistralai
+pipeline_tag: text-generation
+quantized_by: MaziyarPanahi
+---
+# Description
+[MaziyarPanahi/Mistral-7B-Instruct-v0.1-AWQ](https://huggingface.co/MaziyarPanahi/Mistral-7B-Instruct-v0.1-AWQ) is a quantized (AWQ) version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
+
+## How to use
+### Install the necessary packages
+
+```
+pip install --upgrade accelerate autoawq transformers
+```
+
+### Example Python code
+
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "MaziyarPanahi/Mistral-7B-Instruct-v0.1-AWQ"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id).to(0)
+
+text = "User:\nHello can you provide me with top-3 cool places to visit in Paris?\n\nAssistant:\n"
+inputs = tokenizer(text, return_tensors="pt").to(0)
+
+out = model.generate(**inputs, max_new_tokens=300)
+print(tokenizer.decode(out[0], skip_special_tokens=True))
+```

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/home/maziyar/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/9ab9e76e2b09f9f29ea2d56aa5bd139e4445c59e",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "modules_to_not_convert": null,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20cde9ef9b238ba9b11051c0e5d7200c6cb1c715ed4c69d0829ae332c4f27fd1
+size 4150880232

quant_config.json

@@ -0,0 +1,7 @@
+{
+    "zero_point": true,
+    "q_group_size": 128,
+    "w_bit": 4,
+    "version": "GEMM",
+    "modules_to_not_convert": null
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}