Uploading AWQ model

README.md

@@ -1,3 +1,72 @@
 ---
+base_model: senseable/WestLake-7B-v2
 license: apache-2.0
+datasets:
+ - cognitivecomputations/samantha-data
+library_name: transformers
+model_creator: cognitivecomputations
+model_name: Samantha 1.1 WestLake 7B - AWQ
+model_type: mistral
+pipeline_tag: text-generation
+prompt_template: '<|im_start|>system
+
+ {system_message}<|im_end|>
+
+ <|im_start|>user
+
+ {prompt}<|im_end|>
+
+ <|im_start|>assistant
+
+ '
+quantized_by: Suparious
 ---
+# Samantha 7B v1.1 laser - AWQ
+
+- Model creator: [cognitivecomputations](https://huggingface.co/cognitivecomputations)
+- Original model: [WestLake 7B v2](https://huggingface.co/cognitivecomputations/WestLake-7B-v2)
+- Fine Tuning: [cognitivecomputations](https://huggingface.co/cognitivecomputations/samantha-1.1-westlake-7b-laser)
+
+It follows the implementation of [laserRMT](https://github.com/cognitivecomputations/laserRMT)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/DQ2iBVPM1PA4GKQBgvMEO.png)
+
+## Model description
+
+This repo contains AWQ model files for [cognitivecomputations's Samantha 7B v1.1](https://huggingface.co/cognitivecomputations/samantha-1.1-westlake-7b-laser).
+
+These files were quantised using hardware kindly provided by [SolidRusT Networks](https://solidrust.net/).
+
+### About AWQ
+
+AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
+
+AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
+
+It is supported by:
+
+- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
+- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
+- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
+- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
+- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
+
+## Prompt template: ChatML
+
+```plaintext
+<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+
+Also working with Basic Mistral format:
+
+```plaintext
+<|system|>
+</s>
+<|user|>
+{prompt}</s>
+<|assistant|>
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+ "<|im_end|>": 32000,
+ "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,36 @@
+{
+ "_name_or_path": "./models/samantha-1.1-westlake-7b-laser",
+ "architectures": [
+ "MistralForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 1,
+ "eos_token_id": 32000,
+ "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,
+ "pad_token_id": 2,
+ "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": "4.37.2",
+ "unsloth_version": "2024.1",
+ "use_cache": false,
+ "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "do_sample": true,
+ "eos_token_id": 2,
+ "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1d541788a07f6bc941ab70ddb369d9a88fb0d3e27e730caff7bbc83e8429c4
+size 4150913000

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+ "additional_special_tokens": [
+ "<unk>",
+ "<s>",
+ "</s>",
+ "<|im_end|>"
+ ],
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,67 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "32000": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "32001": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [
+ "<unk>",
+ "<s>",
+ "</s>",
+ "<|im_end|>"
+ ],
+ "bos_token": "<s>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "legacy": true,
+ "model_max_length": 255,
+ "pad_token": "<unk>",
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "trust_remote_code": false,
+ "unk_token": "<unk>",
+ "use_default_system_prompt": true,
+ "use_fast": true
+}