init

README.md

@@ -1,3 +1,45 @@
 ---
 license: apache-2.0
 ---
+
+# Mistral 7B Instruct
+
+AWQ quantized model.
+
+Dependencies:
+
+```
+pip install git+https://github.com/casper-hansen/AutoAWQ.git
+pip install git+https://github.com/huggingface/transformers.git
+```
+
+Example:
+
+```python
+from awq import AutoAWQForCausalLM
+from transformers import AutoTokenizer, TextStreamer
+
+quant_path = "mistral-7b-instruct-v0.1"
+
+# Load model
+model = AutoAWQForCausalLM.from_quantized(quant_path, fuse_layers=True)
+tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True)
+streamer = TextStreamer(tokenizer, skip_special_tokens=True)
+
+# Convert prompt to tokens
+text = "<s>[INST] What is your favourite condiment? [/INST]"
+"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
+"[INST] Do you have mayonnaise recipes? [/INST]"
+
+tokens = tokenizer(
+    text, 
+    return_tensors='pt'
+).input_ids.cuda()
+
+# Generate output
+generation_output = model.generate(
+    tokens, 
+    streamer=streamer,
+    max_new_tokens=512
+)
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/2b962727a90291ab7049acf983dcf508bbc488ad",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "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,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0fdba638d7c5684e0d7be2ccc7407c941345fada7dab335c8f6ef768894f94
+size 4151034841

quant_config.json

@@ -0,0 +1,6 @@
+{
+    "zero_point": true,
+    "q_group_size": 128,
+    "w_bit": 4,
+    "version": "GEMM"
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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>",
+  "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": true
+}