初始化项目，由ModelHub XC社区提供模型

Model: ciCic/llama-3.2-1B-Instruct-AWQ
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,145 @@
+---
+language:
+- en
+- de
+- fr
+- it
+- pt
+- hi
+- es
+- th
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- facebook
+- meta
+- pytorch
+- llama-3
+license: llama3.2
+base_model:
+- meta-llama/Llama-3.2-1B-Instruct
+---
+# Represents
+A quantized version of Llama 3.2 1B Instruct with Activation-aware Weight Quantization (AWQ)[https://github.com/mit-han-lab/llm-awq]
+
+## Use with transformers/autoawq
+Starting with 
+- `transformers==4.45.1`
+- `accelerate==0.34.2`
+- `torch==2.3.1`
+- `numpy==2.0.0`
+- `autoawq==0.2.6`
+
+Experimented with
+- OS  = Windows
+- GPU = Nvidia GeForce RTX 3080 10gb
+- CPU = Intel Core i5-9600K
+- RAM = 32GB
+
+### For CUDA users
+
+**AutoAWQ**
+  
+NOTE: this example uses `fuse_layers=True` to fuse attention and mlp layers together for faster inference
+```python
+from awq import AutoAWQForCausalLM
+from transformers import AutoTokenizer, TextStreamer
+
+quant_id = "ciCic/llama-3.2-1B-Instruct-AWQ"
+model = AutoAWQForCausalLM.from_quantized(quant_id, fuse_layers=True)
+tokenizer = AutoTokenizer.from_pretrained(quant_id, trust_remote_code=True)
+
+streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+
+# Declare prompt
+prompt = "You're standing on the surface of the Earth. "\
+        "You walk one mile south, one mile west and one mile north. "\
+        "You end up exactly where you started. Where are you?"
+
+# Tokenization of the prompt
+tokens = tokenizer(
+   prompt, 
+    return_tensors='pt'
+).input_ids.cuda()
+
+# Generate output in a streaming fashion
+generation_output = model.generate(
+    tokens, 
+    streamer=streamer,
+    max_new_tokens=512
+)
+```
+
+**Transformers**
+
+```python
+from transformers import AutoTokenizer, TextStreamer, AutoModelForCausalLM
+import torch
+
+quant_id = "ciCic/llama-3.2-1B-Instruct-AWQ"
+tokenizer = AutoTokenizer.from_pretrained(quant_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    quant_id, 
+    torch_dtype=torch.float16, 
+    low_cpu_mem_usage=True,
+    device_map="cuda"
+)
+
+streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+
+# Convert prompt to tokens
+prompt = "You're standing on the surface of the Earth. "\
+        "You walk one mile south, one mile west and one mile north. "\
+        "You end up exactly where you started. Where are you?"
+
+tokens = tokenizer(
+   prompt, 
+    return_tensors='pt'
+).input_ids.cuda()
+
+# Generate output
+generation_output = model.generate(
+    tokens, 
+    streamer=streamer,
+    max_new_tokens=512
+)
+```
+
+#### Issue/Solution
+- torch.from_numpy fails
+  - This might be due to certain issues within `torch==2.3.1` .cpp files. Since AutoAWQ uses torch version 2.3.1, instead of most recent, this issue might occur within module `marlin.py -> def _get_perms()`
+  - Module path: Python\Python311\site-packages\awq\modules\linear\marlin.py
+  - Solution:
+    - there are several operations to numpy (cpu) then back to tensor (gpu) which could be completely replaced by tensor without having to use numpy, this will solve (temporarily) the from_numpy() issue
+```python
+def _get_perms():
+    perm = []
+    for i in range(32):
+        perm1 = []
+        col = i // 4
+        for block in [0, 1]:
+            for row in [
+                2 * (i % 4),
+                2 * (i % 4) + 1,
+                2 * (i % 4 + 4),
+                2 * (i % 4 + 4) + 1,
+            ]:
+                perm1.append(16 * row + col + 8 * block)
+
+        for j in range(4):
+            perm.extend([p + 256 * j for p in perm1])
+
+    # perm = np.array(perm)
+    perm = torch.asarray(perm)
+    # interleave = np.array([0, 2, 4, 6, 1, 3, 5, 7])
+    interleave = torch.asarray([0, 2, 4, 6, 1, 3, 5, 7])
+    perm = perm.reshape((-1, 8))[:, interleave].ravel()
+    # perm = torch.from_numpy(perm)
+    scale_perm = []
+    for i in range(8):
+        scale_perm.extend([i + 8 * j for j in range(8)])
+    scale_perm_single = []
+    for i in range(4):
+        scale_perm_single.extend([2 * i + j for j in [0, 1, 8, 9, 16, 17, 24, 25]])
+    return perm, scale_perm, scale_perm_single
+```

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "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_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.45.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754a7a3c9e43ed5a55175d379322f8462d82cb2d5c29676e2caf1c69d58931c6
+size 1556394472

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}