提交chatglm2-6b推理的示例代码

README.md

+# ChatGLM2-6B_CPP
+
+## 模型介绍
+ChatGLM**2**-6B 是开源中英双语对话模型 [ChatGLM-6B](https://github.com/THUDM/ChatGLM-6B) 的第二代版本，在保留了初代模型对话流畅、部署门槛较低等众多优秀特性的基础之上，ChatGLM**2**-6B 引入了如下新特性：
+
+1. **更强大的性能**：基于 ChatGLM 初代模型的开发经验，我们全面升级了 ChatGLM2-6B 的基座模型。ChatGLM2-6B 使用了 [GLM](https://github.com/THUDM/GLM) 的混合目标函数，经过了 1.4T 中英标识符的预训练与人类偏好对齐训练，[评测结果](https://github.com/THUDM/ChatGLM2-6B#评测结果)显示，相比于初代模型，ChatGLM2-6B 在 MMLU（+23%）、CEval（+33%）、GSM8K（+571%） 、BBH（+60%）等数据集上的性能取得了大幅度的提升，在同尺寸开源模型中具有较强的竞争力。
+2. **更长的上下文**：基于 [FlashAttention](https://github.com/HazyResearch/flash-attention) 技术，我们将基座模型的上下文长度（Context Length）由 ChatGLM-6B 的 2K 扩展到了 32K，并在对话阶段使用 8K 的上下文长度训练。对于更长的上下文，我们发布了 [ChatGLM2-6B-32K](https://huggingface.co/THUDM/chatglm2-6b-32k) 模型。[LongBench](https://github.com/THUDM/LongBench) 的测评结果表明，在等量级的开源模型中，ChatGLM2-6B-32K 有着较为明显的竞争优势。
+3. **更高效的推理**：基于 [Multi-Query Attention](http://arxiv.org/abs/1911.02150) 技术，ChatGLM2-6B 有更高效的推理速度和更低的显存占用：在官方的模型实现下，推理速度相比初代提升了 42%，INT4 量化下，6G 显存支持的对话长度由 1K 提升到了 8K。
+4. **更开放的协议**：ChatGLM2-6B 权重对学术研究**完全开放**，在填写[问卷](https://open.bigmodel.cn/mla/form)进行登记后**亦允许免费商业使用**。
+
+本项目主要针对ChatGLM2-6B在DCU平台的推理性能优化，达到DCU平台较快的对话效果。
+
+## 模型推理
+
+### 下载镜像
+
+在光源可拉取推理的docker镜像，拉取方式如下：
+
+```
+docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:glm-ft-v1.0
+```
+
+### 安装方法
+
+```
+#进入本工程目录
+cd package
+python setup install
+```
+
+### ChatGLM2原版模型转换
+
+```
+# 将模型转换脚本chatglm_export.py移动到原版ChatGLM2-6B环境中，也可以根据工程自带的requirements.txt安装相关依赖
+# 如果使用自己finetune的模型需要修改chatglm_export.py文件中创建tokenizer, model时的模型存放路径
+# 执行：
+python3 chatglm_export.py chatglm2-6b-fp16.bin float16 # 导出fp16模型，参数为导出的模型路径
+python3 chatglm_export.py chatglm2-6b-fp16.bin int8 #    导出int8模型，参数为导出的模型路径
+```
+
+
+### 运行ChatGLM2-6B模型实例
+
+```
+# 命令行聊天程序，使用了模型创建以及流式对话效果
+python cli_demo.py -p chatglm2-6b-fp16.bin
+
+# 简易webui，需要先安装streamlit-chat
+streamlit run web_demo.py chatglm2-6b-fp16.bin 
+```
+
+## 源码仓库及问题反馈
+
+https://developer.hpccube.com/codes/modelzoo/chatglm2-6b_cpp
+
+## 参考
+
+https://github.com/THUDM/ChatGLM2-6B

chatglm_export.py

+import sys
+from transformers import AutoTokenizer, AutoModel
+import struct
+import numpy as np
+import torch
+
+def writeString(fo, s):
+    fo.write(struct.pack('i', len(s)))
+    fo.write(s.encode())
+
+def writeKeyValue(fo, key, value):
+    writeString(fo, key)
+    writeString(fo, value)
+
+fastllm_data_type_dict = {
+    "int4": 8,
+    "int8": 3,
+    "float16": 7,
+    "float32": 0,
+}
+fastllm_weight_type_dict = {
+    "linear": 1,
+    "embedding": 2
+}
+
+v = np.random.randint(-127, 127, [10, 20]);
+temp = v;
+c_max = np.expand_dims(np.abs(v).max(axis = -1), -1)
+c_scale = c_max / 127.0
+v = (v / c_scale + 128.5).clip(1, 255).astype(np.uint8)
+
+def write_int8(fo, v):
+    c_max = np.expand_dims(np.abs(v).max(axis = -1), -1).clip(0.1, 1e100)
+    c_scale = c_max / 127.0
+    v = (v / c_scale + 128.5).clip(1, 255).astype(np.uint8)
+    fo.write(struct.pack('i', 3))
+    fo.write(struct.pack('i', 0))
+    for i in range(c_max.shape[0]):
+        fo.write(struct.pack('f', -c_max[i][0]));
+        fo.write(struct.pack('f', c_max[i][0]));
+    fo.write(v.data)
+
+def write_int4(fo, v):
+    c_min = np.expand_dims(-np.abs(v).max(axis = -1), -1)
+    c_max = np.expand_dims(np.abs(v).max(axis = -1), -1)
+    c_scale = c_max / 7.0
+    c_min = c_scale * -8.0
+    v = (v - c_min) / c_scale
+    v = (v + 0.5).astype(np.int8).clip(0, 15).astype(np.uint8)
+    v = v[:, 0::2] * 16 + v[:, 1::2]
+    fo.write(struct.pack('i', 8))
+    fo.write(struct.pack('i', 0))
+    for i in range(c_min.shape[0]):
+        fo.write(struct.pack('f', c_min[i][0]));
+        fo.write(struct.pack('f', c_max[i][0]));
+    fo.write(v.data)
+
+def tofile(exportPath,
+           model,
+           tokenizer = None,
+           pre_prompt = None,
+           user_role = None,
+           bot_role = None,
+           history_sep = None,
+           dtype = "float16"):
+    if (dtype not in fastllm_data_type_dict):
+        print("dtype should in ", list(fastllm_data_type_dict.keys()))
+        exit(0)
+
+    dict = model.state_dict()
+    fo = open(exportPath, "wb")
+
+    # 0. version id
+    fo.write(struct.pack('i', 2))
+
+    # 0.1 model info
+    modelInfo = model.config.__dict__
+    if model.generation_config is not None:
+        modelInfo.update(model.generation_config.__dict__)
+    if ("model_type" not in modelInfo):
+        print("unknown model_type.")
+        exit(0)
+
+    if (pre_prompt):
+        modelInfo["pre_prompt"] = pre_prompt
+    if (user_role):
+        modelInfo["user_role"] = user_role
+    if (bot_role):
+        modelInfo["bot_role"] = bot_role
+    if (history_sep):
+        modelInfo["history_sep"] = history_sep
+
+    modelInfo["tokenizer_use_score"] = "1" # 分词带分数
+
+    fo.write(struct.pack('i', len(modelInfo)))
+    for it in modelInfo.keys():
+        writeKeyValue(fo, str(it), str(modelInfo[it]))
+
+    # 1. vocab
+    if (tokenizer):
+        if (hasattr(tokenizer, "tokenizer")):
+            if (modelInfo['model_type'] == "qwen"):
+                pass
+            else:
+                tokenizer = tokenizer.tokenizer
+        if (hasattr(tokenizer, "sp_model")):
+            piece_size = tokenizer.sp_model.piece_size()
+            fo.write(struct.pack('i', piece_size))
+            for i in range(piece_size):
+                s = tokenizer.sp_model.id_to_piece(i).encode()
+                fo.write(struct.pack('i', len(s)))
+                for c in s:
+                    fo.write(struct.pack('i', c))
+                fo.write(struct.pack('i', i))
+                fo.write(struct.pack('f', float(tokenizer.sp_model.get_score(i))))
+        else:
+            vocab = tokenizer.get_vocab()
+            fo.write(struct.pack('i', len(vocab)))
+            for v in vocab.keys():
+                if (modelInfo['model_type'] == "qwen"):
+                    s = v
+                else:
+                    s = v.decode()
+                if (modelInfo["model_type"] == "moss"):
+                    s = [(ord(c) if c not in tokenizer.byte_decoder else tokenizer.byte_decoder[c]) for c in v]
+                fo.write(struct.pack('i', len(s)))
+                for c in s:
+                    fo.write(struct.pack('i', c))
+                fo.write(struct.pack('i', vocab[v]))
+                fo.write(struct.pack('f', 1.0))
+    else:
+        fo.write(struct.pack('i', 0))
+
+    weight_type_dict = {}
+    module_dict = {}
+    for key, m in model.named_modules():
+        if (isinstance(m, torch.nn.Linear)):
+            weight_type_dict[key + ".weight"] = "linear"
+            module_dict[key + ".weight"] = m
+        if (isinstance(m, torch.nn.Embedding)):
+            weight_type_dict[key] = "embedding"
+
+    # 2. weight
+    fo.write(struct.pack('i', len(dict)))
+    tot = 0
+    for key in dict:
+        ori_data_type = 0
+        ori_np_data_type = np.float32
+        cur_weight_type = 0
+        if (key in weight_type_dict and weight_type_dict[key] in fastllm_weight_type_dict):
+            cur_weight_type = fastllm_weight_type_dict[weight_type_dict[key]]
+        to_data_type = 0
+        if (cur_weight_type == 1):
+            to_data_type = fastllm_data_type_dict[dtype]
+            if (to_data_type == 7):
+                ori_data_type = 7
+                ori_np_data_type = np.float16
+
+        cur = dict[key].numpy().astype(ori_np_data_type)
+        fo.write(struct.pack('i', len(key)))
+        fo.write(key.encode())
+        fo.write(struct.pack('i', len(cur.shape)))
+        for i in cur.shape:
+            fo.write(struct.pack('i', i))
+        if (to_data_type == 3):
+            write_int8(fo, cur)
+        elif (to_data_type == 8):
+            write_int4(fo, cur)
+        else:
+            fo.write(struct.pack('i', to_data_type))
+            fo.write(cur.data)
+        tot += 1
+        print("output (", tot, "/", len(dict), end = " )\r")
+    print("\nfinish.")
+    fo.close()
+
+if __name__ == "__main__":
+    tokenizer = AutoTokenizer.from_pretrained("./chatglm2-6b/", trust_remote_code=True)
+    model = AutoModel.from_pretrained("./chatglm2_model/chatglm2-6b/", trust_remote_code=True)
+    model = model.eval()
+
+    dtype = sys.argv[2] if len(sys.argv) >= 3 else "float16"
+    exportPath = sys.argv[1] if len(sys.argv) >= 2 else "chatglm-6b-' + dtype + '.bin"
+    tofile(exportPath, model, tokenizer, dtype = dtype)

cli_demo.py

+import argparse
+from fastllm_pytools import llm
+
+def args_parser():
+    parser = argparse.ArgumentParser(description = 'fastllm_chat_demo')
+    parser.add_argument('-p', '--path', type = str, required = True, default = '', help = '模型文件的路径')
+    args = parser.parse_args()
+    return args
+
+if __name__ == "__main__":
+    args = args_parser()
+    model = llm.model(args.path)
+
+    history = []
+    print("输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
+    while True:
+        query = input("\n用户：")
+        if query.strip() == "stop":
+            break
+        if query.strip() == "clear":
+            history = []
+            print("输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
+            continue
+        print("AI:", end = "");
+        curResponse = "";
+        for response in model.stream_response(query, history = history):
+            curResponse += response;
+            print(response, flush = True, end = "")
+        history.append((query, curResponse))
\ No newline at end of file

package/fastllm_pytools/__init__.py

+__all__ = ["llm"]
\ No newline at end of file

package/fastllm_pytools/hf_model.py

+from fastllm_pytools import llm;
+import torch;
+import ctypes;
+import numpy as np;
+
+fastllm_data_type_dict = {
+    "int4": 8,
+    "int8": 3,
+    "float16": 7
+}
+fastllm_weight_type_dict = {
+    "linear": 1,
+    "embedding": 2,
+    "QuantizedLinear": 111
+}
+
+def create(model,
+           tokenizer = None,
+           pre_prompt = None,
+           user_role = None,
+           bot_role = None,
+           history_sep = None,
+           dtype = "float16"):
+    if (dtype not in fastllm_data_type_dict):
+        print("dtype should in ", list(fastllm_data_type_dict.keys()));
+        exit(0);
+
+    # 0.1 model info
+    modelInfo = model.config.__dict__
+    if (pre_prompt):
+        modelInfo["pre_prompt"] = pre_prompt;
+    if (user_role):
+        modelInfo["user_role"] = user_role;
+    if (bot_role):
+        modelInfo["bot_role"] = bot_role;
+    if (history_sep):
+        modelInfo["history_sep"] = history_sep;
+    if (modelInfo["model_type"] == "baichuan" and hasattr(model, "model") and hasattr(model.model, "get_alibi_mask")):
+        # Baichuan 2代
+        modelInfo["use_alibi"] = "1";
+        modelInfo["pre_prompt"] = "";
+        modelInfo["user_role"] = ("<FLM_FIX_TOKEN_" + str(model.generation_config.user_token_id) + "> ") if hasattr(model.generation_config, "user_token_id") else "";
+        modelInfo["bot_role"] = ("<FLM_FIX_TOKEN_" + str(model.generation_config.assistant_token_id) + ">") if hasattr(model.generation_config, "assistant_token_id") else "";
+        modelInfo["history_sep"] = "";
+    if (modelInfo["model_type"] == "qwen"):
+        modelInfo["im_end_id"] = tokenizer.im_end_id
+        modelInfo["im_start_id"] = tokenizer.im_start_id
+
+
+    weight_type_dict = {};
+    module_dict = {};
+    weight_bits = {};
+    for key, m in model.named_modules():
+        if (str(type(m)).find("QuantizedLinear") != -1):
+            weight_type_dict[key + ".weight"] = "QuantizedLinear";
+            weight_bits[key + ".weight"] = m.weight_bit_width;
+        if (isinstance(m, torch.nn.Linear)):
+            weight_type_dict[key + ".weight"] = "linear";
+            module_dict[key + ".weight"] = m;
+        if (isinstance(m, torch.nn.Embedding)):
+            weight_type_dict[key] = "embedding";
+
+    model = model.cpu();
+    dict = model.state_dict();
+    model_type = model.config.__dict__["model_type"];
+    model = llm.fastllm_lib.create_empty_llm_model(model_type.encode());
+    for it in modelInfo.keys():
+        llm.fastllm_lib.add_dict_llm_model(model, str(it).encode(), str(modelInfo[it]).encode());
+
+    # 1. vocab
+    if (tokenizer):
+        if (hasattr(tokenizer, "tokenizer")):
+            if modelInfo["model_type"] == "qwen":
+                pass
+            else:
+                tokenizer = tokenizer.tokenizer;
+        if (hasattr(tokenizer, "sp_model")):
+            piece_size = tokenizer.sp_model.piece_size();
+            for i in range(piece_size):
+                llm.fastllm_lib.add_tokenizer_word_llm_model(model, tokenizer.sp_model.id_to_piece(i).encode(),
+                                                             i, ctypes.c_float(tokenizer.sp_model.get_score(i)));
+        else:
+            vocab = tokenizer.get_vocab();
+            for v in vocab.keys():
+                if (modelInfo["model_type"] == "moss"):
+                    vv = [(ord(c) if c not in tokenizer.byte_decoder else tokenizer.byte_decoder[c]) for c in v];
+                    llm.fastllm_lib.add_tokenizer_word_llm_model(model, vv, vocab[v], ctypes.c_float(1.0));
+                elif (modelInfo["model_type"] == "qwen"):
+                    llm.fastllm_lib.add_tokenizer_word_llm_model(model, v, vocab[v], ctypes.c_float(1.0));
+                else:
+                    llm.fastllm_lib.add_tokenizer_word_llm_model(model, v.encode(), vocab[v], ctypes.c_float(1.0));
+    tot = 0;
+    for key in dict:
+        ori_data_type = 0;
+        ori_np_data_type = np.float32;
+        cur_weight_type = 0;
+        if (key in weight_type_dict and weight_type_dict[key] in fastllm_weight_type_dict):
+            cur_weight_type = fastllm_weight_type_dict[weight_type_dict[key]];
+        to_data_type = 0;
+
+        if (cur_weight_type == 1):
+            to_data_type = fastllm_data_type_dict[dtype];
+            if (to_data_type == 7):
+                ori_data_type = 7;
+                ori_np_data_type = np.float16;
+        elif (cur_weight_type == 2):
+            # TODO bfloat
+            to_data_type = 0;
+
+        if (cur_weight_type == 111):
+            llm.fastllm_lib.add_qlinear_weight_llm_model(model, key.encode(),
+                                                 len(dict[key].shape),
+                                                 (ctypes.c_int * len(dict[key].shape))(*list(dict[key].shape)),
+                                                 weight_bits[key],
+                                                 dict[key + "_scale"].numpy().astype(np.float32).ctypes.data_as(ctypes.c_void_p),
+                                                 dict[key].numpy().ctypes.data_as(ctypes.c_void_p));
+        else:
+            llm.fastllm_lib.add_weight_llm_model(model, key.encode(),
+                                             len(dict[key].shape),
+                                             (ctypes.c_int * len(dict[key].shape))(*list(dict[key].shape)),
+                                             to_data_type, cur_weight_type, ori_data_type,
+                                             dict[key].numpy().astype(ori_np_data_type).ctypes.data_as(ctypes.c_void_p));
+        tot += 1;
+        print("convert (", tot, "/", len(dict), end = " )\r");
+
+    print("");
+    llm.fastllm_lib.init_params_llm_model(model);
+    llm.fastllm_lib.warmup_llm_model(model);
+    ret = llm.model("", id = model);
+    return ret;
+

package/fastllm_pytools/llm.py

+import ctypes;
+import os;
+from typing import Optional, Tuple, Union, List, Callable, Dict, Any;
+
+import platform
+if platform.system() == 'Windows':
+    fastllm_lib = ctypes.cdll.LoadLibrary(os.path.join(os.path.split(os.path.realpath(__file__))[0], "fastllm_tools.dll"))
+else:
+    fastllm_lib = ctypes.cdll.LoadLibrary(os.path.join(os.path.split(os.path.realpath(__file__))[0], "libfastllm_tools.so"))
+
+fastllm_lib.create_llm_model.argtypes = [ctypes.c_char_p]
+fastllm_lib.create_llm_model.restype = ctypes.c_int
+
+fastllm_lib.launch_response_llm_model.argtypes = [ctypes.c_int, ctypes.c_int, ctypes.c_void_p,
+                                                  ctypes.c_int, ctypes.c_bool, ctypes.c_float, ctypes.c_int,
+                                                  ctypes.c_float, ctypes.c_float, ctypes.c_bool]
+fastllm_lib.launch_response_llm_model.restype = ctypes.c_int
+
+fastllm_lib.fetch_response_llm_model.argtypes = [ctypes.c_int, ctypes.c_int]
+fastllm_lib.fetch_response_llm_model.restype = ctypes.c_int
+
+fastllm_lib.fetch_response_logits_llm_model.argtypes = [ctypes.c_int, ctypes.c_int, ctypes.POINTER(ctypes.c_float)]
+fastllm_lib.fetch_response_logits_llm_model.restype = ctypes.c_int
+
+fastllm_lib.response_str_llm_model.argtypes = [ctypes.c_int, ctypes.c_char_p,
+                                               ctypes.c_int, ctypes.c_bool, ctypes.c_float, ctypes.c_int,
+                                               ctypes.c_float, ctypes.c_float, ctypes.c_bool]
+fastllm_lib.response_str_llm_model.restype = ctypes.c_char_p
+
+fastllm_lib.launch_response_str_llm_model.argtype = [ctypes.c_int, ctypes.c_char_p,
+                                                     ctypes.c_int, ctypes.c_bool, ctypes.c_float, ctypes.c_int,
+                                                     ctypes.c_float, ctypes.c_float, ctypes.c_bool]
+fastllm_lib.launch_response_str_llm_model.restype = ctypes.c_int
+
+fastllm_lib.fetch_response_str_llm_model.argtypes = [ctypes.c_int, ctypes.c_int]
+fastllm_lib.fetch_response_str_llm_model.restype = ctypes.c_char_p
+
+fastllm_lib.make_history_llm_model.argtype = [ctypes.c_int, ctypes.c_char_p, ctypes.c_int, ctypes.c_char_p, ctypes.c_char_p]
+fastllm_lib.make_history_llm_model.restype = ctypes.c_char_p
+
+fastllm_lib.make_input_llm_model.argtype = [ctypes.c_int, ctypes.c_char_p, ctypes.c_int, ctypes.c_char_p]
+fastllm_lib.make_input_llm_model.restype = ctypes.c_char_p
+
+fastllm_lib.add_tokenizer_word_llm_model.argtype = [ctypes.c_int, ctypes.c_char_p, ctypes.c_float, ctypes.c_int]
+
+fastllm_lib.set_device_map.argtype = [ctypes.c_int, ctypes.c_void_p, ctypes.c_char_p, ctypes.c_void_p]
+
+def set_cpu_threads(threads: int):
+    fastllm_lib.set_cpu_threads(threads);
+
+def get_cpu_threads() -> int:
+    return fastllm_lib.get_cpu_threads();
+
+def print_ins_info():
+    fastllm_lib.print_cpu_ins();
+
+def set_cpu_kvcache(cpu_kvcache):
+    fastllm_lib.set_kvcache_in_cpu(ctypes.c_bool(cpu_kvcache));
+
+def get_cpu_kvcache():
+    return fastllm_lib.get_kvcache_in_cpu();
+
+def set_cpu_low_mem(low_mem):
+    fastllm_lib.set_cpu_low_mem(ctypes.c_bool(low_mem));
+
+def get_cpu_low_mem():
+    return fastllm_lib.get_cpu_low_mem();
+
+def set_device_map(device_map):
+    devices = [];
+    values = [];
+    if (isinstance(device_map, str)):
+        devices.append(device_map);
+        values.append(1);
+    elif (isinstance(device_map, list)):
+        devices = [str(x) for x in device_map];
+        values = [1 for x in device_map];
+    elif (isinstance(device_map, dict)):
+        devices = [str(x) for x in device_map.keys()];
+        values = [int(device_map[x]) for x in device_map.keys()];
+    else:
+        print("set_device_map error.");
+        return;
+    device_str = ''.join(devices);
+    device_len = [len(x) for x in devices];
+    fastllm_lib.set_device_map(len(device_len),
+                               (ctypes.c_int * len(device_len))(*device_len),
+                               device_str.encode(),
+                               (ctypes.c_int * len(values))(*values));
+def from_hf(model,
+            tokenizer = None,
+            dtype = "float16"):
+    from fastllm_pytools import hf_model;
+    return hf_model.create(model, tokenizer, dtype = dtype);
+
+class model:
+    def __init__ (self, path : str,
+                  id : int = -99999):
+        if (id != -99999):
+            self.model = id;
+        else:
+            self.model = fastllm_lib.create_llm_model(path.encode());
+        self.direct_query = False;
+
+    def get_prompt(self,
+                   query: str,
+                   history: List[Tuple[str, str]] = None) -> str:
+        if (not(history)):
+            history = [];
+        prompt = "";
+        for i, (old_query, response) in enumerate(history):
+            prompt = fastllm_lib.make_history_llm_model(self.model, prompt.encode(), i, old_query.encode(), response.encode()).decode();
+        prompt = fastllm_lib.make_input_llm_model(self.model, prompt.encode(), len(history), query.encode()).decode();
+        return prompt;
+
+    def save(self, path : str):
+        fastllm_lib.save_llm_model(self.model, path.encode());
+
+    def eval(self):
+        pass;
+
+    def response_logits(self,
+                        query: str,
+                        history: List[Tuple[str, str]] = None,
+                        tokenizer = None) -> str:
+        prompt = query if self.direct_query else self.get_prompt(query, history);
+        if (tokenizer == None):
+            handle = fastllm_lib.launch_response_str_llm_model(self.model, prompt.encode(),
+                                                           ctypes.c_int(1), ctypes.c_bool(False), ctypes.c_float(1), ctypes.c_int(1),
+                                                           ctypes.c_float(1), ctypes.c_float(1), ctypes.c_bool(True));
+        else:
+            input = tokenizer.encode(prompt);
+            handle = fastllm_lib.launch_response_llm_model(self.model, len(input), (ctypes.c_int * len(input))(*input),
+                                                           1, False, 1, 1, 1, 1, True);
+        vocab_size = fastllm_lib.get_tokenizer_vocab_size(self.model);
+        logits = list(range(vocab_size))
+        array = (ctypes.c_float * (vocab_size * 4))(*logits);
+        ret = fastllm_lib.fetch_response_logits_llm_model(self.model, handle, array);
+        out = list(array)[:vocab_size];
+        while (ret != -1):
+            ret = fastllm_lib.fetch_response_logits_llm_model(self.model, handle, array);
+        return out;
+
+    def response(self,
+                 query: str,
+                 history: List[Tuple[str, str]] = None,
+                 max_length: int = 8192, do_sample = True, top_p = 0.8, top_k = 1, temperature = 1.0, repeat_penalty = 1.0) -> str:
+        ret = "";
+        for i in self.stream_response(query = query,
+                                      history = history,
+                                      max_length = max_length,
+                                      do_sample = do_sample,
+                                      top_p = top_p, top_k = top_k,
+                                      temperature = temperature,
+                                      repeat_penalty = repeat_penalty,
+                                      one_by_one = True):
+            ret += i;
+        return ret;
+
+    def stream_response(self,
+                        query: str,
+                        history: List[Tuple[str, str]] = None,
+                        max_length: int = 8192, do_sample = True, top_p = 0.8, top_k = 1, temperature = 1.0, repeat_penalty = 1.0,
+                        one_by_one = True):
+        prompt = query if self.direct_query else self.get_prompt(query, history);
+        handle = fastllm_lib.launch_response_str_llm_model(self.model, prompt.encode(),
+                                                           ctypes.c_int(max_length), ctypes.c_bool(do_sample), ctypes.c_float(top_p), ctypes.c_int(top_k),
+                                                           ctypes.c_float(temperature), ctypes.c_float(repeat_penalty), ctypes.c_bool(False));
+        res = "";
+        ret = b'';
+        fail_cnt = 0;
+        while True:
+            ret += fastllm_lib.fetch_response_str_llm_model(self.model, handle);
+            cur = "";
+            try:
+                cur = ret.decode();
+                ret = b'';
+            except:
+                fail_cnt += 1;
+                if (fail_cnt == 20):
+                    break;
+                else:
+                    continue;
+            fail_cnt = 0;
+            if (cur == "<flmeos>"):
+                break;
+            if one_by_one:
+                yield cur;
+            else:
+                res += cur;
+                yield res;
+
+    def chat(self, tokenizer, query: str, history: List[Tuple[str, str]] = None, max_length: int = 8192,
+             do_sample = True, top_p = 0.8, top_k = 1, temperature = 1.0, repeat_penalty = 1.0, **kwargs):
+        if (not(history)):
+            history = [];
+        prompt = query if self.direct_query else self.get_prompt(query, history);
+        input = tokenizer.encode(prompt);
+        handle = fastllm_lib.launch_response_llm_model(self.model, len(input), (ctypes.c_int * len(input))(*input),
+                                                       max_length, do_sample, top_p, top_k, temperature, repeat_penalty,
+                                                       False);
+
+        result = [];
+        while True:
+            cur = fastllm_lib.fetch_response_llm_model(self.model, handle);
+            if (cur == -1):
+                break;
+            result.append(cur);
+        response = tokenizer.decode(result);
+        history = history + [(query, response)];
+        return response, history;
+
+    def stream_chat(self, tokenizer, query: str, history: List[Tuple[str, str]] = None, past_key_values = None,
+                    max_length: int = 8192, do_sample = True, top_p = 0.8, top_k = 1, temperature = 1.0, repeat_penalty = 1.0,
+                    return_past_key_values = False, **kwargs) -> str:
+        if (not(history)):
+            history = [];
+        prompt = query if self.direct_query else self.get_prompt(query, history);
+        input = tokenizer.encode(prompt);
+        handle = fastllm_lib.launch_response_llm_model(self.model, len(input), (ctypes.c_int * len(input))(*input),
+                                                       max_length, do_sample, top_p, top_k, temperature, repeat_penalty,
+                                                       False);
+        tokens = [];
+        while True:
+            cur = fastllm_lib.fetch_response_llm_model(self.model, handle);
+            if (cur == -1):
+                break;
+            tokens.append(cur);
+            response = tokenizer.decode(tokens);
+            new_history = history + [(query, response)];
+            if return_past_key_values:
+                yield response, new_history, None;
+            else:
+                yield response, new_history;

package/fastllm_pytools/torch2flm.py

+import struct
+import numpy as np
+import torch
+
+def writeString(fo, s):
+    fo.write(struct.pack('i', len(s)))
+    fo.write(s.encode())
+
+def writeKeyValue(fo, key, value):
+    writeString(fo, key)
+    writeString(fo, value)
+
+fastllm_data_type_dict = {
+    "int4": 8,
+    "int8": 3,
+    "float16": 7,
+    "float32": 0,
+}
+fastllm_weight_type_dict = {
+    "linear": 1,
+    "embedding": 2
+}
+
+v = np.random.randint(-127, 127, [10, 20]);
+temp = v;
+c_max = np.expand_dims(np.abs(v).max(axis = -1), -1)
+c_scale = c_max / 127.0
+v = (v / c_scale + 128.5).clip(1, 255).astype(np.uint8)
+
+def write_int8(fo, v):
+    c_max = np.expand_dims(np.abs(v).max(axis = -1), -1).clip(0.1, 1e100)
+    c_scale = c_max / 127.0
+    v = (v / c_scale + 128.5).clip(1, 255).astype(np.uint8)
+    fo.write(struct.pack('i', 3))
+    fo.write(struct.pack('i', 0))
+    for i in range(c_max.shape[0]):
+        fo.write(struct.pack('f', -c_max[i][0]));
+        fo.write(struct.pack('f', c_max[i][0]));
+    fo.write(v.data)
+
+def write_int4(fo, v):
+    c_min = np.expand_dims(-np.abs(v).max(axis = -1), -1)
+    c_max = np.expand_dims(np.abs(v).max(axis = -1), -1)
+    c_scale = c_max / 7.0
+    c_min = c_scale * -8.0
+    v = (v - c_min) / c_scale
+    v = (v + 0.5).astype(np.int8).clip(0, 15).astype(np.uint8)
+    v = v[:, 0::2] * 16 + v[:, 1::2]
+    fo.write(struct.pack('i', 8))
+    fo.write(struct.pack('i', 0))
+    for i in range(c_min.shape[0]):
+        fo.write(struct.pack('f', c_min[i][0]));
+        fo.write(struct.pack('f', c_max[i][0]));
+    fo.write(v.data)
+
+def tofile(exportPath,
+           model,
+           tokenizer = None,
+           pre_prompt = None,
+           user_role = None,
+           bot_role = None,
+           history_sep = None,
+           dtype = "float16"):
+    if (dtype not in fastllm_data_type_dict):
+        print("dtype should in ", list(fastllm_data_type_dict.keys()))
+        exit(0)
+
+    dict = model.state_dict()
+    fo = open(exportPath, "wb")
+
+    # 0. version id
+    fo.write(struct.pack('i', 2))
+
+    # 0.1 model info
+    modelInfo = model.config.__dict__
+    if model.generation_config is not None:
+        modelInfo.update(model.generation_config.__dict__)
+    if ("model_type" not in modelInfo):
+        print("unknown model_type.")
+        exit(0)
+
+    if (pre_prompt):
+        modelInfo["pre_prompt"] = pre_prompt
+    if (user_role):
+        modelInfo["user_role"] = user_role
+    if (bot_role):
+        modelInfo["bot_role"] = bot_role
+    if (history_sep):
+        modelInfo["history_sep"] = history_sep
+    if (modelInfo["model_type"] == "baichuan" and hasattr(model, "model") and hasattr(model.model, "get_alibi_mask")):
+        # Baichuan 2代
+        modelInfo["use_alibi"] = "1"
+        modelInfo["pre_prompt"] = ""
+        modelInfo["user_role"] = ("<FLM_FIX_TOKEN_" + str(model.generation_config.user_token_id) + "> ") if hasattr(model.generation_config, "user_token_id") else "";
+        modelInfo["bot_role"] = ("<FLM_FIX_TOKEN_" + str(model.generation_config.assistant_token_id) + ">") if hasattr(model.generation_config, "assistant_token_id") else "";
+        modelInfo["history_sep"] = ""
+    if modelInfo["model_type"] == "qwen":
+        modelInfo["im_end_id"] = tokenizer.im_end_id
+        modelInfo["im_start_id"] = tokenizer.im_start_id
+
+    modelInfo["tokenizer_use_score"] = "1" # 分词带分数
+
+    fo.write(struct.pack('i', len(modelInfo)))
+    for it in modelInfo.keys():
+        writeKeyValue(fo, str(it), str(modelInfo[it]))
+
+    # 1. vocab
+    if (tokenizer):
+        if (hasattr(tokenizer, "tokenizer")):
+            if (modelInfo['model_type'] == "qwen"):
+                pass
+            else:
+                tokenizer = tokenizer.tokenizer
+        if (hasattr(tokenizer, "sp_model")):
+            piece_size = tokenizer.sp_model.piece_size()
+            fo.write(struct.pack('i', piece_size))
+            for i in range(piece_size):
+                s = tokenizer.sp_model.id_to_piece(i).encode()
+                fo.write(struct.pack('i', len(s)))
+                for c in s:
+                    fo.write(struct.pack('i', c))
+                fo.write(struct.pack('i', i))
+                fo.write(struct.pack('f', float(tokenizer.sp_model.get_score(i))))
+        else:
+            vocab = tokenizer.get_vocab()
+            fo.write(struct.pack('i', len(vocab)))
+            for v in vocab.keys():
+                if (modelInfo['model_type'] == "qwen"):
+                    s = v
+                else:
+                    s = v.decode()
+                if (modelInfo["model_type"] == "moss"):
+                    s = [(ord(c) if c not in tokenizer.byte_decoder else tokenizer.byte_decoder[c]) for c in v]
+                fo.write(struct.pack('i', len(s)))
+                for c in s:
+                    fo.write(struct.pack('i', c))
+                fo.write(struct.pack('i', vocab[v]))
+                fo.write(struct.pack('f', 1.0))
+    else:
+        fo.write(struct.pack('i', 0))
+
+    weight_type_dict = {}
+    module_dict = {}
+    for key, m in model.named_modules():
+        if (isinstance(m, torch.nn.Linear)):
+            weight_type_dict[key + ".weight"] = "linear"
+            module_dict[key + ".weight"] = m
+        if (isinstance(m, torch.nn.Embedding)):
+            weight_type_dict[key] = "embedding"
+
+    # 2. weight
+    fo.write(struct.pack('i', len(dict)))
+    tot = 0
+    for key in dict:
+        ori_data_type = 0
+        ori_np_data_type = np.float32
+        cur_weight_type = 0
+        if (key in weight_type_dict and weight_type_dict[key] in fastllm_weight_type_dict):
+            cur_weight_type = fastllm_weight_type_dict[weight_type_dict[key]]
+        to_data_type = 0
+        if (cur_weight_type == 1):
+            to_data_type = fastllm_data_type_dict[dtype]
+            if (to_data_type == 7):
+                ori_data_type = 7
+                ori_np_data_type = np.float16
+
+        cur = dict[key].numpy().astype(ori_np_data_type)
+        fo.write(struct.pack('i', len(key)))
+        fo.write(key.encode())
+        fo.write(struct.pack('i', len(cur.shape)))
+        for i in cur.shape:
+            fo.write(struct.pack('i', i))
+        if (to_data_type == 3):
+            write_int8(fo, cur)
+        elif (to_data_type == 8):
+            write_int4(fo, cur)
+        else:
+            fo.write(struct.pack('i', to_data_type))
+            fo.write(cur.data)
+        tot += 1
+        print("output (", tot, "/", len(dict), end = " )\r")
+    print("\nfinish.")
+    fo.close()
\ No newline at end of file

package/setup.py

+from setuptools import setup, find_packages
+
+setup (
+    name = "fastllm_pytools",
+    version = "0.0.1",
+    author = "huangyuyang",
+    author_email = "ztxz16@foxmail.com",
+    description = "Fastllm pytools",
+    url = "https://github.com/ztxz16/fastllm",
+    packages = ['fastllm_pytools'],
+
+    package_data = {
+        '': ['*.dll', '*.so']
+    }
+)

web_demo.py

+import streamlit as st
+from streamlit_chat import message
+from fastllm_pytools import llm
+import sys
+
+st.set_page_config(
+    page_title="fastllm web demo",
+    page_icon=":robot:"
+)
+
+@st.cache_resource
+def get_model():
+    model = llm.model(sys.argv[1])
+    return model
+
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+for i, (prompt, response) in enumerate(st.session_state.messages):
+    with st.chat_message("user"):
+        st.markdown(prompt)
+    with st.chat_message("assistant"):
+        st.markdown(response)
+
+if prompt := st.chat_input("请开始对话"):
+    model = get_model()
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    with st.chat_message("assistant"):
+        message_placeholder = st.empty()
+        full_response = ""
+        for chunk in model.stream_response(prompt, st.session_state.messages, one_by_one = True):
+            full_response += chunk
+            message_placeholder.markdown(full_response + "▌")
+        message_placeholder.markdown(full_response)
+    st.session_state.messages.append((prompt, full_response))