the last ones

.gitattributes

@@ -45,3 +45,5 @@ vikhr-7b-instruct_0.2.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
 vikhr-7b-instruct_0.2.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
 vikhr-7b-instruct_0.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 vikhr-7b-instruct_0.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+vikhr-7b-instruct_0.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+vikhr-7b-instruct_0.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,88 @@
+Quantized version of [Vikhr-7B-instruct_0.2](https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_0.2) using llama.cpp.
+
+See [Files and Versions](https://huggingface.co/pirbis/Vikhr-7B-instruct_0.2-GGUF/tree/main) for quantized GGUF files.
+
+model_config.json contains an example of settings to use with LMStudio.
+
+---
+language:
+- ru
+- en
+datasets:
+- zjkarina/Vikhr_instruct
+---
+```python
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
+import torch
+
+MODEL_NAME = "Vikhrmodels/Vikhr-7B-instruct_0.2"
+DEFAULT_MESSAGE_TEMPLATE = "<s>{role}\n{content}</s>\n"
+DEFAULT_SYSTEM_PROMPT = "Ты — Вихрь, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им."
+
+class Conversation:
+    def __init__(
+        self,
+        message_template=DEFAULT_MESSAGE_TEMPLATE,
+        system_prompt=DEFAULT_SYSTEM_PROMPT,
+    ):
+        self.message_template = message_template
+        self.messages = [{
+            "role": "system",
+            "content": system_prompt
+        }]
+
+    def add_user_message(self, message):
+        self.messages.append({
+            "role": "user",
+            "content": message
+        })
+
+    def get_prompt(self, tokenizer):
+        final_text = ""
+        for message in self.messages:
+            message_text = self.message_template.format(**message)
+            final_text += message_text
+        final_text += 'bot'
+        return final_text.strip()
+
+
+def generate(model, tokenizer, prompt, generation_config):
+    data = tokenizer(prompt, return_tensors="pt")
+    data = {k: v.to(model.device) for k, v in data.items()}
+    output_ids = model.generate(
+        **data,
+        generation_config=generation_config
+    )[0]
+    output_ids = output_ids[len(data["input_ids"][0]):]
+    output = tokenizer.decode(output_ids, skip_special_tokens=True)
+    return output.strip()
+    
+#config = PeftConfig.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(
+    config.base_model_name_or_path,
+    load_in_8bit=True,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+#model = PeftModel.from_pretrained(    model,   MODEL_NAME,   torch_dtype=torch.float16)
+model.eval()
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=False)
+generation_config = GenerationConfig.from_pretrained(MODEL_NAME)
+print(generation_config)
+
+inputs = ["Как тебя зовут?", "Кто такой Колмогоров?"]
+
+for inp in inputs:
+    conversation = Conversation()
+    conversation.add_user_message(inp)
+    prompt = conversation.get_prompt(tokenizer)
+
+    output = generate(model, tokenizer, prompt, generation_config)
+    print(inp)
+    print(output)
+    print('\n')
+```
+
+[wandb](https://wandb.ai/karina_romanova/vikhr/runs/up2hw5eh?workspace=user-karina_romanova)

model_config.json

@@ -0,0 +1,51 @@
+{
+  "name": "Config for Chat ID 1708268236270",
+  "load_params": {
+    "n_ctx": 2048,
+    "n_batch": 512,
+    "rope_freq_base": 0,
+    "rope_freq_scale": 0,
+    "n_gpu_layers": 24,
+    "use_mlock": true,
+    "main_gpu": 0,
+    "tensor_split": [
+      0
+    ],
+    "seed": -1,
+    "f16_kv": true,
+    "use_mmap": true,
+    "no_kv_offload": false,
+    "num_experts_used": 0
+  },
+  "inference_params": {
+    "n_threads": 12,
+    "n_predict": -1,
+    "top_k": 40,
+    "min_p": 0.05,
+    "top_p": 0.95,
+    "temp": 0.8,
+    "repeat_penalty": 1.1,
+    "input_prefix": "<s>user\n",
+    "input_suffix": "</s>\nbot\n",
+    "antiprompt": [
+      "</s>"
+    ],
+    "pre_prompt": "Ты — Вихрь, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.",
+    "pre_prompt_suffix": "</s>\n",
+    "pre_prompt_prefix": "<s>system\n",
+    "seed": -1,
+    "tfs_z": 1,
+    "typical_p": 1,
+    "repeat_last_n": 64,
+    "frequency_penalty": 0,
+    "presence_penalty": 0,
+    "n_keep": 0,
+    "logit_bias": {},
+    "mirostat": 0,
+    "mirostat_tau": 5,
+    "mirostat_eta": 0.1,
+    "memory_f16": true,
+    "multiline_input": false,
+    "penalize_nl": true
+  }
+}

vikhr-7b-instruct_0.2.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e14bb39b39422f89214ed12c29661d9f4dbe37fc3a043157f070f0cecf907b0
+size 5719879552

vikhr-7b-instruct_0.2.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fba35dda2e1717f5e96d4768ad31d0d99845e94e8f5c2c48d227f0feea4b61f
+size 7407835008