Hugging Face's logo

Spaces:
sourize
/
DeepTalks
Sleeping

App Files Community
sourize commited on
Commit
55faf97
·
1 Parent(s): 857744a

Commit

Browse files
Files changed (11) hide show
  1. app.py +60 -50
  2. models/phi2-deeptalk-lora/README.md +0 -202
  3. models/phi2-deeptalk-lora/adapter_config.json +0 -36
  4. models/phi2-deeptalk-lora/adapter_model.safetensors +0 -3
  5. models/phi2-deeptalk-lora/added_tokens.json +0 -41
  6. models/phi2-deeptalk-lora/merges.txt +0 -0
  7. models/phi2-deeptalk-lora/special_tokens_map.json +0 -30
  8. models/phi2-deeptalk-lora/tokenizer.json +0 -0
  9. models/phi2-deeptalk-lora/tokenizer_config.json +0 -335
  10. models/phi2-deeptalk-lora/training_args.bin +0 -3
  11. models/phi2-deeptalk-lora/vocab.json +0 -0
app.py CHANGED
@@ -7,36 +7,39 @@ from transformers import (
7
  AutoModelForCausalLM,
8
  BitsAndBytesConfig,
9
  )
10
- from peft import LoraConfig, get_peft_model
11
- from safetensors.torch import load_file as safe_load
12
 
13
  # ── Configuration ──────────────────────────────────────────────────────────
14
- BASE_MODEL = "microsoft/phi-2"
15
- ADAPTER_DIR = os.path.join(os.path.dirname(__file__), "models", "phi2-deeptalk-lora")
16
- CONTEXT_TURNS = 6
17
- MAX_NEW_TOKENS = 32
18
- DEVICE_MAP = "auto"
19
 
20
  SYSTEM = (
21
- "You are a helpful assistant for DeepTalks with base Phi-2 fine-tuned "
22
- "by Sourish for domain support.\n"
23
- "Answer only using the conversation context below.\n"
 
24
  "If you don’t know, say “I don't know.”\n"
25
  )
26
 
27
- # ── Model loader (cached) ──────────────────────────────────────────────────
28
  @st.cache_resource(show_spinner=False)
29
- def load_generator():
30
- # 1) Tokenizer (from official HF cache)
31
  tokenizer = AutoTokenizer.from_pretrained(
32
- BASE_MODEL, trust_remote_code=True, padding_side="left"
 
 
33
  )
34
  if tokenizer.pad_token_id is None:
35
  tokenizer.add_special_tokens({"pad_token": "[PAD]"})
36
 
37
- # 2) Base model (4-bit on GPU, else FP16/FP32)
38
  if torch.cuda.is_available():
39
- bnb = BitsAndBytesConfig(
40
  load_in_4bit=True,
41
  bnb_4bit_quant_type="nf4",
42
  bnb_4bit_compute_dtype="float16",
@@ -45,8 +48,10 @@ def load_generator():
45
  base = AutoModelForCausalLM.from_pretrained(
46
  BASE_MODEL,
47
  trust_remote_code=True,
48
- quantization_config=bnb,
49
- device_map=DEVICE_MAP,
 
 
50
  )
51
  else:
52
  dtype = torch.float16 if torch.cuda.is_available() else torch.float32
@@ -54,76 +59,81 @@ def load_generator():
54
  BASE_MODEL,
55
  trust_remote_code=True,
56
  torch_dtype=dtype,
57
- device_map=DEVICE_MAP,
 
 
58
  )
59
 
60
- # 3) Resize embeddings & wrap LoRA
61
  base.resize_token_embeddings(len(tokenizer))
62
- peft_config = LoraConfig.from_pretrained(ADAPTER_DIR, local_files_only=True)
63
- model = get_peft_model(base, peft_config)
64
 
65
- # 4) Load adapter weights (.safetensors)
66
- adapter_file = os.path.join(ADAPTER_DIR, "adapter_model.safetensors")
67
- state_dict = safe_load(adapter_file)
68
- model.load_state_dict(state_dict, strict=False)
 
 
 
 
 
 
69
  model.eval()
70
 
71
- # 5) Build a **greedy** pipeline for max speed
72
  gen = pipeline(
73
  "text-generation",
74
  model=model,
75
  tokenizer=tokenizer,
76
- device_map=DEVICE_MAP,
77
  max_new_tokens=MAX_NEW_TOKENS,
78
- do_sample=False, # greedy
79
  use_cache=True,
80
  return_full_text=False,
81
  )
82
- return tokenizer, gen
83
 
84
- tokenizer, generator = load_generator()
 
 
 
85
 
86
  # ── Streamlit UI ──────────────────────────────────────────────────────────
87
  st.set_page_config(layout="centered")
88
  st.title("🧠 Memory-Aware Phi-2 Chat")
89
 
90
- # Initialize chat history
91
  if "history" not in st.session_state:
92
- st.session_state.history = [] # list of (role, text)
93
 
94
- # Render past messages
95
  for role, text in st.session_state.history:
96
- st.chat_message("user" if role=="You" else "assistant").write(text)
97
 
98
- # User input at bottom
99
  user_input = st.chat_input("Your message…")
100
  if user_input:
101
- # Show/store user turn
102
  st.chat_message("user").write(user_input)
103
  st.session_state.history.append(("You", user_input))
104
 
105
- # Build context from last N turns
106
  recent = st.session_state.history[-CONTEXT_TURNS*2:]
107
- ctx = "\n".join(
108
- f"{'User' if r=='You' else 'Assistant'}: {t}"
109
- for r,t in recent
110
- )
111
  prompt = f"""{SYSTEM}
112
 
113
  Context:
114
- {ctx}
115
 
116
  User: {user_input}
117
  Assistant:"""
118
 
119
- # Generate reply (spinner)
120
  with st.spinner("Thinking…"):
121
  try:
122
- out = generator(prompt)[0]["generated_text"].strip()
123
  except Exception as e:
124
- out = "I’m sorry, something went wrong."
125
- st.error(f"Error: {e}")
126
 
127
- # Show/store assistant
128
- st.chat_message("assistant").write(out)
129
- st.session_state.history.append(("Bot", out))
 
7
  AutoModelForCausalLM,
8
  BitsAndBytesConfig,
9
  )
10
+ from peft import PeftModel
11
+ import logging
12
 
13
  # ── Configuration ──────────────────────────────────────────────────────────
14
+ BASE_MODEL = "microsoft/phi-2"
15
+ ADAPTER_REPO = "sourize/phi2-memory-lora"
16
+ CONTEXT_TURNS = 6
17
+ MAX_NEW_TOKENS = 32
18
+ OFFLOAD_DIR = "offload"
19
 
20
  SYSTEM = (
21
+ "You are a helpful assistant for DeepTalks with base Phi-2 "
22
+ "fine-tuned by Sourish for domain support.\n"
23
+ "Answer **only** using the conversation context below.\n"
24
+ "Do NOT output any lines beginning with 'User:' or 'Assistant:'.\n"
25
  "If you don’t know, say “I don't know.”\n"
26
  )
27
 
28
+
29
  @st.cache_resource(show_spinner=False)
30
+ def load_pipeline():
31
+ # 1) Tokenizer
32
  tokenizer = AutoTokenizer.from_pretrained(
33
+ BASE_MODEL,
34
+ trust_remote_code=True,
35
+ padding_side="left",
36
  )
37
  if tokenizer.pad_token_id is None:
38
  tokenizer.add_special_tokens({"pad_token": "[PAD]"})
39
 
40
+ # 2) Base model (4-bit quant on GPU, else FP16/FP32)
41
  if torch.cuda.is_available():
42
+ bnb_config = BitsAndBytesConfig(
43
  load_in_4bit=True,
44
  bnb_4bit_quant_type="nf4",
45
  bnb_4bit_compute_dtype="float16",
 
48
  base = AutoModelForCausalLM.from_pretrained(
49
  BASE_MODEL,
50
  trust_remote_code=True,
51
+ quantization_config=bnb_config,
52
+ device_map="auto",
53
+ offload_folder=OFFLOAD_DIR,
54
+ offload_state_dict=True,
55
  )
56
  else:
57
  dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
59
  BASE_MODEL,
60
  trust_remote_code=True,
61
  torch_dtype=dtype,
62
+ device_map="auto",
63
+ offload_folder=OFFLOAD_DIR,
64
+ offload_state_dict=True,
65
  )
66
 
67
+ # 3) Resize embeddings
68
  base.resize_token_embeddings(len(tokenizer))
 
 
69
 
70
+ # 4) Overlay LoRA adapter from Hugging Face Hub
71
+ model = PeftModel.from_pretrained(
72
+ base,
73
+ ADAPTER_REPO,
74
+ trust_remote_code=True,
75
+ device_map="auto",
76
+ torch_dtype="auto",
77
+ offload_folder=OFFLOAD_DIR,
78
+ offload_state_dict=True,
79
+ )
80
  model.eval()
81
 
82
+ # 5) Build generation pipeline (greedy for speed)
83
  gen = pipeline(
84
  "text-generation",
85
  model=model,
86
  tokenizer=tokenizer,
87
+ device_map="auto",
88
  max_new_tokens=MAX_NEW_TOKENS,
89
+ do_sample=False, # greedy decoding
90
  use_cache=True,
91
  return_full_text=False,
92
  )
 
93
 
94
+ logging.info(f"Loaded pipeline with model {BASE_MODEL} + adapter {ADAPTER_REPO}")
95
+ return gen
96
+
97
+ generator = load_pipeline()
98
 
99
  # ── Streamlit UI ──────────────────────────────────────────────────────────
100
  st.set_page_config(layout="centered")
101
  st.title("🧠 Memory-Aware Phi-2 Chat")
102
 
103
+ # initialize chat history
104
  if "history" not in st.session_state:
105
+ st.session_state.history = [] # List of (role, text)
106
 
107
+ # render chat history
108
  for role, text in st.session_state.history:
109
+ st.chat_message("user" if role == "You" else "assistant").write(text)
110
 
111
+ # user input
112
  user_input = st.chat_input("Your message…")
113
  if user_input:
114
+ # show & store user turn
115
  st.chat_message("user").write(user_input)
116
  st.session_state.history.append(("You", user_input))
117
 
118
+ # build context from last CONTEXT_TURNS
119
  recent = st.session_state.history[-CONTEXT_TURNS*2:]
120
+ context = "\n".join(t for _, t in recent)
 
 
 
121
  prompt = f"""{SYSTEM}
122
 
123
  Context:
124
+ {context}
125
 
126
  User: {user_input}
127
  Assistant:"""
128
 
129
+ # generate reply
130
  with st.spinner("Thinking…"):
131
  try:
132
+ output = generator(prompt)[0]["generated_text"].strip()
133
  except Exception as e:
134
+ output = "I’m sorry, something went wrong."
135
+ st.error(f"Generation error: {e}")
136
 
137
+ # show & store assistant turn
138
+ st.chat_message("assistant").write(output)
139
+ st.session_state.history.append(("Bot", output))
models/phi2-deeptalk-lora/README.md DELETED
@@ -1,202 +0,0 @@
1
- ---
2
- base_model: microsoft/phi-2
3
- library_name: peft
4
- ---
5
-
6
- # Model Card for Model ID
7
-
8
- <!-- Provide a quick summary of what the model is/does. -->
9
-
10
-
11
-
12
- ## Model Details
13
-
14
- ### Model Description
15
-
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
-
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
-
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
-
36
- ## Uses
37
-
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
- ### Direct Use
41
-
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
-
70
- ## How to Get Started with the Model
71
-
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
-
78
- ### Training Data
79
-
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
-
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
-
153
- ## Technical Specifications [optional]
154
-
155
- ### Model Architecture and Objective
156
-
157
- [More Information Needed]
158
-
159
- ### Compute Infrastructure
160
-
161
- [More Information Needed]
162
-
163
- #### Hardware
164
-
165
- [More Information Needed]
166
-
167
- #### Software
168
-
169
- [More Information Needed]
170
-
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
-
175
- **BibTeX:**
176
-
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
184
-
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
-
187
- [More Information Needed]
188
-
189
- ## More Information [optional]
190
-
191
- [More Information Needed]
192
-
193
- ## Model Card Authors [optional]
194
-
195
- [More Information Needed]
196
-
197
- ## Model Card Contact
198
-
199
- [More Information Needed]
200
- ### Framework versions
201
-
202
- - PEFT 0.14.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/phi2-deeptalk-lora/adapter_config.json DELETED
@@ -1,36 +0,0 @@
1
- {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "microsoft/phi-2",
5
- "bias": "none",
6
- "eva_config": null,
7
- "exclude_modules": null,
8
- "fan_in_fan_out": false,
9
- "inference_mode": true,
10
- "init_lora_weights": true,
11
- "layer_replication": null,
12
- "layers_pattern": null,
13
- "layers_to_transform": null,
14
- "loftq_config": {},
15
- "lora_alpha": 32,
16
- "lora_bias": false,
17
- "lora_dropout": 0.05,
18
- "megatron_config": null,
19
- "megatron_core": "megatron.core",
20
- "modules_to_save": null,
21
- "peft_type": "LORA",
22
- "r": 4,
23
- "rank_pattern": {},
24
- "revision": null,
25
- "target_modules": [
26
- "dense",
27
- "k_proj",
28
- "fc2",
29
- "fc1",
30
- "v_proj",
31
- "q_proj"
32
- ],
33
- "task_type": "CAUSAL_LM",
34
- "use_dora": false,
35
- "use_rslora": false
36
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/phi2-deeptalk-lora/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7aa408089fb13fb4630b32e35cf2ccaec31e99aa519c3c0ec24ce465179ac34b
3
- size 538774784
 
 
 
 
models/phi2-deeptalk-lora/added_tokens.json DELETED
@@ -1,41 +0,0 @@
1
- {
2
- "\t\t": 50294,
3
- "\t\t\t": 50293,
4
- "\t\t\t\t": 50292,
5
- "\t\t\t\t\t": 50291,
6
- "\t\t\t\t\t\t": 50290,
7
- "\t\t\t\t\t\t\t": 50289,
8
- "\t\t\t\t\t\t\t\t": 50288,
9
- "\t\t\t\t\t\t\t\t\t": 50287,
10
- " ": 50286,
11
- " ": 50285,
12
- " ": 50284,
13
- " ": 50283,
14
- " ": 50282,
15
- " ": 50281,
16
- " ": 50280,
17
- " ": 50279,
18
- " ": 50278,
19
- " ": 50277,
20
- " ": 50276,
21
- " ": 50275,
22
- " ": 50274,
23
- " ": 50273,
24
- " ": 50272,
25
- " ": 50271,
26
- " ": 50270,
27
- " ": 50269,
28
- " ": 50268,
29
- " ": 50267,
30
- " ": 50266,
31
- " ": 50265,
32
- " ": 50264,
33
- " ": 50263,
34
- " ": 50262,
35
- " ": 50261,
36
- " ": 50260,
37
- " ": 50259,
38
- " ": 50258,
39
- " ": 50257,
40
- "[PAD]": 50295
41
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/phi2-deeptalk-lora/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
models/phi2-deeptalk-lora/special_tokens_map.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<|endoftext|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|endoftext|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "[PAD]",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<|endoftext|>",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/phi2-deeptalk-lora/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
models/phi2-deeptalk-lora/tokenizer_config.json DELETED
@@ -1,335 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "50256": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "50257": {
13
- "content": " ",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": false
19
- },
20
- "50258": {
21
- "content": " ",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": false
27
- },
28
- "50259": {
29
- "content": " ",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": false
35
- },
36
- "50260": {
37
- "content": " ",
38
- "lstrip": false,
39
- "normalized": true,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": false
43
- },
44
- "50261": {
45
- "content": " ",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": false
51
- },
52
- "50262": {
53
- "content": " ",
54
- "lstrip": false,
55
- "normalized": true,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": false
59
- },
60
- "50263": {
61
- "content": " ",
62
- "lstrip": false,
63
- "normalized": true,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": false
67
- },
68
- "50264": {
69
- "content": " ",
70
- "lstrip": false,
71
- "normalized": true,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": false
75
- },
76
- "50265": {
77
- "content": " ",
78
- "lstrip": false,
79
- "normalized": true,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": false
83
- },
84
- "50266": {
85
- "content": " ",
86
- "lstrip": false,
87
- "normalized": true,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": false
91
- },
92
- "50267": {
93
- "content": " ",
94
- "lstrip": false,
95
- "normalized": true,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": false
99
- },
100
- "50268": {
101
- "content": " ",
102
- "lstrip": false,
103
- "normalized": true,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": false
107
- },
108
- "50269": {
109
- "content": " ",
110
- "lstrip": false,
111
- "normalized": true,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": false
115
- },
116
- "50270": {
117
- "content": " ",
118
- "lstrip": false,
119
- "normalized": true,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "50271": {
125
- "content": " ",
126
- "lstrip": false,
127
- "normalized": true,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "50272": {
133
- "content": " ",
134
- "lstrip": false,
135
- "normalized": true,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "50273": {
141
- "content": " ",
142
- "lstrip": false,
143
- "normalized": true,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "50274": {
149
- "content": " ",
150
- "lstrip": false,
151
- "normalized": true,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "50275": {
157
- "content": " ",
158
- "lstrip": false,
159
- "normalized": true,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "50276": {
165
- "content": " ",
166
- "lstrip": false,
167
- "normalized": true,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "50277": {
173
- "content": " ",
174
- "lstrip": false,
175
- "normalized": true,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "50278": {
181
- "content": " ",
182
- "lstrip": false,
183
- "normalized": true,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "50279": {
189
- "content": " ",
190
- "lstrip": false,
191
- "normalized": true,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "50280": {
197
- "content": " ",
198
- "lstrip": false,
199
- "normalized": true,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "50281": {
205
- "content": " ",
206
- "lstrip": false,
207
- "normalized": true,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "50282": {
213
- "content": " ",
214
- "lstrip": false,
215
- "normalized": true,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": false
219
- },
220
- "50283": {
221
- "content": " ",
222
- "lstrip": false,
223
- "normalized": true,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": false
227
- },
228
- "50284": {
229
- "content": " ",
230
- "lstrip": false,
231
- "normalized": true,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": false
235
- },
236
- "50285": {
237
- "content": " ",
238
- "lstrip": false,
239
- "normalized": true,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": false
243
- },
244
- "50286": {
245
- "content": " ",
246
- "lstrip": false,
247
- "normalized": true,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": false
251
- },
252
- "50287": {
253
- "content": "\t\t\t\t\t\t\t\t\t",
254
- "lstrip": false,
255
- "normalized": true,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": false
259
- },
260
- "50288": {
261
- "content": "\t\t\t\t\t\t\t\t",
262
- "lstrip": false,
263
- "normalized": true,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": false
267
- },
268
- "50289": {
269
- "content": "\t\t\t\t\t\t\t",
270
- "lstrip": false,
271
- "normalized": true,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": false
275
- },
276
- "50290": {
277
- "content": "\t\t\t\t\t\t",
278
- "lstrip": false,
279
- "normalized": true,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": false
283
- },
284
- "50291": {
285
- "content": "\t\t\t\t\t",
286
- "lstrip": false,
287
- "normalized": true,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": false
291
- },
292
- "50292": {
293
- "content": "\t\t\t\t",
294
- "lstrip": false,
295
- "normalized": true,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": false
299
- },
300
- "50293": {
301
- "content": "\t\t\t",
302
- "lstrip": false,
303
- "normalized": true,
304
- "rstrip": false,
305
- "single_word": false,
306
- "special": false
307
- },
308
- "50294": {
309
- "content": "\t\t",
310
- "lstrip": false,
311
- "normalized": true,
312
- "rstrip": false,
313
- "single_word": false,
314
- "special": false
315
- },
316
- "50295": {
317
- "content": "[PAD]",
318
- "lstrip": false,
319
- "normalized": false,
320
- "rstrip": false,
321
- "single_word": false,
322
- "special": true
323
- }
324
- },
325
- "bos_token": "<|endoftext|>",
326
- "clean_up_tokenization_spaces": true,
327
- "eos_token": "<|endoftext|>",
328
- "extra_special_tokens": {},
329
- "model_max_length": 2048,
330
- "pad_token": "[PAD]",
331
- "padding_side": "left",
332
- "return_token_type_ids": false,
333
- "tokenizer_class": "CodeGenTokenizer",
334
- "unk_token": "<|endoftext|>"
335
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/phi2-deeptalk-lora/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fa1d3e24dbecb64fba08308dbfbc755a81ffcfafe47980e4bbfb871f79b0ebd
3
- size 5304
 
 
 
 
models/phi2-deeptalk-lora/vocab.json DELETED
The diff for this file is too large to render. See raw diff