streamft 0.4.1__tar.gz → 0.5.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {streamft-0.4.1 → streamft-0.5.0}/PKG-INFO +29 -1
- {streamft-0.4.1 → streamft-0.5.0}/README.md +28 -0
- {streamft-0.4.1 → streamft-0.5.0}/pyproject.toml +1 -1
- {streamft-0.4.1 → streamft-0.5.0}/streamft/__main__.py +6 -0
- streamft-0.5.0/streamft/serve.py +146 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft.egg-info/PKG-INFO +29 -1
- {streamft-0.4.1 → streamft-0.5.0}/streamft.egg-info/SOURCES.txt +1 -0
- {streamft-0.4.1 → streamft-0.5.0}/LICENSE +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/setup.cfg +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/__init__.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/autotune.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/cli.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/data.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/disk_quant_store.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/doctor.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/easy.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/evals.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/fit.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/lora.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/merge.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/metrics.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/stream_quant_lora.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft/stream_train.py +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft.egg-info/dependency_links.txt +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft.egg-info/entry_points.txt +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft.egg-info/requires.txt +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/streamft.egg-info/top_level.txt +0 -0
- {streamft-0.4.1 → streamft-0.5.0}/tests/test_streamft_smoke.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: streamft
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.5.0
|
|
4
4
|
Summary: Fine-tune models that do not fit: stream NF4 weights from disk, one transformer block at a time.
|
|
5
5
|
Author-email: Gokhan Cava <byjameson@users.noreply.github.com>
|
|
6
6
|
License: Apache-2.0
|
|
@@ -163,6 +163,34 @@ the same passage costs **1.13 tokens/word in English, 1.74 in German and 2.39 in
|
|
|
163
163
|
(LLaDA/Mercury: 800?1,500 tok/s at batch 1, but the same memory footprint) do not change
|
|
164
164
|
this project's bottleneck are in [`docs/TOKENIZERS.md`](docs/TOKENIZERS.md).
|
|
165
165
|
|
|
166
|
+
### Run it in a browser (no server)
|
|
167
|
+
|
|
168
|
+
```bash
|
|
169
|
+
streamft merge --model Qwen/Qwen2.5-0.5B --adapter checkpoints/cpu_cookbook --out merged/q05
|
|
170
|
+
powershell -ExecutionPolicy Bypass -File scripts/export_gguf.ps1 # -> q05-q4_k_m.gguf
|
|
171
|
+
python scripts/serve_static.py --port 8765
|
|
172
|
+
# open http://127.0.0.1:8765/wasm/index.html?model=../q05-q4_k_m.gguf
|
|
173
|
+
```
|
|
174
|
+
|
|
175
|
+
Measured on the reference laptop, 0.5B Q4_K_M (379 MB): **1.3 tok/s** with the plain
|
|
176
|
+
`http.server`, **6.0 tok/s** behind `scripts/serve_static.py` ? the COOP/COEP headers are
|
|
177
|
+
what let wllama use 12 threads instead of one. Details and limits in
|
|
178
|
+
[`wasm/README.md`](wasm/README.md).
|
|
179
|
+
|
|
180
|
+
### Share one machine on the LAN
|
|
181
|
+
|
|
182
|
+
One PC with the model can serve everyone on the same network:
|
|
183
|
+
|
|
184
|
+
```bash
|
|
185
|
+
streamft serve --model merged/q05_cpu --port 8000
|
|
186
|
+
# others open http://<that-machine-ip>:8000
|
|
187
|
+
```
|
|
188
|
+
|
|
189
|
+
It ships a small chat page and an OpenAI-compatible `POST /v1/chat/completions`, so existing
|
|
190
|
+
tools can point at it. This is **one machine computing, the rest as clients** ? not
|
|
191
|
+
peer-to-peer sharding and not volunteer compute. Tested end to end: `/health` and a
|
|
192
|
+
16-token completion (1.9 s on the reference GPU).
|
|
193
|
+
|
|
166
194
|
### Measured on
|
|
167
195
|
|
|
168
196
|
Every speed number here comes from **one machine**: RTX 3050 Laptop 6 GB, Windows 11,
|
|
@@ -133,6 +133,34 @@ the same passage costs **1.13 tokens/word in English, 1.74 in German and 2.39 in
|
|
|
133
133
|
(LLaDA/Mercury: 800?1,500 tok/s at batch 1, but the same memory footprint) do not change
|
|
134
134
|
this project's bottleneck are in [`docs/TOKENIZERS.md`](docs/TOKENIZERS.md).
|
|
135
135
|
|
|
136
|
+
### Run it in a browser (no server)
|
|
137
|
+
|
|
138
|
+
```bash
|
|
139
|
+
streamft merge --model Qwen/Qwen2.5-0.5B --adapter checkpoints/cpu_cookbook --out merged/q05
|
|
140
|
+
powershell -ExecutionPolicy Bypass -File scripts/export_gguf.ps1 # -> q05-q4_k_m.gguf
|
|
141
|
+
python scripts/serve_static.py --port 8765
|
|
142
|
+
# open http://127.0.0.1:8765/wasm/index.html?model=../q05-q4_k_m.gguf
|
|
143
|
+
```
|
|
144
|
+
|
|
145
|
+
Measured on the reference laptop, 0.5B Q4_K_M (379 MB): **1.3 tok/s** with the plain
|
|
146
|
+
`http.server`, **6.0 tok/s** behind `scripts/serve_static.py` ? the COOP/COEP headers are
|
|
147
|
+
what let wllama use 12 threads instead of one. Details and limits in
|
|
148
|
+
[`wasm/README.md`](wasm/README.md).
|
|
149
|
+
|
|
150
|
+
### Share one machine on the LAN
|
|
151
|
+
|
|
152
|
+
One PC with the model can serve everyone on the same network:
|
|
153
|
+
|
|
154
|
+
```bash
|
|
155
|
+
streamft serve --model merged/q05_cpu --port 8000
|
|
156
|
+
# others open http://<that-machine-ip>:8000
|
|
157
|
+
```
|
|
158
|
+
|
|
159
|
+
It ships a small chat page and an OpenAI-compatible `POST /v1/chat/completions`, so existing
|
|
160
|
+
tools can point at it. This is **one machine computing, the rest as clients** ? not
|
|
161
|
+
peer-to-peer sharding and not volunteer compute. Tested end to end: `/health` and a
|
|
162
|
+
16-token completion (1.9 s on the reference GPU).
|
|
163
|
+
|
|
136
164
|
### Measured on
|
|
137
165
|
|
|
138
166
|
Every speed number here comes from **one machine**: RTX 3050 Laptop 6 GB, Windows 11,
|
|
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "streamft"
|
|
7
|
-
version = "0.
|
|
7
|
+
version = "0.5.0"
|
|
8
8
|
description = "Fine-tune models that do not fit: stream NF4 weights from disk, one transformer block at a time."
|
|
9
9
|
readme = "README.md"
|
|
10
10
|
requires-python = ">=3.10"
|
|
@@ -8,6 +8,7 @@
|
|
|
8
8
|
streamft synth generate training pairs locally with a small model
|
|
9
9
|
streamft eval run a small local prompt set (repetition/refusal/keywords)
|
|
10
10
|
streamft merge fold a saved adapter into the base model (for serving / GGUF)
|
|
11
|
+
streamft serve host a merged model on the LAN (chat page + /v1/chat/completions)
|
|
11
12
|
streamft doctor environment report (torch, CUDA, bitsandbytes, VRAM)
|
|
12
13
|
"""
|
|
13
14
|
from __future__ import annotations
|
|
@@ -24,6 +25,7 @@ USAGE = """streamft - fine-tune models that do not fit
|
|
|
24
25
|
streamft synth --model <small-model> --n 50 --out data/synth.jsonl
|
|
25
26
|
streamft eval --model <model> [--prompts mine.jsonl]
|
|
26
27
|
streamft merge --model <base> --adapter <dir> --out merged/<name>
|
|
28
|
+
streamft serve --model merged/<name> --port 8000
|
|
27
29
|
streamft doctor
|
|
28
30
|
|
|
29
31
|
Docs: https://github.com/byjameson/stream-finetune
|
|
@@ -47,6 +49,10 @@ def main() -> int:
|
|
|
47
49
|
from streamft.easy import cpu_main
|
|
48
50
|
return cpu_main(rest)
|
|
49
51
|
|
|
52
|
+
if cmd == "serve":
|
|
53
|
+
from streamft.serve import main as serve_main
|
|
54
|
+
return serve_main(rest)
|
|
55
|
+
|
|
50
56
|
if cmd == "merge":
|
|
51
57
|
from streamft.merge import main as merge_main
|
|
52
58
|
return merge_main(rest)
|
|
@@ -0,0 +1,146 @@
|
|
|
1
|
+
"""`streamft serve` — one machine hosts, others on the LAN use it.
|
|
2
|
+
|
|
3
|
+
streamft serve --model merged/q05_cpu --port 8000
|
|
4
|
+
|
|
5
|
+
Open http://<this-machine-ip>:8000 from any phone/laptop on the same network. There is a
|
|
6
|
+
small chat page and an OpenAI-compatible `POST /v1/chat/completions` endpoint, so existing
|
|
7
|
+
tools can point at it too.
|
|
8
|
+
|
|
9
|
+
This is the practical version of "share the setup": one PC with the model, everyone else
|
|
10
|
+
uses a browser. It is *not* a peer-to-peer network — no sharding, no volunteer compute.
|
|
11
|
+
|
|
12
|
+
Adapters: pass `--adapter checkpoints/my_adapter` to serve an unmerged adapter on top of
|
|
13
|
+
the base.
|
|
14
|
+
"""
|
|
15
|
+
from __future__ import annotations
|
|
16
|
+
|
|
17
|
+
import argparse
|
|
18
|
+
import json
|
|
19
|
+
import threading
|
|
20
|
+
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
|
21
|
+
|
|
22
|
+
import torch
|
|
23
|
+
|
|
24
|
+
_lock = threading.Lock()
|
|
25
|
+
_state: dict = {}
|
|
26
|
+
|
|
27
|
+
PAGE = """<!doctype html><meta charset="utf-8"><title>streamft serve</title>
|
|
28
|
+
<style>body{font:16px/1.5 system-ui;max-width:760px;margin:40px auto;padding:0 20px}
|
|
29
|
+
textarea{width:100%;min-height:90px}#o{white-space:pre-wrap;background:#f6f6f6;padding:12px;border-radius:8px}
|
|
30
|
+
</style>
|
|
31
|
+
<h2>streamft serve</h2><p id="m" style="color:#666"></p>
|
|
32
|
+
<textarea id="p">Write one sentence about small GPUs.</textarea>
|
|
33
|
+
<button id="g">Send</button><pre id="o"></pre>
|
|
34
|
+
<script>
|
|
35
|
+
fetch('/health').then(r=>r.json()).then(j=>document.getElementById('m').textContent='model: '+(j.model||'?'));
|
|
36
|
+
document.getElementById('g').onclick=async()=>{
|
|
37
|
+
const o=document.getElementById('o'); o.textContent='…';
|
|
38
|
+
const r=await fetch('/v1/chat/completions',{method:'POST',headers:{'Content-Type':'application/json'},
|
|
39
|
+
body:JSON.stringify({messages:[{role:'user',content:document.getElementById('p').value}],max_tokens:128})});
|
|
40
|
+
const j=await r.json();
|
|
41
|
+
o.textContent = j.error ? ('error: '+j.error) : j.choices[0].message.content;
|
|
42
|
+
};
|
|
43
|
+
</script>"""
|
|
44
|
+
|
|
45
|
+
|
|
46
|
+
def build_prompt(tok, messages) -> str:
|
|
47
|
+
if getattr(tok, "chat_template", None):
|
|
48
|
+
return tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|
49
|
+
return "\n".join(m.get("content", "") for m in messages) + "\n"
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
class Handler(BaseHTTPRequestHandler):
|
|
53
|
+
protocol_version = "HTTP/1.1"
|
|
54
|
+
|
|
55
|
+
def _send(self, code: int, body: bytes, ctype: str = "application/json"):
|
|
56
|
+
self.send_response(code)
|
|
57
|
+
self.send_header("Content-Type", ctype)
|
|
58
|
+
self.send_header("Content-Length", str(len(body)))
|
|
59
|
+
self.send_header("Access-Control-Allow-Origin", "*")
|
|
60
|
+
self.end_headers()
|
|
61
|
+
self.wfile.write(body)
|
|
62
|
+
|
|
63
|
+
def do_GET(self):
|
|
64
|
+
if self.path == "/health":
|
|
65
|
+
self._send(200, json.dumps({"ok": True, "model": _state["model_id"]}).encode())
|
|
66
|
+
elif self.path in ("/", "/index.html"):
|
|
67
|
+
self._send(200, PAGE.encode(), "text/html; charset=utf-8")
|
|
68
|
+
else:
|
|
69
|
+
self._send(404, b'{"error":"not found"}')
|
|
70
|
+
|
|
71
|
+
def do_POST(self):
|
|
72
|
+
if self.path != "/v1/chat/completions":
|
|
73
|
+
return self._send(404, b'{"error":"not found"}')
|
|
74
|
+
try:
|
|
75
|
+
n = int(self.headers.get("Content-Length", "0"))
|
|
76
|
+
req = json.loads(self.rfile.read(n) or b"{}")
|
|
77
|
+
messages = req.get("messages") or [{"role": "user", "content": req.get("prompt", "")}]
|
|
78
|
+
max_new = int(req.get("max_tokens", 128))
|
|
79
|
+
prompt = build_prompt(_state["tok"], messages)
|
|
80
|
+
ids = _state["tok"](prompt, return_tensors="pt").to(_state["device"])
|
|
81
|
+
with _lock, torch.inference_mode():
|
|
82
|
+
out = _state["model"].generate(
|
|
83
|
+
**ids, max_new_tokens=max_new, do_sample=bool(req.get("temperature", 0) > 0),
|
|
84
|
+
temperature=float(req.get("temperature", 0.7) or 0.7),
|
|
85
|
+
top_p=float(req.get("top_p", 0.9)),
|
|
86
|
+
pad_token_id=_state["tok"].eos_token_id,
|
|
87
|
+
)
|
|
88
|
+
text = _state["tok"].decode(out[0][ids["input_ids"].shape[1]:],
|
|
89
|
+
skip_special_tokens=True).strip()
|
|
90
|
+
body = {
|
|
91
|
+
"object": "chat.completion",
|
|
92
|
+
"model": _state["model_id"],
|
|
93
|
+
"choices": [{"index": 0, "message": {"role": "assistant", "content": text},
|
|
94
|
+
"finish_reason": "stop"}],
|
|
95
|
+
"usage": {"prompt_tokens": int(ids["input_ids"].shape[1]),
|
|
96
|
+
"completion_tokens": int(out.shape[1] - ids["input_ids"].shape[1])},
|
|
97
|
+
}
|
|
98
|
+
self._send(200, json.dumps(body, ensure_ascii=False).encode())
|
|
99
|
+
except Exception as e: # keep the server alive, report the error
|
|
100
|
+
self._send(500, json.dumps({"error": f"{type(e).__name__}: {e}"}).encode())
|
|
101
|
+
|
|
102
|
+
def log_message(self, fmt, *args):
|
|
103
|
+
pass
|
|
104
|
+
|
|
105
|
+
|
|
106
|
+
def main(argv=None) -> int:
|
|
107
|
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
108
|
+
|
|
109
|
+
ap = argparse.ArgumentParser(prog="streamft serve")
|
|
110
|
+
ap.add_argument("--model", required=True, help="merged model dir or HF id")
|
|
111
|
+
ap.add_argument("--adapter", default="", help="optional adapter dir with adapter.pt")
|
|
112
|
+
ap.add_argument("--host", default="0.0.0.0")
|
|
113
|
+
ap.add_argument("--port", type=int, default=8000)
|
|
114
|
+
ap.add_argument("--device", default="cuda" if torch.cuda.is_available() else "cpu")
|
|
115
|
+
args = ap.parse_args(argv)
|
|
116
|
+
|
|
117
|
+
dtype = torch.bfloat16 if args.device == "cuda" else torch.float32
|
|
118
|
+
tok = AutoTokenizer.from_pretrained(args.model)
|
|
119
|
+
model = AutoModelForCausalLM.from_pretrained(args.model, torch_dtype=dtype).to(args.device).eval()
|
|
120
|
+
|
|
121
|
+
if args.adapter:
|
|
122
|
+
from pathlib import Path
|
|
123
|
+
|
|
124
|
+
from .lora import apply_lora, set_lora_state_dict
|
|
125
|
+
|
|
126
|
+
p = Path(args.adapter)
|
|
127
|
+
p = p / "adapter.pt" if p.is_dir() else p
|
|
128
|
+
state = torch.load(str(p), map_location="cpu", weights_only=True)
|
|
129
|
+
r = int(next(v for k, v in state.items() if k.endswith(".A")).shape[0])
|
|
130
|
+
apply_lora(model, r_attn=r, r_mlp=0)
|
|
131
|
+
set_lora_state_dict(model, state)
|
|
132
|
+
print(f"[serve] adapter {p.name} (r={r})", flush=True)
|
|
133
|
+
|
|
134
|
+
_state.update(model=model, tok=tok, device=args.device, model_id=args.model)
|
|
135
|
+
srv = ThreadingHTTPServer((args.host, args.port), Handler)
|
|
136
|
+
print(f"[serve] http://{args.host}:{args.port} (device {args.device})", flush=True)
|
|
137
|
+
print("[serve] others on the same network: http://<this-machine-ip>:%d" % args.port, flush=True)
|
|
138
|
+
try:
|
|
139
|
+
srv.serve_forever()
|
|
140
|
+
except KeyboardInterrupt:
|
|
141
|
+
pass
|
|
142
|
+
return 0
|
|
143
|
+
|
|
144
|
+
|
|
145
|
+
if __name__ == "__main__":
|
|
146
|
+
raise SystemExit(main())
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: streamft
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.5.0
|
|
4
4
|
Summary: Fine-tune models that do not fit: stream NF4 weights from disk, one transformer block at a time.
|
|
5
5
|
Author-email: Gokhan Cava <byjameson@users.noreply.github.com>
|
|
6
6
|
License: Apache-2.0
|
|
@@ -163,6 +163,34 @@ the same passage costs **1.13 tokens/word in English, 1.74 in German and 2.39 in
|
|
|
163
163
|
(LLaDA/Mercury: 800?1,500 tok/s at batch 1, but the same memory footprint) do not change
|
|
164
164
|
this project's bottleneck are in [`docs/TOKENIZERS.md`](docs/TOKENIZERS.md).
|
|
165
165
|
|
|
166
|
+
### Run it in a browser (no server)
|
|
167
|
+
|
|
168
|
+
```bash
|
|
169
|
+
streamft merge --model Qwen/Qwen2.5-0.5B --adapter checkpoints/cpu_cookbook --out merged/q05
|
|
170
|
+
powershell -ExecutionPolicy Bypass -File scripts/export_gguf.ps1 # -> q05-q4_k_m.gguf
|
|
171
|
+
python scripts/serve_static.py --port 8765
|
|
172
|
+
# open http://127.0.0.1:8765/wasm/index.html?model=../q05-q4_k_m.gguf
|
|
173
|
+
```
|
|
174
|
+
|
|
175
|
+
Measured on the reference laptop, 0.5B Q4_K_M (379 MB): **1.3 tok/s** with the plain
|
|
176
|
+
`http.server`, **6.0 tok/s** behind `scripts/serve_static.py` ? the COOP/COEP headers are
|
|
177
|
+
what let wllama use 12 threads instead of one. Details and limits in
|
|
178
|
+
[`wasm/README.md`](wasm/README.md).
|
|
179
|
+
|
|
180
|
+
### Share one machine on the LAN
|
|
181
|
+
|
|
182
|
+
One PC with the model can serve everyone on the same network:
|
|
183
|
+
|
|
184
|
+
```bash
|
|
185
|
+
streamft serve --model merged/q05_cpu --port 8000
|
|
186
|
+
# others open http://<that-machine-ip>:8000
|
|
187
|
+
```
|
|
188
|
+
|
|
189
|
+
It ships a small chat page and an OpenAI-compatible `POST /v1/chat/completions`, so existing
|
|
190
|
+
tools can point at it. This is **one machine computing, the rest as clients** ? not
|
|
191
|
+
peer-to-peer sharding and not volunteer compute. Tested end to end: `/health` and a
|
|
192
|
+
16-token completion (1.9 s on the reference GPU).
|
|
193
|
+
|
|
166
194
|
### Measured on
|
|
167
195
|
|
|
168
196
|
Every speed number here comes from **one machine**: RTX 3050 Laptop 6 GB, Windows 11,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|